{"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/attention-pool","entry":"attention_pool","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":13,"n_papers_ran":5,"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":6,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":15,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":1,"ran":2,"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":"2601.22674","paper":"/paper/arxiv-2601-22674","title":"VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"hanxunyu/VisionTrim","path":"llava/model/multimodal_projector/visual_plugin.py","file_url":"https://github.com/hanxunyu/VisionTrim/blob/HEAD/llava/model/multimodal_projector/visual_plugin.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"049db0114a85e508","mcp_get_code":{"code_sha256":"049db0114a85e508"}},{"arxiv_id":"2410.19553","paper":"/paper/on-occlusions-in-video-action-detection-1","title":"On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes","date":"2024-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rajatmodi62/OccludedActionBenchmark","path":"codebase/codebase_islands/slowfast/models/attention.py","file_url":"https://github.com/rajatmodi62/OccludedActionBenchmark/blob/HEAD/codebase/codebase_islands/slowfast/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":"a4723eab8df61dbe","mcp_get_code":{"code_sha256":"a4723eab8df61dbe"}},{"arxiv_id":"2403.05856","paper":"/paper/pov-prompt-oriented-view-agnostic-learning","title":"POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-View World","date":"2024-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xuboshen/pov_acmmm2023","path":"slowfast/models/attention_mprompt.py","file_url":"https://github.com/xuboshen/pov_acmmm2023/blob/HEAD/slowfast/models/attention_mprompt.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":"e60a7360a40621b1","mcp_get_code":{"code_sha256":"e60a7360a40621b1"}},{"arxiv_id":"2402.11301","paper":"/paper/revit-enhancing-vision-transformers-with","title":"ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual Connections","date":"2024-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adiko1997/revit","path":"model/attention.py","file_url":"https://github.com/adiko1997/revit/blob/HEAD/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":"f118f90404a2705d","mcp_get_code":{"code_sha256":"f118f90404a2705d"}},{"arxiv_id":"2401.11174","paper":"/paper/pixel-wise-recognition-for-holistic-surgical","title":"Pixel-Wise Recognition for Holistic Surgical Scene Understanding","date":"2024-01-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bcv-uniandes/tapir","path":"slowfast/models/attention.py","file_url":"https://github.com/bcv-uniandes/tapir/blob/HEAD/slowfast/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":"a4723eab8df61dbe","mcp_get_code":{"code_sha256":"a4723eab8df61dbe"}},{"arxiv_id":"2401.11174","paper":"/paper/pixel-wise-recognition-for-holistic-surgical","title":"Pixel-Wise Recognition for Holistic Surgical Scene Understanding","date":"2024-01-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bcv-uniandes/grasp","path":"TAPIS/tapis/models/attention.py","file_url":"https://github.com/bcv-uniandes/grasp/blob/HEAD/TAPIS/tapis/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":"5803e73c1b7f2a96","mcp_get_code":{"code_sha256":"5803e73c1b7f2a96"}},{"arxiv_id":"2311.00180","paper":"/paper/object-centric-video-representation-for-long","title":"Object-centric Video Representation for Long-term Action Anticipation","date":"2023-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brown-palm/ObjectPrompt","path":"src/models/mvit.py","file_url":"https://github.com/brown-palm/ObjectPrompt/blob/HEAD/src/models/mvit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a4723eab8df61dbe","mcp_get_code":{"code_sha256":"a4723eab8df61dbe"}},{"arxiv_id":"2302.04869","paper":"/paper/reversible-vision-transformers-1","title":"Reversible Vision Transformers","date":"2023-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/mvit","path":"mvit/models/attention.py","file_url":"https://github.com/facebookresearch/mvit/blob/HEAD/mvit/models/attention.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"049db0114a85e508","mcp_get_code":{"code_sha256":"049db0114a85e508"}},{"arxiv_id":"2302.04869","paper":"/paper/reversible-vision-transformers-1","title":"Reversible Vision Transformers","date":"2023-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/SlowFast","path":"slowfast/models/attention.py","file_url":"https://github.com/facebookresearch/SlowFast/blob/HEAD/slowfast/models/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":"a4723eab8df61dbe","mcp_get_code":{"code_sha256":"a4723eab8df61dbe"}},{"arxiv_id":"2211.09552","paper":"/paper/uniformerv2-spatiotemporal-learning-by-arming-1","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","date":"2022-11-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenGVLab/UniFormerV2","path":"slowfast/models/attention.py","file_url":"https://github.com/OpenGVLab/UniFormerV2/blob/HEAD/slowfast/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":"a4723eab8df61dbe","mcp_get_code":{"code_sha256":"a4723eab8df61dbe"}},{"arxiv_id":"2204.07962","paper":"/paper/an-extendable-efficient-and-effective","title":"An Extendable, Efficient and Effective Transformer-based Object Detector","date":"2022-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/detectron2","path":"detectron2/modeling/backbone/mvit.py","file_url":"https://github.com/facebookresearch/detectron2/blob/HEAD/detectron2/modeling/backbone/mvit.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2378025224edad54","mcp_get_code":{"code_sha256":"2378025224edad54"}},{"arxiv_id":"2203.10233","paper":"/paper/direcformer-a-directed-attention-in","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","date":"2022-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uark-cviu/direcformer","path":"slowfast/models/attention.py","file_url":"https://github.com/uark-cviu/direcformer/blob/HEAD/slowfast/models/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":"a4723eab8df61dbe","mcp_get_code":{"code_sha256":"a4723eab8df61dbe"}},{"arxiv_id":"2110.06915","paper":"/paper/object-region-video-transformers-1","title":"Object-Region Video Transformers","date":"2021-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eladb3/orvit","path":"slowfast/models/attention.py","file_url":"https://github.com/eladb3/orvit/blob/HEAD/slowfast/models/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":"a4723eab8df61dbe","mcp_get_code":{"code_sha256":"a4723eab8df61dbe"}},{"arxiv_id":"2106.09703","paper":"/paper/modist-motion-distillation-for-self","title":"MaCLR: Motion-aware Contrastive Learning of Representations for Videos","date":"2021-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/self-supervised-maclr","path":"slowfast/models/attention.py","file_url":"https://github.com/amazon-science/self-supervised-maclr/blob/HEAD/slowfast/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":"a4723eab8df61dbe","mcp_get_code":{"code_sha256":"a4723eab8df61dbe"}},{"arxiv_id":"136950068","paper":null,"title":"arXiv:136950068","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wangjk666/STTS","path":"MViT/slowfast/models/attention.py","file_url":"https://github.com/wangjk666/STTS/blob/HEAD/MViT/slowfast/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":"a4723eab8df61dbe","mcp_get_code":{"code_sha256":"a4723eab8df61dbe"}}]}