{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/sigmoid-focal-loss","entry":"sigmoid_focal_loss","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":122,"n_papers_ran":89,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":46,"n_samples_ran":25,"n_samples_fingerprinted":8,"n_places":123,"n_places_pointer_only":43,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":22,"unverified":21},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2606.02178","paper":"/paper/arxiv-2606-02178","title":"Order within Chaos: Capturing Intrinsic Energy Anomalies for AI-Manipulated Image Forgery Localization","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"phoenixnir/FLAME","path":"FLAME/utils/metrics.py","file_url":"https://github.com/phoenixnir/FLAME/blob/HEAD/FLAME/utils/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fd031662f9fef178","mcp_get_code":{"code_sha256":"fd031662f9fef178"}},{"arxiv_id":"2602.01753","paper":"/paper/arxiv-2602-01753","title":"ObjEmbed: Towards Universal Multimodal Object Embeddings","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"WeChatCV/ObjEmbed","path":"models/qwen3vl_objembed.py","file_url":"https://github.com/WeChatCV/ObjEmbed/blob/HEAD/models/qwen3vl_objembed.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"34d3bd26e7ae4a9c","mcp_get_code":{"code_sha256":"34d3bd26e7ae4a9c"}},{"arxiv_id":"2601.01908","paper":"/paper/arxiv-2601-01908","title":"Nodule-DETR: A Novel DETR Architecture with Frequency-Channel Attention for Ultrasound Thyroid Nodule Detection","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"wjj1wjj/Nodule-DETR","path":"Nodule-DETR/models/DABDETR.py","file_url":"https://github.com/wjj1wjj/Nodule-DETR/blob/HEAD/Nodule-DETR/models/DABDETR.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2512.23427","paper":"/paper/arxiv-2512-23427","title":"Towards Integrating Uncertainty for Domain-Agnostic Segmentation","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"JesseBrouw/UncertSAM","path":"src/loss_fns.py","file_url":"https://github.com/JesseBrouw/UncertSAM/blob/HEAD/src/loss_fns.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"f655437ab080689e","mcp_get_code":{"code_sha256":"f655437ab080689e"}},{"arxiv_id":"2510.11417","paper":"/paper/arxiv-2510-11417","title":"Robust Ego-Exo Correspondence with Long-Term Memory","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"juneyeeHu/LM-EEC","path":"training/loss_fns.py","file_url":"https://github.com/juneyeeHu/LM-EEC/blob/HEAD/training/loss_fns.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"42fec6fdc1faf6f1","mcp_get_code":{"code_sha256":"42fec6fdc1faf6f1"}},{"arxiv_id":"2510.03853","paper":"/paper/arxiv-2510-03853","title":"UGround: Towards Unified Visual Grounding with Unrolled Transformers","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"rui-qian/UGround","path":"model/READ.py","file_url":"https://github.com/rui-qian/UGround/blob/HEAD/model/READ.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5e032c86b35b7a19","mcp_get_code":{"code_sha256":"5e032c86b35b7a19"}},{"arxiv_id":"2508.08612","paper":"/paper/arxiv-2508-08612","title":"Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"JiahuaDong/HVPL","path":"hvpl/modeling/vita_criterion.py","file_url":"https://github.com/JiahuaDong/HVPL/blob/HEAD/hvpl/modeling/vita_criterion.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f56d065ac11dd808","mcp_get_code":{"code_sha256":"f56d065ac11dd808"}},{"arxiv_id":"2507.19993","paper":null,"title":"arXiv:2507.19993","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"Howardkhh/FROSS","path":"EGTR/model/util.py","file_url":"https://github.com/Howardkhh/FROSS/blob/HEAD/EGTR/model/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"728119ce133dfec1","mcp_get_code":{"code_sha256":"728119ce133dfec1"}},{"arxiv_id":"2507.08555","paper":"/paper/disentangling-instance-and-scene-contexts-for","title":"Disentangling Instance and Scene Contexts for 3D Semantic Scene Completion","date":"2025-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Enyu-Liu/DISC","path":"maskdino/models/criterion.py","file_url":"https://github.com/Enyu-Liu/DISC/blob/HEAD/maskdino/models/criterion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2506.09985","paper":"/paper/v-jepa-2-self-supervised-video-models-enable","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","date":"2025-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/vjepa2","path":"evals/action_anticipation_frozen/losses.py","file_url":"https://github.com/facebookresearch/vjepa2/blob/HEAD/evals/action_anticipation_frozen/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"3d79c2bcb14adc04","mcp_get_code":{"code_sha256":"3d79c2bcb14adc04"}},{"arxiv_id":"2505.11726","paper":"/paper/disambiguating-reference-in-visually-grounded","title":"Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures","date":"2025-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ashkamath/mdetr","path":"models/segmentation.py","file_url":"https://github.com/ashkamath/mdetr/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2505.04270","paper":"/paper/object-shot-enhanced-grounding-network-for","title":"Object-Shot Enhanced Grounding Network for Egocentric Video","date":"2025-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yisen-Feng/OSGNet","path":"libs/modeling/losses.py","file_url":"https://github.com/Yisen-Feng/OSGNet/blob/HEAD/libs/modeling/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cb7608e384b5c1d7","mcp_get_code":{"code_sha256":"cb7608e384b5c1d7"}},{"arxiv_id":"2504.13181","paper":"/paper/perception-encoder-the-best-visual-embeddings","title":"Perception Encoder: The best visual embeddings are not at the output of the network","date":"2025-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/perception_models","path":"apps/detection/DETA_pe/models/segmentation.py","file_url":"https://github.com/facebookresearch/perception_models/blob/HEAD/apps/detection/DETA_pe/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2503.22405","paper":"/paper/modeling-multiple-normal-action","title":"Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks","date":"2025-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iSEE-Laboratory/AMNAR","path":"libs/modeling/losses.py","file_url":"https://github.com/iSEE-Laboratory/AMNAR/blob/HEAD/libs/modeling/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a617c27dff1d8aec","mcp_get_code":{"code_sha256":"a617c27dff1d8aec"}},{"arxiv_id":"2503.10616","paper":"/paper/ovtr-end-to-end-open-vocabulary-multiple","title":"OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer","date":"2025-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jinyanglii/OVTR","path":"ovtr/models/segmentation.py","file_url":"https://github.com/jinyanglii/OVTR/blob/HEAD/ovtr/models/segmentation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e830c3de135f1096","mcp_get_code":{"code_sha256":"e830c3de135f1096"}},{"arxiv_id":"2503.10616","paper":"/paper/ovtr-end-to-end-open-vocabulary-multiple","title":"OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer","date":"2025-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jinyanglii/OVTR","path":"ovtr/models/utils.py","file_url":"https://github.com/jinyanglii/OVTR/blob/HEAD/ovtr/models/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"23eb1c50e6bb2ba5","mcp_get_code":{"code_sha256":"23eb1c50e6bb2ba5"}},{"arxiv_id":"2503.09595","paper":"/paper/pisa-experiments-exploring-physics-post","title":"PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop","date":"2025-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vision-x-nyu/pisa-experiments","path":"sam2/training/loss_fns.py","file_url":"https://github.com/vision-x-nyu/pisa-experiments/blob/HEAD/sam2/training/loss_fns.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"42fec6fdc1faf6f1","mcp_get_code":{"code_sha256":"42fec6fdc1faf6f1"}},{"arxiv_id":"2412.12628","paper":"/paper/dense-audio-visual-event-localization-under","title":"Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration","date":"2024-12-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzhhfut/ccnet-aaai2025","path":"libs/modeling/losses.py","file_url":"https://github.com/zzhhfut/ccnet-aaai2025/blob/HEAD/libs/modeling/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e5b38592e26eef34","mcp_get_code":{"code_sha256":"e5b38592e26eef34"}},{"arxiv_id":"2412.09032","paper":"/paper/speech-forensics-towards-comprehensive","title":"Speech-Forensics: Towards Comprehensive Synthetic Speech Dataset Establishment and Analysis","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ring-zl/Speech-Forensics","path":"libs/modeling/losses.py","file_url":"https://github.com/ring-zl/Speech-Forensics/blob/HEAD/libs/modeling/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d06c0983d985a4a","mcp_get_code":{"code_sha256":"0d06c0983d985a4a"}},{"arxiv_id":"2412.08879","paper":"/paper/video-repurposing-from-user-generated-content","title":"Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yongliang-wu/repurpose","path":"models/losses.py","file_url":"https://github.com/yongliang-wu/repurpose/blob/HEAD/models/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5500f7dbd94b2c87","mcp_get_code":{"code_sha256":"5500f7dbd94b2c87"}},{"arxiv_id":"2411.17576","paper":"/paper/a-distractor-aware-memory-for-visual-object","title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","date":"2024-11-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jovanavidenovic/dam4sam","path":"training/loss_fns.py","file_url":"https://github.com/jovanavidenovic/dam4sam/blob/HEAD/training/loss_fns.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"42fec6fdc1faf6f1","mcp_get_code":{"code_sha256":"42fec6fdc1faf6f1"}},{"arxiv_id":"2409.17531","paper":"/paper/simvg-a-simple-framework-for-visual-grounding","title":"SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dmmm1997/simvg","path":"simvg/core/criterion/criterion.py","file_url":"https://github.com/dmmm1997/simvg/blob/HEAD/simvg/core/criterion/criterion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dff0f0000acdc0ad","mcp_get_code":{"code_sha256":"dff0f0000acdc0ad"}},{"arxiv_id":"2409.07541","paper":"/paper/enact-entropy-based-clustering-of-attention","title":"ENACT: Entropy-based Clustering of Attention Input for Improving the Computational Performance of Object Detection Transformers","date":"2024-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gsavathrakis/enact","path":"Anchor-DETR-ENACT/models/segmentation.py","file_url":"https://github.com/gsavathrakis/enact/blob/HEAD/Anchor-DETR-ENACT/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2408.07931","paper":"/paper/surgical-sam-2-real-time-segment-anything-in","title":"Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning","date":"2024-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jinlab-imvr/surgical-sam-2","path":"training/loss_fns.py","file_url":"https://github.com/jinlab-imvr/surgical-sam-2/blob/HEAD/training/loss_fns.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"42fec6fdc1faf6f1","mcp_get_code":{"code_sha256":"42fec6fdc1faf6f1"}},{"arxiv_id":"2408.01120","paper":"/paper/2408-01120","title":"An Efficient and Effective Transformer Decoder-Based Framework for Multi-Task Visual Grounding","date":"2024-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chenwei746/eevg","path":"utils/loss_utils.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/utils/loss_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0ce2b81bef4f1424","mcp_get_code":{"code_sha256":"0ce2b81bef4f1424"}},{"arxiv_id":"2408.01044","paper":"/paper/2408-01044","title":"Boosting Gaze Object Prediction via Pixel-level Supervision from Vision Foundation Model","date":"2024-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jinyang06/SamGOP","path":"maskGOP/modeling/criterion.py","file_url":"https://github.com/jinyang06/SamGOP/blob/HEAD/maskGOP/modeling/criterion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2408.00714","paper":"/paper/2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bowang-lab/medsam2","path":"training/loss_fns.py","file_url":"https://github.com/bowang-lab/medsam2/blob/HEAD/training/loss_fns.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"42fec6fdc1faf6f1","mcp_get_code":{"code_sha256":"42fec6fdc1faf6f1"}},{"arxiv_id":"2407.16696","paper":"/paper/partglee-a-foundation-model-for-recognizing","title":"PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ProvenceStar/PartGLEE","path":"projects/PartGLEE/partglee/models/criterion.py","file_url":"https://github.com/ProvenceStar/PartGLEE/blob/HEAD/projects/PartGLEE/partglee/models/criterion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2407.07402","paper":"/paper/actionvos-actions-as-prompts-for-video-object","title":"ActionVOS: Actions as Prompts for Video Object Segmentation","date":"2024-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ut-vision/ActionVOS","path":"RF_ActionVOS/segmentation.py","file_url":"https://github.com/ut-vision/ActionVOS/blob/HEAD/RF_ActionVOS/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2407.03197","paper":"/paper/dyfadet-dynamic-feature-aggregation-for","title":"DyFADet: Dynamic Feature Aggregation for Temporal Action Detection","date":"2024-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yangle15/DyFADet-pytorch","path":"libs/modeling/losses.py","file_url":"https://github.com/yangle15/DyFADet-pytorch/blob/HEAD/libs/modeling/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"54293ea22bd4f952","mcp_get_code":{"code_sha256":"54293ea22bd4f952"}},{"arxiv_id":"2406.05039","paper":"/paper/bootstrapping-referring-multi-object-tracking","title":"Bootstrapping Referring Multi-Object Tracking","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zyn213/temprmot","path":"models/segmentation.py","file_url":"https://github.com/zyn213/temprmot/blob/HEAD/models/segmentation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e830c3de135f1096","mcp_get_code":{"code_sha256":"e830c3de135f1096"}},{"arxiv_id":"2406.03459","paper":"/paper/lw-detr-a-transformer-replacement-to-yolo-for","title":"LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection","date":"2024-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"atten4vis/lw-detr","path":"models/lwdetr.py","file_url":"https://github.com/atten4vis/lw-detr/blob/HEAD/models/lwdetr.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2406.00670","paper":"/paper/cascade-clip-cascaded-vision-language","title":"Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation","date":"2024-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hvision-nku/cascade-clip","path":"models/losses/criterion.py","file_url":"https://github.com/hvision-nku/cascade-clip/blob/HEAD/models/losses/criterion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2675e89c94ae08bf","mcp_get_code":{"code_sha256":"2675e89c94ae08bf"}},{"arxiv_id":"2405.17913","paper":"/paper/ov-dquo-open-vocabulary-detr-with-denoising","title":"OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaomoguhz/ov-dquo","path":"models/ov_dquo/utils.py","file_url":"https://github.com/xiaomoguhz/ov-dquo/blob/HEAD/models/ov_dquo/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f09e169e2656c2f7","mcp_get_code":{"code_sha256":"f09e169e2656c2f7"}},{"arxiv_id":"2405.17427","paper":"/paper/reason3d-searching-and-reasoning-3d","title":"Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kuanchihhuang/reason3d","path":"lavis/models/reason3d_models/seg_loss.py","file_url":"https://github.com/kuanchihhuang/reason3d/blob/HEAD/lavis/models/reason3d_models/seg_loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"94629ea5eed6e387","mcp_get_code":{"code_sha256":"94629ea5eed6e387"}},{"arxiv_id":"2404.07610","paper":"/paper/do-you-remember-dense-video-captioning-with","title":"Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval","date":"2024-04-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ailab-kyunghee/cm2_dvc","path":"cm2/criterion.py","file_url":"https://github.com/ailab-kyunghee/cm2_dvc/blob/HEAD/cm2/criterion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2404.03179","paper":"/paper/uniav-unified-audio-visual-perception-for","title":"UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ttgeng233/UniAV","path":"libs/modeling/losses.py","file_url":"https://github.com/ttgeng233/UniAV/blob/HEAD/libs/modeling/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54293ea22bd4f952","mcp_get_code":{"code_sha256":"54293ea22bd4f952"}},{"arxiv_id":"2404.02257","paper":"/paper/snag-scalable-and-accurate-video-grounding","title":"SnAG: Scalable and Accurate Video Grounding","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"happyharrycn/actionformer_release","path":"libs/modeling/losses.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/modeling/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d06c0983d985a4a","mcp_get_code":{"code_sha256":"0d06c0983d985a4a"}},{"arxiv_id":"2404.02072","paper":"/paper/egtr-extracting-graph-from-transformer-for","title":"EGTR: Extracting Graph from Transformer for Scene Graph Generation","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver-ai/egtr","path":"model/util.py","file_url":"https://github.com/naver-ai/egtr/blob/HEAD/model/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"728119ce133dfec1","mcp_get_code":{"code_sha256":"728119ce133dfec1"}},{"arxiv_id":"2404.01725","paper":"/paper/disentangled-pre-training-for-human-object","title":"Disentangled Pre-training for Human-Object Interaction Detection","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xingaoli/DP-HOI","path":"models/segmentation.py","file_url":"https://github.com/xingaoli/DP-HOI/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2403.20126","paper":"/paper/eclipse-efficient-continual-learning-in","title":"ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning","date":"2024-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clovaai/ECLIPSE","path":"continual/method_wrapper/loss.py","file_url":"https://github.com/clovaai/ECLIPSE/blob/HEAD/continual/method_wrapper/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8820a1f39a3f1556","mcp_get_code":{"code_sha256":"8820a1f39a3f1556"}},{"arxiv_id":"2403.19407","paper":"/paper/towards-temporally-consistent-referring-video","title":"Temporally Consistent Referring Video Object Segmentation with Hybrid Memory","date":"2024-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bo-miao/HTR","path":"models/segmentation.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2403.17839","paper":"/paper/remamber-referring-image-segmentation-with","title":"ReMamber: Referring Image Segmentation with Mamba Twister","date":"2024-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yyh-rain-song/ReMamber","path":"model/utils.py","file_url":"https://github.com/yyh-rain-song/ReMamber/blob/HEAD/model/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"36be76eee5039426","mcp_get_code":{"code_sha256":"36be76eee5039426"}},{"arxiv_id":"2403.16848","paper":"/paper/multiple-object-tracking-as-id-prediction","title":"Multiple Object Tracking as ID Prediction","date":"2024-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MCG-NJU/MOTIP","path":"models/motip/id_criterion.py","file_url":"https://github.com/MCG-NJU/MOTIP/blob/HEAD/models/motip/id_criterion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a542c79696b8b5ae","mcp_get_code":{"code_sha256":"a542c79696b8b5ae"}},{"arxiv_id":"2403.14183","paper":"/paper/otseg-multi-prompt-sinkhorn-attention-for","title":"OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation","date":"2024-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cubeyoung/OTSeg","path":"models/losses/criterion.py","file_url":"https://github.com/cubeyoung/OTSeg/blob/HEAD/models/losses/criterion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2675e89c94ae08bf","mcp_get_code":{"code_sha256":"2675e89c94ae08bf"}},{"arxiv_id":"2403.06213","paper":"/paper/v-kd-improving-knowledge-distillation-using","title":"$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections","date":"2024-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"roymiles/vkd","path":"vidt/methods/vidt/criterion.py","file_url":"https://github.com/roymiles/vkd/blob/HEAD/vidt/methods/vidt/criterion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bf3a75e08dc2c405","mcp_get_code":{"code_sha256":"bf3a75e08dc2c405"}},{"arxiv_id":"2403.05297","paper":"/paper/peeb-part-based-image-classifiers-with-an","title":"PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck","date":"2024-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anguyen8/peeb","path":"src/owlvit_cls.py","file_url":"https://github.com/anguyen8/peeb/blob/HEAD/src/owlvit_cls.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"695ff74df95375df","mcp_get_code":{"code_sha256":"695ff74df95375df"}},{"arxiv_id":"2402.13578","paper":"/paper/transgop-transformer-based-gaze-object","title":"TransGOP: Transformer-Based Gaze Object Prediction","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chenxi-Guo/TransGOP","path":"models/TransGOP/segmentation.py","file_url":"https://github.com/chenxi-Guo/TransGOP/blob/HEAD/models/TransGOP/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2401.14159","paper":"/paper/grounded-sam-assembling-open-world-models-for","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","date":"2024-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"idea-research/groundingdino","path":"groundingdino/models/GroundingDINO/utils.py","file_url":"https://github.com/idea-research/groundingdino/blob/HEAD/groundingdino/models/GroundingDINO/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"23eb1c50e6bb2ba5","mcp_get_code":{"code_sha256":"23eb1c50e6bb2ba5"}},{"arxiv_id":"2401.10556","paper":"/paper/symbol-as-points-panoptic-symbol-spotting-via","title":"Symbol as Points: Panoptic Symbol Spotting via Point-based Representation","date":"2024-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicehuster/sympoint","path":"svgnet/model/criterion.py","file_url":"https://github.com/nicehuster/sympoint/blob/HEAD/svgnet/model/criterion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2401.03989","paper":"/paper/ms-detr-efficient-detr-training-with-mixed","title":"MS-DETR: Efficient DETR Training with Mixed Supervision","date":"2024-01-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"atten4vis/ms-detr","path":"models/segmentation.py","file_url":"https://github.com/atten4vis/ms-detr/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2312.09158","paper":"/paper/general-object-foundation-model-for-images","title":"General Object Foundation Model for Images and Videos at Scale","date":"2023-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FoundationVision/GLEE","path":"projects/GLEE/glee/models/criterion.py","file_url":"https://github.com/FoundationVision/GLEE/blob/HEAD/projects/GLEE/glee/models/criterion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2312.06505","paper":"/paper/grounded-question-answering-in-long","title":"Grounded Question-Answering in Long Egocentric Videos","date":"2023-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"becomebright/groundvqa","path":"model/ours/nlq_head.py","file_url":"https://github.com/becomebright/groundvqa/blob/HEAD/model/ours/nlq_head.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7b7c8610c42bb07c","mcp_get_code":{"code_sha256":"7b7c8610c42bb07c"}},{"arxiv_id":"2312.03203","paper":"/paper/feature-3dgs-supercharging-3d-gaussian","title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","date":"2023-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keloee/maskfield","path":"models/losses.py","file_url":"https://github.com/keloee/maskfield/blob/HEAD/models/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"71e149dc0c33b040","mcp_get_code":{"code_sha256":"71e149dc0c33b040"}},{"arxiv_id":"2312.02158","paper":"/paper/pasco-urban-3d-panoptic-scene-completion-with","title":"PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"astra-vision/PaSCo","path":"pasco/loss/losses.py","file_url":"https://github.com/astra-vision/PaSCo/blob/HEAD/pasco/loss/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"549df7244d5a6b10","mcp_get_code":{"code_sha256":"549df7244d5a6b10"}},{"arxiv_id":"2310.08854","paper":"/paper/rank-detr-for-high-quality-object-detection","title":"Rank-DETR for High Quality Object Detection","date":"2023-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LeapLabTHU/Rank-DETR","path":"projects/rank_detr/modeling/rankdetr_criterion.py","file_url":"https://github.com/LeapLabTHU/Rank-DETR/blob/HEAD/projects/rank_detr/modeling/rankdetr_criterion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"dff0f0000acdc0ad","mcp_get_code":{"code_sha256":"dff0f0000acdc0ad"}},{"arxiv_id":"2310.08530","paper":"/paper/unipose-detecting-any-keypoints","title":"X-Pose: Detecting Any Keypoints","date":"2023-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDEA-Research/UniPose","path":"models/UniPose/utils.py","file_url":"https://github.com/IDEA-Research/UniPose/blob/HEAD/models/UniPose/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"23eb1c50e6bb2ba5","mcp_get_code":{"code_sha256":"23eb1c50e6bb2ba5"}},{"arxiv_id":"2309.01017","paper":"/paper/contrastive-grouping-with-transformer-for-1","title":"Contrastive Grouping with Transformer for Referring Image Segmentation","date":"2023-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"toneyaya/cgformer","path":"model/segmenter.py","file_url":"https://github.com/toneyaya/cgformer/blob/HEAD/model/segmenter.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e71d9c7dd14f39b8","mcp_get_code":{"code_sha256":"e71d9c7dd14f39b8"}},{"arxiv_id":"2308.14575","paper":"/paper/referring-image-segmentation-using-text","title":"Referring Image Segmentation Using Text Supervision","date":"2023-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fawnliu/tris","path":"loss/seg_loss.py","file_url":"https://github.com/fawnliu/tris/blob/HEAD/loss/seg_loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9cf331c90b5daee7","mcp_get_code":{"code_sha256":"9cf331c90b5daee7"}},{"arxiv_id":"2308.09905","paper":"/paper/diffusiontrack-diffusion-model-for-multi","title":"DiffusionTrack: Diffusion Model For Multi-Object Tracking","date":"2023-08-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rainbowluocs/diffusiontrack","path":"yolox/models/losses.py","file_url":"https://github.com/rainbowluocs/diffusiontrack/blob/HEAD/yolox/models/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"774f31ba06110943","mcp_get_code":{"code_sha256":"774f31ba06110943"}},{"arxiv_id":"2308.09351","paper":"/paper/rlipv2-fast-scaling-of-relational-language","title":"RLIPv2: Fast Scaling of Relational Language-Image Pre-training","date":"2023-08-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jacobyuan7/ocn-hoi-benchmark","path":"models/segmentation.py","file_url":"https://github.com/jacobyuan7/ocn-hoi-benchmark/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2308.08182","paper":"/paper/unsupervised-domain-adaptive-detection-with","title":"Unsupervised Domain Adaptive Detection with Network Stability Analysis","date":"2023-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tiankongzhang/nsa","path":"detection/layers/losses.py","file_url":"https://github.com/tiankongzhang/nsa/blob/HEAD/detection/layers/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b4ba161af9015512","mcp_get_code":{"code_sha256":"b4ba161af9015512"}},{"arxiv_id":"2308.07313","paper":"/paper/group-pose-a-simple-baseline-for-end-to-end","title":"Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation","date":"2023-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Michel-liu/GroupPose","path":"models/grouppose/utils.py","file_url":"https://github.com/Michel-liu/GroupPose/blob/HEAD/models/grouppose/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2308.04409","paper":"/paper/v-detr-detr-with-vertex-relative-position","title":"V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection","date":"2023-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yichaoshen-ms/v-detr","path":"criterion.py","file_url":"https://github.com/yichaoshen-ms/v-detr/blob/HEAD/criterion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2308.01045","paper":"/paper/dynamic-token-pruning-in-plain-vision","title":"Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation","date":"2023-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zbwxp/Dynamic-Token-Pruning","path":"mmseg_custom/loss/criterion.py","file_url":"https://github.com/zbwxp/Dynamic-Token-Pruning/blob/HEAD/mmseg_custom/loss/criterion.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"71e149dc0c33b040","mcp_get_code":{"code_sha256":"71e149dc0c33b040"}},{"arxiv_id":"2307.15700","paper":"/paper/memotr-long-term-memory-augmented-transformer","title":"MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking","date":"2023-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mcg-nju/memotr","path":"models/criterion.py","file_url":"https://github.com/mcg-nju/memotr/blob/HEAD/models/criterion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a542c79696b8b5ae","mcp_get_code":{"code_sha256":"a542c79696b8b5ae"}},{"arxiv_id":"2307.14786","paper":"/paper/towards-deeply-unified-depth-aware-panoptic","title":"Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning","date":"2023-07-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jwh97nn/DeepDPS","path":"model/loss.py","file_url":"https://github.com/jwh97nn/DeepDPS/blob/HEAD/model/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b27de4fc1aeb35a","mcp_get_code":{"code_sha256":"9b27de4fc1aeb35a"}},{"arxiv_id":"2307.12239","paper":"/paper/dq-det-learning-dynamic-query-combinations","title":"Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation","date":"2023-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/DQ-Det","path":"Cond-DETR-DQ/models/segmentation.py","file_url":"https://github.com/bytedance/DQ-Det/blob/HEAD/Cond-DETR-DQ/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2307.11828","paper":"/paper/enhancing-your-trained-detrs-with-box","title":"Enhancing Your Trained DETRs with Box Refinement","date":"2023-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yiqunchen1999/refinebox","path":"refinebox/models/layers/criterion.py","file_url":"https://github.com/yiqunchen1999/refinebox/blob/HEAD/refinebox/models/layers/criterion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e584d922cadbfdce","mcp_get_code":{"code_sha256":"e584d922cadbfdce"}},{"arxiv_id":"2307.05916","paper":"/paper/swift-swin-4d-fmri-transformer-1","title":"SwiFT: Swin 4D fMRI Transformer","date":"2023-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Project-MONAI/MONAI","path":"monai/losses/focal_loss.py","file_url":"https://github.com/Project-MONAI/MONAI/blob/HEAD/monai/losses/focal_loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0a9007867090337a","mcp_get_code":{"code_sha256":"0a9007867090337a"}},{"arxiv_id":"2306.15670","paper":"/paper/symphonize-3d-semantic-scene-completion-with","title":"Symphonize 3D Semantic Scene Completion with Contextual Instance Queries","date":"2023-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hustvl/symphonies","path":"maskdino/models/criterion.py","file_url":"https://github.com/hustvl/symphonies/blob/HEAD/maskdino/models/criterion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2306.09347","paper":"/paper/segment-any-point-cloud-sequences-by","title":"Segment Any Point Cloud Sequences by Distilling Vision Foundation Models","date":"2023-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDEA-Research/OpenSeeD","path":"openseed/modules/criterion.py","file_url":"https://github.com/IDEA-Research/OpenSeeD/blob/HEAD/openseed/modules/criterion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2305.13921","paper":"/paper/compositional-text-to-image-synthesis-with","title":"Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OPPO-Mente-Lab/attention-mask-control","path":"boxnet_models/segmentation.py","file_url":"https://github.com/OPPO-Mente-Lab/attention-mask-control/blob/HEAD/boxnet_models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2305.04276","paper":"/paper/adaptiveclick-clicks-aware-transformer-with","title":"AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation","date":"2023-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lab206/adaptiveclick","path":"isegm/model/criterion.py","file_url":"https://github.com/lab206/adaptiveclick/blob/HEAD/isegm/model/criterion.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"71e149dc0c33b040","mcp_get_code":{"code_sha256":"71e149dc0c33b040"}},{"arxiv_id":"2304.07527","paper":"/paper/align-detr-improving-detr-with-simple-iou","title":"Align-DETR: Enhancing End-to-end Object Detection with Aligned Loss","date":"2023-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"felixcaae/aligndetr","path":"aligndetr/losses/losses.py","file_url":"https://github.com/felixcaae/aligndetr/blob/HEAD/aligndetr/losses/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"dff0f0000acdc0ad","mcp_get_code":{"code_sha256":"dff0f0000acdc0ad"}},{"arxiv_id":"2304.04742","paper":"/paper/detection-transformer-with-stable-matching","title":"Detection Transformer with Stable Matching","date":"2023-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDEA-Research/Stable-DINO","path":"projects/stabledino/modeling/dn_criterion.py","file_url":"https://github.com/IDEA-Research/Stable-DINO/blob/HEAD/projects/stabledino/modeling/dn_criterion.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"97059585f50ae421","mcp_get_code":{"code_sha256":"97059585f50ae421"}},{"arxiv_id":"2303.14404","paper":"/paper/bridging-precision-and-confidence-a-train","title":"Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection","date":"2023-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2303.12930","paper":"/paper/dense-localizing-audio-visual-events-in","title":"Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline","date":"2023-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ttgeng233/UnAV","path":"libs/modeling/losses.py","file_url":"https://github.com/ttgeng233/UnAV/blob/HEAD/libs/modeling/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54293ea22bd4f952","mcp_get_code":{"code_sha256":"54293ea22bd4f952"}},{"arxiv_id":"2303.07347","paper":"/paper/tridet-temporal-action-detection-with","title":"TriDet: Temporal Action Detection with Relative Boundary Modeling","date":"2023-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dingfengshi/TriDet","path":"libs/modeling/losses.py","file_url":"https://github.com/dingfengshi/TriDet/blob/HEAD/libs/modeling/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54293ea22bd4f952","mcp_get_code":{"code_sha256":"54293ea22bd4f952"}},{"arxiv_id":"2302.11084","paper":"/paper/distribution-normalization-an-effortless-test","title":"Test-Time Distribution Normalization for Contrastively Learned Vision-language Models","date":"2023-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2302.01872","paper":"/paper/mose-a-new-dataset-for-video-object","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","date":"2023-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"henghuiding/MOSE-api","path":"MOSEv2/sam2_rcms/training/loss_fns.py","file_url":"https://github.com/henghuiding/MOSE-api/blob/HEAD/MOSEv2/sam2_rcms/training/loss_fns.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"42fec6fdc1faf6f1","mcp_get_code":{"code_sha256":"42fec6fdc1faf6f1"}},{"arxiv_id":"2212.03588","paper":"/paper/zegclip-towards-adapting-clip-for-zero-shot","title":"ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation","date":"2022-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZiqinZhou66/ZegCLIP","path":"models/losses/criterion.py","file_url":"https://github.com/ZiqinZhou66/ZegCLIP/blob/HEAD/models/losses/criterion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2675e89c94ae08bf","mcp_get_code":{"code_sha256":"2675e89c94ae08bf"}},{"arxiv_id":"2211.16799","paper":"/paper/nope-sac-neural-one-plane-ransac-for-sparse","title":"NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction","date":"2022-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"icetttb/nopesac","path":"NopeSAC_Net/modeling/criterion.py","file_url":"https://github.com/icetttb/nopesac/blob/HEAD/NopeSAC_Net/modeling/criterion.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"71e149dc0c33b040","mcp_get_code":{"code_sha256":"71e149dc0c33b040"}},{"arxiv_id":"2211.11953","paper":"/paper/teach-detr-better-training-detr-with-teachers","title":"Teach-DETR: Better Training DETR with Teachers","date":"2022-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leonhlj/teach-detr","path":"H-Deformable-DETR/models/segmentation.py","file_url":"https://github.com/leonhlj/teach-detr/blob/HEAD/H-Deformable-DETR/models/segmentation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"155608ecaae7d2ec","mcp_get_code":{"code_sha256":"155608ecaae7d2ec"}},{"arxiv_id":"2210.05176","paper":"/paper/fine-grained-image-style-transfer-with-visual","title":"Fine-Grained Image Style Transfer with Visual Transformers","date":"2022-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"researchmm/sttr","path":"models_istt/segmentation.py","file_url":"https://github.com/researchmm/sttr/blob/HEAD/models_istt/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2207.13325","paper":"/paper/siri-a-simple-selective-retraining-mechanism","title":"SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding","date":"2022-07-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qumengxue/siri-vg","path":"models/segmentation.py","file_url":"https://github.com/qumengxue/siri-vg/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2207.13080","paper":"/paper/detrs-with-hybrid-matching","title":"DETRs with Hybrid Matching","date":"2022-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HDETR/H-Deformable-DETR","path":"models/segmentation.py","file_url":"https://github.com/HDETR/H-Deformable-DETR/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2207.07097","paper":"/paper/react-temporal-action-detection-with","title":"ReAct: Temporal Action Detection with Relational Queries","date":"2022-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sssste/React","path":"React/model/React.py","file_url":"https://github.com/sssste/React/blob/HEAD/React/model/React.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2043ee96aadac29d","mcp_get_code":{"code_sha256":"2043ee96aadac29d"}},{"arxiv_id":"2206.02777","paper":"/paper/mask-dino-towards-a-unified-transformer-based-1","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","date":"2022-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDEA-opensource/DN-DETR","path":"models/DN_DAB_DETR/DABDETR.py","file_url":"https://github.com/IDEA-opensource/DN-DETR/blob/HEAD/models/DN_DAB_DETR/DABDETR.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2206.00468","paper":"/paper/panopticdepth-a-unified-framework-for-depth","title":"PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation","date":"2022-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NaiyuGao/PanopticDepth","path":"projects/PanopticDepth/panoptic_depth/loss.py","file_url":"https://github.com/NaiyuGao/PanopticDepth/blob/HEAD/projects/PanopticDepth/panoptic_depth/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b27de4fc1aeb35a","mcp_get_code":{"code_sha256":"9b27de4fc1aeb35a"}},{"arxiv_id":"2204.02932","paper":"/paper/an-empirical-study-of-end-to-end-temporal","title":"An Empirical Study of End-to-End Temporal Action Detection","date":"2022-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xlliu7/E2E-TAD","path":"models/custom_loss.py","file_url":"https://github.com/xlliu7/E2E-TAD/blob/HEAD/models/custom_loss.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2203.03605","paper":"/paper/dino-detr-with-improved-denoising-anchor-1","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","date":"2022-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDEACVR/MaskDINO","path":"maskdino/modeling/criterion.py","file_url":"https://github.com/IDEACVR/MaskDINO/blob/HEAD/maskdino/modeling/criterion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2203.01305","paper":"/paper/dn-detr-accelerate-detr-training-by","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","date":"2022-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FengLi-ust/DN-DETR","path":"models/DN_DAB_DETR/DABDETR.py","file_url":"https://github.com/FengLi-ust/DN-DETR/blob/HEAD/models/DN_DAB_DETR/DABDETR.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2201.12329","paper":"/paper/dab-detr-dynamic-anchor-boxes-are-better-1","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","date":"2022-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDEA-Research/DAB-DETR","path":"models/DAB_DETR/DABDETR.py","file_url":"https://github.com/IDEA-Research/DAB-DETR/blob/HEAD/models/DAB_DETR/DABDETR.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2201.05047","paper":"/paper/transvod-end-to-end-video-object-detection","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","date":"2022-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SJTU-LuHe/TransVOD","path":"models/segmentation.py","file_url":"https://github.com/SJTU-LuHe/TransVOD/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2112.08647","paper":"/paper/qahoi-query-based-anchors-for-human-object","title":"QAHOI: Query-Based Anchors for Human-Object Interaction Detection","date":"2021-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cjw2021/QAHOI","path":"models/QAHOI.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/models/QAHOI.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2112.04888","paper":"/paper/a-bilingual-openworld-video-text-dataset-and","title":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer","date":"2021-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weijiawu/transvtspotter","path":"models/segmentation.py","file_url":"https://github.com/weijiawu/transvtspotter/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2111.14821","paper":"/paper/end-to-end-referring-video-object","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","date":"2021-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mttr2021/MTTR","path":"models/segmentation.py","file_url":"https://github.com/mttr2021/MTTR/blob/HEAD/models/segmentation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"71e149dc0c33b040","mcp_get_code":{"code_sha256":"71e149dc0c33b040"}},{"arxiv_id":"2110.06864","paper":"/paper/bytetrack-multi-object-tracking-by-1","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","date":"2021-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ifzhang/ByteTrack","path":"yolox/models/losses.py","file_url":"https://github.com/ifzhang/ByteTrack/blob/HEAD/yolox/models/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"774f31ba06110943","mcp_get_code":{"code_sha256":"774f31ba06110943"}},{"arxiv_id":"2109.10852","paper":"/paper/pix2seq-a-language-modeling-framework-for","title":"Pix2seq: A Language Modeling Framework for Object Detection","date":"2021-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gaopengcuhk/Unofficial-Pix2Seq","path":"models/segmentation.py","file_url":"https://github.com/gaopengcuhk/Unofficial-Pix2Seq/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2108.07781","paper":"/paper/end-to-end-dense-video-captioning-with","title":"End-to-End Dense Video Captioning with Parallel Decoding","date":"2021-08-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ttengwang/pdvc","path":"pdvc/criterion.py","file_url":"https://github.com/ttengwang/pdvc/blob/HEAD/pdvc/criterion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2108.07682","paper":"/paper/fully-convolutional-networks-for-panoptic-1","title":"Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision","date":"2021-08-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/panopticfcn","path":"panopticfcn/loss.py","file_url":"https://github.com/dvlab-research/panopticfcn/blob/HEAD/panopticfcn/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b27de4fc1aeb35a","mcp_get_code":{"code_sha256":"9b27de4fc1aeb35a"}},{"arxiv_id":"2108.06152","paper":"/paper/conditional-detr-for-fast-training","title":"Conditional DETR for Fast Training Convergence","date":"2021-08-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"atten4vis/conditionaldetr","path":"models/segmentation.py","file_url":"https://github.com/atten4vis/conditionaldetr/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2106.04550","paper":"/paper/detreg-unsupervised-pretraining-with-region","title":"DETReg: Unsupervised Pretraining with Region Priors for Object Detection","date":"2021-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amirbar/detreg","path":"models/segmentation.py","file_url":"https://github.com/amirbar/detreg/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2104.12763","paper":"/paper/mdetr-modulated-detection-for-end-to-end","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"b-faye/lightmdetr","path":"models/segmentation.py","file_url":"https://github.com/b-faye/lightmdetr/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2103.12115","paper":"/paper/end-to-end-trainable-multi-instance-pose","title":"End-to-End Trainable Multi-Instance Pose Estimation with Transformers","date":"2021-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pranoyr/pose-estimation-with-transformers","path":"models/segmentation.py","file_url":"https://github.com/pranoyr/pose-estimation-with-transformers/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2103.11731","paper":"/paper/meta-detr-few-shot-object-detection-via","title":"Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation","date":"2021-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhangGongjie/Meta-DETR","path":"models/meta_detr.py","file_url":"https://github.com/ZhangGongjie/Meta-DETR/blob/HEAD/models/meta_detr.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2010.04159","paper":"/paper/deformable-detr-deformable-transformers-for-1","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","date":"2020-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Cedric-Perauer/Deformable_Detr_PIL","path":"models/segmentation.py","file_url":"https://github.com/Cedric-Perauer/Deformable_Detr_PIL/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2005.12872","paper":"/paper/end-to-end-object-detection-with-transformers","title":"End-to-End Object Detection with Transformers","date":"2020-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/detr","path":"models/segmentation.py","file_url":"https://github.com/facebookresearch/detr/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"2004.10934","paper":"/paper/yolov4-optimal-speed-and-accuracy-of-object","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","date":"2020-04-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Gavino7/YOLOv3set","path":"yolo3/loss.py","file_url":"https://github.com/Gavino7/YOLOv3set/blob/HEAD/yolo3/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"119b2c846dc6f0bd","mcp_get_code":{"code_sha256":"119b2c846dc6f0bd"}},{"arxiv_id":"1911.08287","paper":"/paper/distance-iou-loss-faster-and-better-learning","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","date":"2019-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"grifon-239/diploma","path":"yolo3/loss.py","file_url":"https://github.com/grifon-239/diploma/blob/HEAD/yolo3/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"119b2c846dc6f0bd","mcp_get_code":{"code_sha256":"119b2c846dc6f0bd"}},{"arxiv_id":"ijcai2022_0136","paper":null,"title":"arXiv:ijcai2022_0136","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"weii41392/AQT","path":"models/segmentation.py","file_url":"https://github.com/weii41392/AQT/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"aaai_27844","paper":null,"title":"arXiv:aaai_27844","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"retsuh-bqw/SRFormer-Text-Det","path":"adet/modeling/srformer/losses.py","file_url":"https://github.com/retsuh-bqw/SRFormer-Text-Det/blob/HEAD/adet/modeling/srformer/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"47bae639172d422d","mcp_get_code":{"code_sha256":"47bae639172d422d"}},{"arxiv_id":"Zohar_PROB_Probabilistic_Objectness_for_Open_World_Object_Detection_CVPR_2023_paper","paper":null,"title":"arXiv:Zohar_PROB_Probabilistic_Objectness_for_Open_World_Object_Detection_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"orrzohar/PROB","path":"models/prob_deformable_detr.py","file_url":"https://github.com/orrzohar/PROB/blob/HEAD/models/prob_deformable_detr.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"35de310b2622fc82","mcp_get_code":{"code_sha256":"35de310b2622fc82"}},{"arxiv_id":"Zhang_MonoDETR_Depth-guided_Transformer_for_Monocular_3D_Object_Detection_ICCV_2023_paper","paper":null,"title":"arXiv:Zhang_MonoDETR_Depth-guided_Transformer_for_Monocular_3D_Object_Detection_ICCV_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ZrrSkywalker/MonoDETR","path":"lib/models/monodetr/dn_components.py","file_url":"https://github.com/ZrrSkywalker/MonoDETR/blob/HEAD/lib/models/monodetr/dn_components.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"Wang_Zero-TPrune_Zero-Shot_Token_Pruning_through_Leveraging_of_the_Attention_Graph_CVPR_2024_paper","paper":null,"title":"arXiv:Wang_Zero-TPrune_Zero-Shot_Token_Pruning_through_Leveraging_of_the_Attention_Graph_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"facebookresearch/fvcore","path":"fvcore/nn/focal_loss.py","file_url":"https://github.com/facebookresearch/fvcore/blob/HEAD/fvcore/nn/focal_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"008567e35a2248cd","mcp_get_code":{"code_sha256":"008567e35a2248cd"}},{"arxiv_id":"Qian_Reasoning_to_Attend_Try_to_Understand_How_SEG_Token_Works_CVPR_2025_paper","paper":null,"title":"arXiv:Qian_Reasoning_to_Attend_Try_to_Understand_How_SEG_Token_Works_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"rui-qian/READ","path":"model/READ.py","file_url":"https://github.com/rui-qian/READ/blob/HEAD/model/READ.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9faec9878faf6267","mcp_get_code":{"code_sha256":"9faec9878faf6267"}},{"arxiv_id":"Pu_MonoDGP_Monocular_3D_Object_Detection_with_Decoupled-Query_and_Geometry-Error_Priors_CVPR_2025_paper","paper":null,"title":"arXiv:Pu_MonoDGP_Monocular_3D_Object_Detection_with_Decoupled-Query_and_Geometry-Error_Priors_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"PuFanqi23/MonoDGP","path":"lib/models/monodgp/dn_components.py","file_url":"https://github.com/PuFanqi23/MonoDGP/blob/HEAD/lib/models/monodgp/dn_components.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"Pan_Wnet_Audio-Guided_Video_Object_Segmentation_via_Wavelet-Based_Cross-Modal_Denoising_Networks_CVPR_2022_paper","paper":null,"title":"arXiv:Pan_Wnet_Audio-Guided_Video_Object_Segmentation_via_Wavelet-Based_Cross-Modal_Denoising_Networks_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"asudahkzj/Wnet","path":"models/segmentation.py","file_url":"https://github.com/asudahkzj/Wnet/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"Nguyen_BoxeR_Box-Attention_for_2D_and_3D_Transformers_CVPR_2022_paper","paper":null,"title":"arXiv:Nguyen_BoxeR_Box-Attention_for_2D_and_3D_Transformers_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"kienduynguyen/BoxeR","path":"e2edet/criterion/losses.py","file_url":"https://github.com/kienduynguyen/BoxeR/blob/HEAD/e2edet/criterion/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"43cd2397d20c992f","mcp_get_code":{"code_sha256":"43cd2397d20c992f"}},{"arxiv_id":"Liu_SAP-DETR_Bridging_the_Gap_Between_Salient_Points_and_Queries-Based_Transformer_CVPR_2023_paper","paper":null,"title":"arXiv:Liu_SAP-DETR_Bridging_the_Gap_Between_Salient_Points_and_Queries-Based_Transformer_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"liuyang-ict/SAP-DETR","path":"models/SAP_DETR/SAPDETR.py","file_url":"https://github.com/liuyang-ict/SAP-DETR/blob/HEAD/models/SAP_DETR/SAPDETR.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"Li_Mask_DINO_Towards_a_Unified_Transformer-Based_Framework_for_Object_Detection_CVPR_2023_paper","paper":null,"title":"arXiv:Li_Mask_DINO_Towards_a_Unified_Transformer-Based_Framework_for_Object_Detection_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"IDEA-Research/MaskDINO","path":"maskdino/modeling/criterion.py","file_url":"https://github.com/IDEA-Research/MaskDINO/blob/HEAD/maskdino/modeling/criterion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"arxiv_id":"Chen_Recurrent_Glimpse-Based_Decoder_for_Detection_With_Transformer_CVPR_2022_paper","paper":null,"title":"arXiv:Chen_Recurrent_Glimpse-Based_Decoder_for_Detection_With_Transformer_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zhechen/Deformable-DETR-REGO","path":"models/segmentation.py","file_url":"https://github.com/zhechen/Deformable-DETR-REGO/blob/HEAD/models/segmentation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"5c0711aada67957e","mcp_get_code":{"code_sha256":"5c0711aada67957e"}}]}