{"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/multi-head-attention-forward","entry":"multi_head_attention_forward","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":73,"n_papers_ran":17,"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":42,"n_samples_ran":13,"n_samples_fingerprinted":0,"n_places":79,"n_places_pointer_only":31,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":4,"ran_fixture":2,"ran":7,"unverified":29},"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":"2606.07345","paper":"/paper/arxiv-2606-07345","title":"TABSWIFT: An Efficient Tabular Foundation Model with Row-Wise Attention","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"LAMDA-Tabular/TabSwift","path":"TALENT/model/lib/tabswift/model/attention.py","file_url":"https://github.com/LAMDA-Tabular/TabSwift/blob/HEAD/TALENT/model/lib/tabswift/model/attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a9dd34f2bf5c94fd","mcp_get_code":{"code_sha256":"a9dd34f2bf5c94fd"}},{"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/attention.py","file_url":"https://github.com/wjj1wjj/Nodule-DETR/blob/HEAD/Nodule-DETR/models/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2510.25094","paper":"/paper/arxiv-2510-25094","title":"Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"mlvlab/VDRP","path":"attention.py","file_url":"https://github.com/mlvlab/VDRP/blob/HEAD/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7653b4a0a7557b30","mcp_get_code":{"code_sha256":"7653b4a0a7557b30"}},{"arxiv_id":"2510.17218","paper":"/paper/arxiv-2510-17218","title":"When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"Zhuo-Cao/QV-M2","path":"FlashMMR/attention.py","file_url":"https://github.com/Zhuo-Cao/QV-M2/blob/HEAD/FlashMMR/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2510.17218","paper":"/paper/arxiv-2510-17218","title":"When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"Zhuo-Cao/QV-M2","path":"FlashMMR/crossattention.py","file_url":"https://github.com/Zhuo-Cao/QV-M2/blob/HEAD/FlashMMR/crossattention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5d7fc668e3b608cf","mcp_get_code":{"code_sha256":"5d7fc668e3b608cf"}},{"arxiv_id":"2506.23502","paper":null,"title":"arXiv:2506.23502","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"Mengxiao-Tian/LAMP","path":"clip/attention.py","file_url":"https://github.com/Mengxiao-Tian/LAMP/blob/HEAD/clip/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"440f24d0f7a85c28","mcp_get_code":{"code_sha256":"440f24d0f7a85c28"}},{"arxiv_id":"2503.20826","paper":"/paper/exploring-clip-s-dense-knowledge-for-weakly","title":"Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation","date":"2025-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zwyang6/ExCEL","path":"model/model_excel.py","file_url":"https://github.com/zwyang6/ExCEL/blob/HEAD/model/model_excel.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a7e566273a4fdcb7","mcp_get_code":{"code_sha256":"a7e566273a4fdcb7"}},{"arxiv_id":"2503.14493","paper":"/paper/state-space-model-meets-transformer-a-new-1","title":"State Space Model Meets Transformer: A New Paradigm for 3D Object Detection","date":"2025-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenSpaceAI/DEST3D","path":"models/multi_head_attention.py","file_url":"https://github.com/OpenSpaceAI/DEST3D/blob/HEAD/models/multi_head_attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fd73be3c7c18abff","mcp_get_code":{"code_sha256":"fd73be3c7c18abff"}},{"arxiv_id":"2501.07305","paper":"/paper/the-devil-is-in-the-spurious-correlation","title":"The Devil is in the Spurious Correlation: Boosting Moment Retrieval via Temporal Dynamic Learning","date":"2025-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xyangzhou/TD-DETR","path":"td_detr/attention.py","file_url":"https://github.com/xyangzhou/TD-DETR/blob/HEAD/td_detr/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2412.13441","paper":"/paper/flashvtg-feature-layering-and-adaptive-score","title":"FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding","date":"2024-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhuo-cao/flashvtg","path":"FlashVTG/attention.py","file_url":"https://github.com/zhuo-cao/flashvtg/blob/HEAD/FlashVTG/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2412.13441","paper":"/paper/flashvtg-feature-layering-and-adaptive-score","title":"FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding","date":"2024-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhuo-cao/flashvtg","path":"FlashVTG/crossattention.py","file_url":"https://github.com/zhuo-cao/flashvtg/blob/HEAD/FlashVTG/crossattention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5d7fc668e3b608cf","mcp_get_code":{"code_sha256":"5d7fc668e3b608cf"}},{"arxiv_id":"2412.02402","paper":"/paper/rg-san-rule-guided-spatial-awareness-network","title":"RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation","date":"2024-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sosppxo/RG-SAN","path":"rg_san/model/attention.py","file_url":"https://github.com/sosppxo/RG-SAN/blob/HEAD/rg_san/model/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a4a324f1b49cd7c6","mcp_get_code":{"code_sha256":"a4a324f1b49cd7c6"}},{"arxiv_id":"2411.10293","paper":"/paper/retr-multi-view-radar-detection-transformer","title":"RETR: Multi-View Radar Detection Transformer for Indoor Perception","date":"2024-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"merlresearch/radar-detection-transformer","path":"src/models/module_retr/attention.py","file_url":"https://github.com/merlresearch/radar-detection-transformer/blob/HEAD/src/models/module_retr/attention.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":"62e28a74b391b811","mcp_get_code":{"code_sha256":"62e28a74b391b811"}},{"arxiv_id":"2408.02901","paper":"/paper/2408-02901","title":"Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection","date":"2024-08-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"line/lighthouse","path":"lighthouse/common/attention.py","file_url":"https://github.com/line/lighthouse/blob/HEAD/lighthouse/common/attention.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":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2408.02901","paper":"/paper/2408-02901","title":"Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection","date":"2024-08-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"line/lighthouse","path":"lighthouse/common/crossattention.py","file_url":"https://github.com/line/lighthouse/blob/HEAD/lighthouse/common/crossattention.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":"5d7fc668e3b608cf","mcp_get_code":{"code_sha256":"5d7fc668e3b608cf"}},{"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":"models/decoder_layer/multi_head_attention.py","file_url":"https://github.com/chenwei746/eevg/blob/HEAD/models/decoder_layer/multi_head_attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"17bc17d91de1161a","mcp_get_code":{"code_sha256":"17bc17d91de1161a"}},{"arxiv_id":"2407.15051","paper":"/paper/prior-knowledge-integration-via-llm-encoding","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","date":"2024-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fletcherjiang/llmepet","path":"llm_epet/attention.py","file_url":"https://github.com/fletcherjiang/llmepet/blob/HEAD/llm_epet/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2407.15051","paper":"/paper/prior-knowledge-integration-via-llm-encoding","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","date":"2024-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fletcherjiang/llmepet","path":"llm_epet/crossattention.py","file_url":"https://github.com/fletcherjiang/llmepet/blob/HEAD/llm_epet/crossattention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"52dcd63a2ee1f51a","mcp_get_code":{"code_sha256":"52dcd63a2ee1f51a"}},{"arxiv_id":"2407.14412","paper":"/paper/deal-disentangle-and-localize-concept-level","title":"DEAL: Disentangle and Localize Concept-level Explanations for VLMs","date":"2024-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tangli-udel/DEAL","path":"CLIP/clip/auxilary.py","file_url":"https://github.com/tangli-udel/DEAL/blob/HEAD/CLIP/clip/auxilary.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"33c1a0c844a11c56","mcp_get_code":{"code_sha256":"33c1a0c844a11c56"}},{"arxiv_id":"2407.05118","paper":"/paper/shine-saliency-aware-hierarchical-negative","title":"SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding","date":"2024-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zxccade/SHINE","path":"shine/attention.py","file_url":"https://github.com/zxccade/SHINE/blob/HEAD/shine/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"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/attention.py","file_url":"https://github.com/atten4vis/lw-detr/blob/HEAD/models/attention.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":"57e6ba78fde593e0","mcp_get_code":{"code_sha256":"57e6ba78fde593e0"}},{"arxiv_id":"2404.09263","paper":"/paper/task-driven-exploration-decoupling-and-inter","title":"Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection","date":"2024-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EdenGabriel/TaskWeave","path":"taskweave/attention.py","file_url":"https://github.com/EdenGabriel/TaskWeave/blob/HEAD/taskweave/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2404.01745","paper":"/paper/unleash-the-potential-of-clip-for-video","title":"Unleash the Potential of CLIP for Video Highlight Detection","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dhk1349/HL-CLIP","path":"moment_detr/attention.py","file_url":"https://github.com/dhk1349/HL-CLIP/blob/HEAD/moment_detr/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2403.15241","paper":"/paper/is-fusion-instance-scene-collaborative-fusion","title":"IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection","date":"2024-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yinjunbo/IS-Fusion","path":"mmdet3d/models/middle_encoders/fusion_encoder.py","file_url":"https://github.com/yinjunbo/IS-Fusion/blob/HEAD/mmdet3d/models/middle_encoders/fusion_encoder.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":"e8974f996d0fa2ae","mcp_get_code":{"code_sha256":"e8974f996d0fa2ae"}},{"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/attention.py","file_url":"https://github.com/chenxi-Guo/TransGOP/blob/HEAD/models/TransGOP/attention.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":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2402.10885","paper":"/paper/3d-diffuser-actor-policy-diffusion-with-3d-1","title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nickgkan/3d_diffuser_actor","path":"diffuser_actor/utils/multihead_custom_attention.py","file_url":"https://github.com/nickgkan/3d_diffuser_actor/blob/HEAD/diffuser_actor/utils/multihead_custom_attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"616805ec8f4f95fb","mcp_get_code":{"code_sha256":"616805ec8f4f95fb"}},{"arxiv_id":"2402.06680","paper":"/paper/social-physics-informed-diffusion-model-for","title":"Social Physics Informed Diffusion Model for Crowd Simulation","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tsinghua-fib-lab/SPDiff","path":"models/multi_attention_forward.py","file_url":"https://github.com/tsinghua-fib-lab/SPDiff/blob/HEAD/models/multi_attention_forward.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4a5f247d4b18ad03","mcp_get_code":{"code_sha256":"4a5f247d4b18ad03"}},{"arxiv_id":"2401.02309","paper":"/paper/tr-detr-task-reciprocal-transformer-for-joint","title":"TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection","date":"2024-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingyao1120/tr-detr","path":"tr_detr/attention.py","file_url":"https://github.com/mingyao1120/tr-detr/blob/HEAD/tr_detr/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2312.12155","paper":"/paper/towards-balanced-alignment-modal-enhanced","title":"Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval","date":"2023-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lntzm/mesm","path":"model/attention.py","file_url":"https://github.com/lntzm/mesm/blob/HEAD/model/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"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/modules/attention.py","file_url":"https://github.com/FoundationVision/GLEE/blob/HEAD/projects/GLEE/glee/modules/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"22a94fc69aed9aca","mcp_get_code":{"code_sha256":"22a94fc69aed9aca"}},{"arxiv_id":"2312.06323","paper":"/paper/learning-hierarchical-prompt-with-structured","title":"Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models","date":"2023-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vill-lab/2024-aaai-hpt","path":"clip/attention.py","file_url":"https://github.com/vill-lab/2024-aaai-hpt/blob/HEAD/clip/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"440f24d0f7a85c28","mcp_get_code":{"code_sha256":"440f24d0f7a85c28"}},{"arxiv_id":"2312.00083","paper":"/paper/bam-detr-boundary-aligned-moment-detection","title":"BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Pilhyeon/BAM-DETR","path":"bam_detr/attention.py","file_url":"https://github.com/Pilhyeon/BAM-DETR/blob/HEAD/bam_detr/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2311.16464","paper":"/paper/bridging-the-gap-a-unified-video","title":"Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"easonxiao-888/uvcom","path":"uvcom/attention.py","file_url":"https://github.com/easonxiao-888/uvcom/blob/HEAD/uvcom/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2311.08835","paper":"/paper/correlation-guided-query-dependency","title":"Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wjun0830/cgdetr","path":"cg_detr/attention.py","file_url":"https://github.com/wjun0830/cgdetr/blob/HEAD/cg_detr/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2311.08835","paper":"/paper/correlation-guided-query-dependency","title":"Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wjun0830/cgdetr","path":"cg_detr/crossattention.py","file_url":"https://github.com/wjun0830/cgdetr/blob/HEAD/cg_detr/crossattention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5d7fc668e3b608cf","mcp_get_code":{"code_sha256":"5d7fc668e3b608cf"}},{"arxiv_id":"2310.12152","paper":"/paper/learning-from-rich-semantics-and-coarse","title":"Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection","date":"2023-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MengLcool/RichSem","path":"models/richsem/attention.py","file_url":"https://github.com/MengLcool/RichSem/blob/HEAD/models/richsem/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"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/attention.py","file_url":"https://github.com/IDEA-Research/UniPose/blob/HEAD/models/UniPose/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2309.12855","paper":"/paper/cross-modal-translation-and-alignment-for","title":"Cross-Modal Translation and Alignment for Survival Analysis","date":"2023-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ft-zhou-zzz/cmta","path":"models/cmta/network.py","file_url":"https://github.com/ft-zhou-zzz/cmta/blob/HEAD/models/cmta/network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ed90a207a3c44285","mcp_get_code":{"code_sha256":"ed90a207a3c44285"}},{"arxiv_id":"2309.09180","paper":"/paper/neural-speaker-diarization-using-memory-aware","title":"Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding with Sequence-to-Sequence Architecture","date":"2023-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liyunlongaaa/nsd-ms2s","path":"local/model_S2S_weight_input_DIM.py","file_url":"https://github.com/liyunlongaaa/nsd-ms2s/blob/HEAD/local/model_S2S_weight_input_DIM.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f89d3dff01a8d443","mcp_get_code":{"code_sha256":"f89d3dff01a8d443"}},{"arxiv_id":"2309.01692","paper":"/paper/mask-attention-free-transformer-for-3d","title":"Mask-Attention-Free Transformer for 3D Instance Segmentation","date":"2023-09-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/mask-attention-free-transformer","path":"maft/model/attention.py","file_url":"https://github.com/dvlab-research/mask-attention-free-transformer/blob/HEAD/maft/model/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f09175b0f39f0ad0","mcp_get_code":{"code_sha256":"f09175b0f39f0ad0"}},{"arxiv_id":"2308.14191","paper":"/paper/sketchdreamer-interactive-text-augmented","title":"SketchDreamer: Interactive Text-Augmented Creative Sketch Ideation","date":"2023-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"winkawaks/sketchdreamer","path":"CLIP_/clip/auxilary.py","file_url":"https://github.com/winkawaks/sketchdreamer/blob/HEAD/CLIP_/clip/auxilary.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":"bc3ccaf78ecd6394","mcp_get_code":{"code_sha256":"bc3ccaf78ecd6394"}},{"arxiv_id":"2308.06947","paper":"/paper/knowing-where-to-focus-event-aware","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","date":"2023-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jinhyunj/eatr","path":"models/attention.py","file_url":"https://github.com/jinhyunj/eatr/blob/HEAD/models/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2308.06202","paper":"/paper/exploring-predicate-visual-context-in","title":"Exploring Predicate Visual Context in Detecting Human-Object Interactions","date":"2023-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fredzzhang/pvic","path":"attention.py","file_url":"https://github.com/fredzzhang/pvic/blob/HEAD/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"7653b4a0a7557b30","mcp_get_code":{"code_sha256":"7653b4a0a7557b30"}},{"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/attention.py","file_url":"https://github.com/bytedance/DQ-Det/blob/HEAD/Cond-DETR-DQ/models/attention.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":"f09175b0f39f0ad0","mcp_get_code":{"code_sha256":"f09175b0f39f0ad0"}},{"arxiv_id":"2307.09749","paper":"/paper/towards-robust-scene-text-image-super","title":"Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement","date":"2023-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csguoh/LEMMA","path":"model/transformer.py","file_url":"https://github.com/csguoh/LEMMA/blob/HEAD/model/transformer.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":"0ca1572c9755ffd9","mcp_get_code":{"code_sha256":"0ca1572c9755ffd9"}},{"arxiv_id":"2307.02869","paper":"/paper/momentdiff-generative-video-moment-retrieval","title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","date":"2023-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"imccretrieval/momentdiff","path":"momentdiff/attention.py","file_url":"https://github.com/imccretrieval/momentdiff/blob/HEAD/momentdiff/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"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/attention.py","file_url":"https://github.com/IDEA-Research/OpenSeeD/blob/HEAD/openseed/modules/attention.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":"22a94fc69aed9aca","mcp_get_code":{"code_sha256":"22a94fc69aed9aca"}},{"arxiv_id":"2306.08330","paper":"/paper/multimodal-optimal-transport-based-co","title":"Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction","date":"2023-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JJ-ZHOU-Code/RobustMultiModel","path":"models/model_coattn.py","file_url":"https://github.com/JJ-ZHOU-Code/RobustMultiModel/blob/HEAD/models/model_coattn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4043b3b3f31ca073","mcp_get_code":{"code_sha256":"4043b3b3f31ca073"}},{"arxiv_id":"2306.03597","paper":"/paper/human-object-interaction-prediction-in-videos","title":"Human-Object Interaction Prediction in Videos through Gaze Following","date":"2023-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nizhf/hoi-prediction-gaze-transformer","path":"modules/sthoip_transformer/sttran/mha_utils.py","file_url":"https://github.com/nizhf/hoi-prediction-gaze-transformer/blob/HEAD/modules/sthoip_transformer/sttran/mha_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c6cbf275e58cc089","mcp_get_code":{"code_sha256":"c6cbf275e58cc089"}},{"arxiv_id":"2305.18951","paper":"/paper/subequivariant-graph-reinforcement-learning","title":"Subequivariant Graph Reinforcement Learning in 3D Environments","date":"2023-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alpc91/sgrl","path":"src/subequivariant_attentions.py","file_url":"https://github.com/alpc91/sgrl/blob/HEAD/src/subequivariant_attentions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"389d696e65ff8fb1","mcp_get_code":{"code_sha256":"389d696e65ff8fb1"}},{"arxiv_id":"2305.18951","paper":"/paper/subequivariant-graph-reinforcement-learning","title":"Subequivariant Graph Reinforcement Learning in 3D Environments","date":"2023-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alpc91/SGRL","path":"src/attentions.py","file_url":"https://github.com/alpc91/SGRL/blob/HEAD/src/attentions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"11c0ca2379df2020","mcp_get_code":{"code_sha256":"11c0ca2379df2020"}},{"arxiv_id":"2305.05140","paper":"/paper/linguistic-more-taking-a-further-step-toward","title":"Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition","date":"2023-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CyrilSterling/LPV","path":"modules/transformer.py","file_url":"https://github.com/CyrilSterling/LPV/blob/HEAD/modules/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0ca1572c9755ffd9","mcp_get_code":{"code_sha256":"0ca1572c9755ffd9"}},{"arxiv_id":"2303.03926","paper":"/paper/speak-foreign-languages-with-your-own-voice","title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","date":"2023-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"plachtaa/vall-e-x","path":"modules/activation.py","file_url":"https://github.com/plachtaa/vall-e-x/blob/HEAD/modules/activation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1b616e7eb0f31017","mcp_get_code":{"code_sha256":"1b616e7eb0f31017"}},{"arxiv_id":"2303.03052","paper":"/paper/masked-images-are-counterfactual-samples-for","title":"Masked Images Are Counterfactual Samples for Robust Fine-tuning","date":"2023-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Coxy7/robust-finetuning","path":"models/clip/multihead_attention.py","file_url":"https://github.com/Coxy7/robust-finetuning/blob/HEAD/models/clip/multihead_attention.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":"10db37a6179c6f22","mcp_get_code":{"code_sha256":"10db37a6179c6f22"}},{"arxiv_id":"2301.08838","paper":"/paper/aquamam-an-autoregressive-quaternion-manifold","title":"AQuaMaM: An Autoregressive, Quaternion Manifold Model for Rapidly Estimating Complex SO(3) Distributions","date":"2023-01-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"airalcorn2/aquamam","path":"aquamam.py","file_url":"https://github.com/airalcorn2/aquamam/blob/HEAD/aquamam.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"968809b799fc5586","mcp_get_code":{"code_sha256":"968809b799fc5586"}},{"arxiv_id":"2210.13950","paper":"/paper/pointly-supervised-panoptic-segmentation","title":"Pointly-Supervised Panoptic Segmentation","date":"2022-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BraveGroup/PSPS","path":"models/attention.py","file_url":"https://github.com/BraveGroup/PSPS/blob/HEAD/models/attention.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":"de985e115a5e7c9b","mcp_get_code":{"code_sha256":"de985e115a5e7c9b"}},{"arxiv_id":"2207.10859","paper":"/paper/geodesic-former-a-geodesic-guided-few-shot-3d","title":"Geodesic-Former: a Geodesic-Guided Few-shot 3D Point Cloud Instance Segmenter","date":"2022-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VinAIResearch/GeoFormer","path":"model/attention.py","file_url":"https://github.com/VinAIResearch/GeoFormer/blob/HEAD/model/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"739083ff32255d01","mcp_get_code":{"code_sha256":"739083ff32255d01"}},{"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/attention.py","file_url":"https://github.com/IDEA-opensource/DN-DETR/blob/HEAD/models/DN_DAB_DETR/attention.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":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2203.11496","paper":"/paper/transfusion-robust-lidar-camera-fusion-for-3d","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","date":"2022-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xuyangbai/transfusion","path":"mmdet3d/models/dense_heads/transfusion_head.py","file_url":"https://github.com/xuyangbai/transfusion/blob/HEAD/mmdet3d/models/dense_heads/transfusion_head.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":"e8974f996d0fa2ae","mcp_get_code":{"code_sha256":"e8974f996d0fa2ae"}},{"arxiv_id":"2203.08459","paper":"/paper/kinyabert-a-morphology-aware-kinyarwanda-1","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","date":"2022-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anzeyimana/kinyabert-acl2022","path":"code/morpho_model.py","file_url":"https://github.com/anzeyimana/kinyabert-acl2022/blob/HEAD/code/morpho_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6b3df8438d1f1eb3","mcp_get_code":{"code_sha256":"6b3df8438d1f1eb3"}},{"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":"idea-research/dino","path":"models/dino/attention.py","file_url":"https://github.com/idea-research/dino/blob/HEAD/models/dino/attention.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":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"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/attention.py","file_url":"https://github.com/FengLi-ust/DN-DETR/blob/HEAD/models/DN_DAB_DETR/attention.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":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"2108.12630","paper":"/paper/groupformer-group-activity-recognition-with","title":"GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer","date":"2021-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xueyee/groupformer","path":"group/models/transformer_cluster.py","file_url":"https://github.com/xueyee/groupformer/blob/HEAD/group/models/transformer_cluster.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":"8e2156fc442de944","mcp_get_code":{"code_sha256":"8e2156fc442de944"}},{"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/attention.py","file_url":"https://github.com/atten4vis/conditionaldetr/blob/HEAD/models/attention.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":"f09175b0f39f0ad0","mcp_get_code":{"code_sha256":"f09175b0f39f0ad0"}},{"arxiv_id":"2106.01269","paper":"/paper/more-identifiable-yet-equally-performant","title":"More Identifiable yet Equally Performant Transformers for Text Classification","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"declare-lab/identifiable-transformers","path":"model_identifiable.py","file_url":"https://github.com/declare-lab/identifiable-transformers/blob/HEAD/model_identifiable.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"650a5edfdd5ec496","mcp_get_code":{"code_sha256":"650a5edfdd5ec496"}},{"arxiv_id":"2105.13868","paper":"/paper/learning-relation-alignment-for-calibrated","title":"Learning Relation Alignment for Calibrated Cross-modal Retrieval","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lancopku/IAIS","path":"model/attention.py","file_url":"https://github.com/lancopku/IAIS/blob/HEAD/model/attention.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fed42c63be2ceb6c","mcp_get_code":{"code_sha256":"fed42c63be2ceb6c"}},{"arxiv_id":"2104.00678","paper":"/paper/group-free-3d-object-detection-via","title":"Group-Free 3D Object Detection via Transformers","date":"2021-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KookHoiKim/GroupFree3dBaseline","path":"models/detector.py","file_url":"https://github.com/KookHoiKim/GroupFree3dBaseline/blob/HEAD/models/detector.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"89a5e4ca75931eac","mcp_get_code":{"code_sha256":"89a5e4ca75931eac"}},{"arxiv_id":"2103.06495","paper":"/paper/read-like-humans-autonomous-bidirectional-and","title":"Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition","date":"2021-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FangShancheng/ABINet","path":"modules/model_abinet.py","file_url":"https://github.com/FangShancheng/ABINet/blob/HEAD/modules/model_abinet.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"62abaf6e5036ae75","mcp_get_code":{"code_sha256":"62abaf6e5036ae75"}},{"arxiv_id":"2101.07448","paper":"/paper/fast-convergence-of-detr-with-spatially","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","date":"2021-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gaopengcuhk/SMCA-DETR","path":"models/attention_layer.py","file_url":"https://github.com/gaopengcuhk/SMCA-DETR/blob/HEAD/models/attention_layer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d72990eaed622d96","mcp_get_code":{"code_sha256":"d72990eaed622d96"}},{"arxiv_id":"2010.15831","paper":"/paper/relationnet-bridging-visual-representations","title":"RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder","date":"2020-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/RelationNet2","path":"code/models/utils/bvr_transformer/multihead_attention.py","file_url":"https://github.com/microsoft/RelationNet2/blob/HEAD/code/models/utils/bvr_transformer/multihead_attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"150c213138c1ac1a","mcp_get_code":{"code_sha256":"150c213138c1ac1a"}},{"arxiv_id":"2006.06195","paper":"/paper/large-scale-adversarial-training-for-vision","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","date":"2020-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhegan27/VILLA","path":"model/attention.py","file_url":"https://github.com/zhegan27/VILLA/blob/HEAD/model/attention.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fed42c63be2ceb6c","mcp_get_code":{"code_sha256":"fed42c63be2ceb6c"}},{"arxiv_id":"2005.08514","paper":"/paper/spatio-temporal-graph-transformer-networks","title":"Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction","date":"2020-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Majiker/STAR","path":"src/multi_attention_forward.py","file_url":"https://github.com/Majiker/STAR/blob/HEAD/src/multi_attention_forward.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4a5f247d4b18ad03","mcp_get_code":{"code_sha256":"4a5f247d4b18ad03"}},{"arxiv_id":"aaai_28387","paper":null,"title":"arXiv:aaai_28387","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Vill-Lab/2024-AAAI-HPT","path":"clip/attention.py","file_url":"https://github.com/Vill-Lab/2024-AAAI-HPT/blob/HEAD/clip/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"440f24d0f7a85c28","mcp_get_code":{"code_sha256":"440f24d0f7a85c28"}},{"arxiv_id":"aaai_28177","paper":null,"title":"arXiv:aaai_28177","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"lntzm/MESM","path":"model/attention.py","file_url":"https://github.com/lntzm/MESM/blob/HEAD/model/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"Xiao_Bridging_the_Gap_A_Unified_Video_Comprehension_Framework_for_Moment_CVPR_2024_paper","paper":null,"title":"arXiv:Xiao_Bridging_the_Gap_A_Unified_Video_Comprehension_Framework_for_Moment_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"EasonXiao-888/UVCOM","path":"uvcom/attention.py","file_url":"https://github.com/EasonXiao-888/UVCOM/blob/HEAD/uvcom/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a82091666b9db8cf","mcp_get_code":{"code_sha256":"a82091666b9db8cf"}},{"arxiv_id":"Wang_Language-Driven_Multi-Label_Zero-Shot_Learning_with_Semantic_Granularity_ICCV_2025_paper","paper":null,"title":"arXiv:Wang_Language-Driven_Multi-Label_Zero-Shot_Learning_with_Semantic_Granularity_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wangshouwen/RCNn","path":"clip/multi_head_attn.py","file_url":"https://github.com/wangshouwen/RCNn/blob/HEAD/clip/multi_head_attn.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":"1274bb9f45cad0b2","mcp_get_code":{"code_sha256":"1274bb9f45cad0b2"}},{"arxiv_id":"Tang_Progressive_Attention_on_Multi-Level_Dense_Difference_Maps_for_Generic_Event_CVPR_2022_paper","paper":null,"title":"arXiv:Tang_Progressive_Attention_on_Multi-Level_Dense_Difference_Maps_for_Generic_Event_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"MCG-NJU/DDM","path":"DDM-Net/modeling/attn.py","file_url":"https://github.com/MCG-NJU/DDM/blob/HEAD/DDM-Net/modeling/attn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f09175b0f39f0ad0","mcp_get_code":{"code_sha256":"f09175b0f39f0ad0"}},{"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/attention.py","file_url":"https://github.com/liuyang-ict/SAP-DETR/blob/HEAD/models/SAP_DETR/attention.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":"8ccb75883fb557ba","mcp_get_code":{"code_sha256":"8ccb75883fb557ba"}},{"arxiv_id":"He_Bidirectional_Alignment_for_Domain_Adaptive_Detection_with_Transformers_ICCV_2023_paper","paper":null,"title":"arXiv:He_Bidirectional_Alignment_for_Domain_Adaptive_Detection_with_Transformers_ICCV_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"helq2612/biADT","path":"models/dn_dab_deformable_detr/attention.py","file_url":"https://github.com/helq2612/biADT/blob/HEAD/models/dn_dab_deformable_detr/attention.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":"f9f896834ab32dc2","mcp_get_code":{"code_sha256":"f9f896834ab32dc2"}}]}