{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/rendezvous-attention-mechanisms-for-the","title":"Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos","arxiv_id":"2109.03223","date":"2021-09-07","proceeding":null,"authors":["Chinedu Innocent Nwoye","Tong Yu","Cristians Gonzalez","Barbara Seeliger","Pietro Mascagni","Didier Mutter","Jacques Marescaux","Nicolas Padoy"],"abstract":"Out of all existing frameworks for surgical workflow analysis in endoscopic videos, action triplet recognition stands out as the only one aiming to provide truly fine-grained and comprehensive information on surgical activities. This information, presented as <instrument, verb, target> combinations, is highly challenging to be accurately identified. Triplet components can be difficult to recognize individually; in this task, it requires not only performing recognition simultaneously for all three triplet components, but also correctly establishing the data association between them. To achieve this task, we introduce our new model, the Rendezvous (RDV), which recognizes triplets directly from surgical videos by leveraging attention at two different levels. We first introduce a new form of spatial attention to capture individual action triplet components in a scene; called Class Activation Guided Attention Mechanism (CAGAM). This technique focuses on the recognition of verbs and targets using activations resulting from instruments. To solve the association problem, our RDV model adds a new form of semantic attention inspired by Transformer networks; called Multi-Head of Mixed Attention (MHMA). This technique uses several cross and self attentions to effectively capture relationships between instruments, verbs, and targets. We also introduce CholecT50 - a dataset of 50 endoscopic videos in which every frame has been annotated with labels from 100 triplet classes. Our proposed RDV model significantly improves the triplet prediction mean AP by over 9% compared to the state-of-the-art methods on this dataset.","url_abs":"https://arxiv.org/abs/2109.03223v2","url_pdf":"https://arxiv.org/pdf/2109.03223v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"rendezvous-attention-mechanisms-for-the","repo_url":"https://github.com/camma-public/attention-tripnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"rendezvous-attention-mechanisms-for-the","repo_url":"https://github.com/camma-public/tripnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"rendezvous-attention-mechanisms-for-the","repo_url":"https://github.com/camma-public/rendezvous","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"rendezvous-attention-mechanisms-for-the","repo_url":"https://github.com/CAMMA-public/cholect45","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"rendezvous-attention-mechanisms-for-the","repo_url":"https://github.com/CAMMA-public/cholect50","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"rendezvous-attention-mechanisms-for-the","repo_url":"https://github.com/camma-public/ivtmetrics","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"rendezvous-attention-mechanisms-for-the","repo_url":"https://github.com/camma-public/ssg-qa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"rendezvous-attention-mechanisms-for-the","repo_url":"https://github.com/camma-public/ssg-vqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"action-triplet-recognition","task_name":"Action Triplet Recognition"},{"task_slug":null,"task_name":"Triplet"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"cagam","method_name":"Class Activation Guided Attention Mechanism"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"mhma","method_name":"MHMA"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"triplet-attention","method_name":"Triplet Attention"}],"datasets_introduced":[{"slug":"cholect45","name":"CholecT45","full_name":"CholecT45"},{"slug":"cholect50","name":"CholecT50","full_name":"Cholecystectomy Action Triplet"}],"methods_introduced":[{"slug":"cagam","name":"Class Activation Guided Attention Mechanism","full_name":"Class Activation Guided Attention Mechanism (CAGAM)"},{"slug":"mhma","name":"MHMA","full_name":"Multi-Heads of Mixed Attention"}],"results":[{"leaderboard":"/sota/action-triplet-recognition-on-cholect50","task":"Action Triplet Recognition","dataset":"CholecT50","model":"Rendezvous (TensorFlow v1)","rank_in_archive_order":1,"of":6,"metrics":{"Mean AP":"29.9"},"uses_additional_data":false},{"leaderboard":"/sota/action-triplet-recognition-on-cholect50","task":"Action Triplet Recognition","dataset":"CholecT50","model":"Attention Tripnet (TensorFlow v1)","rank_in_archive_order":3,"of":6,"metrics":{"Mean AP":"23.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.03223","atlas_url":"https://app.syntology.ai/?focus=2109.03223","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2109.03223"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2109.03223\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2109.03223"},"call":"get_concepts_for_paper(arxiv_id=\"2109.03223\")"}],"by_repo":[{"repo":"camma-public/attention-tripnet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"camma-public/tripnet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"camma-public/rendezvous","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"CAMMA-public/cholect45","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"CAMMA-public/cholect50","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"camma-public/ivtmetrics","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"camma-public/ssg-qa","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2312.10251"],"harvested_for_calls":[{"arxiv_id":"2312.10251","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.10251"},"call":"get_harvested_code_for_paper(arxiv_id=\"2312.10251\")"}]},{"repo":"camma-public/ssg-vqa","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5a35c7f0878aa38398f2322029f7e07fd81b4f096e4300e5cf16b497031f453a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}