{"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/nestedtensor","entry":"NestedTensor","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":24,"n_papers_ran":23,"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":26,"n_samples_ran":24,"n_samples_fingerprinted":0,"n_places":26,"n_places_pointer_only":8,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":24,"unverified":2},"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":"2601.02212","paper":"/paper/arxiv-2601-02212","title":"Prior-Guided DETR for Ultrasound Nodule Detection","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"wjj1wjj/Ultrasound-DETR","path":"models/dn_dab_deformable_detr/dab_deformable_detr.py","file_url":"https://github.com/wjj1wjj/Ultrasound-DETR/blob/HEAD/models/dn_dab_deformable_detr/dab_deformable_detr.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5fcd889ee3ae8609","mcp_get_code":{"code_sha256":"5fcd889ee3ae8609"}},{"arxiv_id":"2410.08021","paper":"/paper/oneref-unified-one-tower-expression-grounding","title":"OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linhuixiao/hivg","path":"models/HiVG.py","file_url":"https://github.com/linhuixiao/hivg/blob/HEAD/models/HiVG.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5a5b1be86e3ab9a4","mcp_get_code":{"code_sha256":"5a5b1be86e3ab9a4"}},{"arxiv_id":"2407.03200","paper":"/paper/segvg-transferring-object-bounding-box-to","title":"SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding","date":"2024-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WeitaiKang/SegVG","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b636bcda4557023e","mcp_get_code":{"code_sha256":"b636bcda4557023e"}},{"arxiv_id":"2404.04624","paper":"/paper/bridging-the-gap-between-end-to-end-and-two","title":"Bridging the Gap Between End-to-End and Two-Step Text Spotting","date":"2024-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mxin262/estextspotter","path":"models/ests/ests.py","file_url":"https://github.com/mxin262/estextspotter/blob/HEAD/models/ests/ests.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6efd3189a09cd0af","mcp_get_code":{"code_sha256":"6efd3189a09cd0af"}},{"arxiv_id":"2403.19128","paper":"/paper/omniparser-a-unified-framework-for-text","title":"OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition","date":"2024-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibabaresearch/advancedliteratemachinery","path":"OCR/OmniParser/model/omniparser.py","file_url":"https://github.com/alibabaresearch/advancedliteratemachinery/blob/HEAD/OCR/OmniParser/model/omniparser.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"884dfe13daaf09f7","mcp_get_code":{"code_sha256":"884dfe13daaf09f7"}},{"arxiv_id":"2403.12042","paper":"/paper/exploring-pre-trained-text-to-video-diffusion","title":"Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation","date":"2024-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"buxiangzhiren/VD-IT","path":"models/diffvos_cross.py","file_url":"https://github.com/buxiangzhiren/VD-IT/blob/HEAD/models/diffvos_cross.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"04e2b0ca4fcbb7b1","mcp_get_code":{"code_sha256":"04e2b0ca4fcbb7b1"}},{"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/memotr.py","file_url":"https://github.com/MCG-NJU/MeMOTR/blob/HEAD/models/memotr.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9e000b2a48eac77c","mcp_get_code":{"code_sha256":"9e000b2a48eac77c"}},{"arxiv_id":"2303.14395","paper":"/paper/mdqe-mining-discriminative-query-embeddings","title":"MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos","date":"2023-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MinghanLi/MDQE_CVPR2023","path":"mdqe/models/mdqe.py","file_url":"https://github.com/MinghanLi/MDQE_CVPR2023/blob/HEAD/mdqe/models/mdqe.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"07f457fdc5fd31da","mcp_get_code":{"code_sha256":"07f457fdc5fd31da"}},{"arxiv_id":"2303.12027","paper":"/paper/joint-visual-grounding-and-tracking-with","title":"Joint Visual Grounding and Tracking with Natural Language Specification","date":"2023-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lizhou-cs/JointNLT","path":"lib/models/JointNLT.py","file_url":"https://github.com/lizhou-cs/JointNLT/blob/HEAD/lib/models/JointNLT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d2de70e6e6e2beee","mcp_get_code":{"code_sha256":"d2de70e6e6e2beee"}},{"arxiv_id":"2303.05675","paper":"/paper/humanbench-towards-general-human-centric","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","date":"2023-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenGVLab/HumanBench","path":"PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","file_url":"https://github.com/OpenGVLab/HumanBench/blob/HEAD/PATH/core/models/backbones/vitdet_for_ladder_attention_share_pos_embed.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39af89396152713c","mcp_get_code":{"code_sha256":"39af89396152713c"}},{"arxiv_id":"2301.10559","paper":"/paper/tracking-different-ant-species-an","title":"Tracking Different Ant Species: An Unsupervised Domain Adaptation Framework and a Dataset for Multi-object Tracking","date":"2023-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chamathabeysinghe/da-tracker","path":"src/trackformer/models/detr_tracking.py","file_url":"https://github.com/chamathabeysinghe/da-tracker/blob/HEAD/src/trackformer/models/detr_tracking.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"da09cbd482f7f33f","mcp_get_code":{"code_sha256":"da09cbd482f7f33f"}},{"arxiv_id":"2210.10775","paper":"/paper/toist-task-oriented-instance-segmentation","title":"TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation","date":"2022-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"air-discover/toist","path":"models/mdetr.py","file_url":"https://github.com/air-discover/toist/blob/HEAD/models/mdetr.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2fbce65b2ac327b","mcp_get_code":{"code_sha256":"c2fbce65b2ac327b"}},{"arxiv_id":"2209.13306","paper":"/paper/embracing-consistency-a-one-stage-approach","title":"Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding","date":"2022-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jy0205/stcat","path":"models/pipeline.py","file_url":"https://github.com/jy0205/stcat/blob/HEAD/models/pipeline.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":"60a2fb58c9949c1d","mcp_get_code":{"code_sha256":"60a2fb58c9949c1d"}},{"arxiv_id":"2207.02204","paper":"/paper/detecting-and-recovering-sequential-deepfake","title":"Detecting and Recovering Sequential DeepFake Manipulation","date":"2022-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rshaojimmy/seqdeepfake","path":"models/SeqFakeFormer.py","file_url":"https://github.com/rshaojimmy/seqdeepfake/blob/HEAD/models/SeqFakeFormer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f10b0094723ad545","mcp_get_code":{"code_sha256":"f10b0094723ad545"}},{"arxiv_id":"2204.01918","paper":"/paper/text-spotting-transformers","title":"Text Spotting Transformers","date":"2022-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlpc-ucsd/TESTR","path":"adet/modeling/testr/models.py","file_url":"https://github.com/mlpc-ucsd/TESTR/blob/HEAD/adet/modeling/testr/models.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":"d515f52b31b887cc","mcp_get_code":{"code_sha256":"d515f52b31b887cc"}},{"arxiv_id":"2203.16518","paper":"/paper/collaborative-transformers-for-grounded","title":"Collaborative Transformers for Grounded Situation Recognition","date":"2022-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"towhee-io/towhee","path":"towhee/models/coformer/coformer.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/coformer/coformer.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":"42fe8f9fc92da57d","mcp_get_code":{"code_sha256":"42fe8f9fc92da57d"}},{"arxiv_id":"2203.16518","paper":"/paper/collaborative-transformers-for-grounded","title":"Collaborative Transformers for Grounded Situation Recognition","date":"2022-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jhcho99/CoFormer","path":"models/coformer.py","file_url":"https://github.com/jhcho99/CoFormer/blob/HEAD/models/coformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8ae3464a294cdaed","mcp_get_code":{"code_sha256":"8ae3464a294cdaed"}},{"arxiv_id":"2203.16434","paper":"/paper/tubedetr-spatio-temporal-video-grounding-with","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","date":"2022-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"antoyang/TubeDETR","path":"models/tubedetr.py","file_url":"https://github.com/antoyang/TubeDETR/blob/HEAD/models/tubedetr.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":"db74b3e6e32586fb","mcp_get_code":{"code_sha256":"db74b3e6e32586fb"}},{"arxiv_id":"2203.11876","paper":"/paper/open-vocabulary-detr-with-conditional","title":"Open-Vocabulary DETR with Conditional Matching","date":"2022-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuhangzang/OV-DETR","path":"ovdetr/models/model.py","file_url":"https://github.com/yuhangzang/OV-DETR/blob/HEAD/ovdetr/models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a59cf95e6b922e44","mcp_get_code":{"code_sha256":"a59cf95e6b922e44"}},{"arxiv_id":"2203.09507","paper":"/paper/towards-data-efficient-detection-transformers","title":"Towards Data-Efficient Detection Transformers","date":"2022-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"encounter1997/de-conddetr","path":"models/conditional_detr.py","file_url":"https://github.com/encounter1997/de-conddetr/blob/HEAD/models/conditional_detr.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":"38eda343ff956bb1","mcp_get_code":{"code_sha256":"38eda343ff956bb1"}},{"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":"helq2612/biadt","path":"models/dn_dab_deformable_detr/dab_deformable_detr.py","file_url":"https://github.com/helq2612/biadt/blob/HEAD/models/dn_dab_deformable_detr/dab_deformable_detr.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d336c6095b11629a","mcp_get_code":{"code_sha256":"d336c6095b11629a"}},{"arxiv_id":"2103.11161","paper":"/paper/montefloor-extending-mcts-for-reconstructing","title":"MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans","date":"2021-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"woodfrog/poly-diffuse","path":"src/models/polygon_models/polygon_net.py","file_url":"https://github.com/woodfrog/poly-diffuse/blob/HEAD/src/models/polygon_models/polygon_net.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"ace1b7ccab9cd45a","mcp_get_code":{"code_sha256":"ace1b7ccab9cd45a"}},{"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":"duongnv0499/Explain-Deformable-DETR","path":"models/deformable_detr.py","file_url":"https://github.com/duongnv0499/Explain-Deformable-DETR/blob/HEAD/models/deformable_detr.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a0958f4fe260b7bf","mcp_get_code":{"code_sha256":"a0958f4fe260b7bf"}},{"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":"zhechen/deformable-detr-rego","path":"models/deformable_detr.py","file_url":"https://github.com/zhechen/deformable-detr-rego/blob/HEAD/models/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":"6e981ab142d64bc6","mcp_get_code":{"code_sha256":"6e981ab142d64bc6"}},{"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":"Li-ai-cell/Interpretation_DETR","path":"models/deformable_detr.py","file_url":"https://github.com/Li-ai-cell/Interpretation_DETR/blob/HEAD/models/deformable_detr.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b3bc5ccabebb6be8","mcp_get_code":{"code_sha256":"b3bc5ccabebb6be8"}},{"arxiv_id":"Nguyen_Region-Level_Data_Attribution_for_Text-to-Image_Generative_Models_ICCV_2025_paper","paper":null,"title":"arXiv:Nguyen_Region-Level_Data_Attribution_for_Text-to-Image_Generative_Models_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"AIoT-Lab-BKAI/AR-Detector","path":"models/GroundingDINO/groundingdino.py","file_url":"https://github.com/AIoT-Lab-BKAI/AR-Detector/blob/HEAD/models/GroundingDINO/groundingdino.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8edcd8b335f324e7","mcp_get_code":{"code_sha256":"8edcd8b335f324e7"}}]}