{"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":"/task/zero-shot-action-recognition","name":"Zero-Shot Action Recognition","slug":"zero-shot-action-recognition","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":83,"papers_with_code":40,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":6,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/zero-shot-action-recognition-on-ucf101","slug":"zero-shot-action-recognition-on-ucf101","dataset":"UCF101","dataset_url":"/dataset/ucf101","rows_in_archive":35,"metrics":["Top-1 Accuracy","Top-5 accuracy"],"first_row_in_archive_order":{"model":"OTI(ViT-L/14)","paper_title":"Orthogonal Temporal Interpolation for Zero-Shot Video Recognition","paper_url":"/paper/orthogonal-temporal-interpolation-for-zero","paper_date":"2023-08-14","arxiv_id":"2308.06897","code_links":[{"title":"sweetorangezhuyan/mm2023_oti","url":"https://github.com/sweetorangezhuyan/mm2023_oti"}],"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/orthogonal-temporal-interpolation-for-zero#ran","syntology_url":"https://syntology.ai/paper/2308.06897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06897"}},"official":{"repos":["sweetorangezhuyan/mm2023_oti"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/zero-shot-action-recognition-on-hmdb51","slug":"zero-shot-action-recognition-on-hmdb51","dataset":"HMDB51","dataset_url":"/dataset/hmdb51","rows_in_archive":29,"metrics":["Top-1 Accuracy","Top-5 Accuracy","Accuracy"],"first_row_in_archive_order":{"model":"MOV (ViT-L/14)","paper_title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models","paper_url":"/paper/multimodal-open-vocabulary-video","paper_date":"2022-07-15","arxiv_id":"2207.07646","code_links":[],"syntology":null}},{"leaderboard":"/sota/zero-shot-action-recognition-on-kinetics","slug":"zero-shot-action-recognition-on-kinetics","dataset":"Kinetics","dataset_url":"/dataset/kinetics","rows_in_archive":20,"metrics":["Top-1 Accuracy","Top-5 Accuracy"],"first_row_in_archive_order":{"model":"TC-CLIP","paper_title":"Leveraging Temporal Contextualization for Video Action Recognition","paper_url":"/paper/leveraging-temporal-contextualization-for","paper_date":"2024-04-15","arxiv_id":"2404.09490","code_links":[{"title":"naver-ai/tc-clip","url":"https://github.com/naver-ai/tc-clip"},{"title":"naver-ai/dawin","url":"https://github.com/naver-ai/dawin"}],"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/leveraging-temporal-contextualization-for#ran","syntology_url":"https://syntology.ai/paper/2404.09490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09490"}},"official":{"repos":["naver-ai/tc-clip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/zero-shot-action-recognition-on-olympics","slug":"zero-shot-action-recognition-on-olympics","dataset":"Olympics","dataset_url":null,"rows_in_archive":9,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"SPOT","paper_title":"Synthetic Sample Selection for Generalized Zero-Shot Learning","paper_url":"/paper/synthetic-sample-selection-for-generalized","paper_date":"2023-04-06","arxiv_id":"2304.02846","code_links":[],"syntology":null}},{"leaderboard":"/sota/zero-shot-action-recognition-on-activitynet","slug":"zero-shot-action-recognition-on-activitynet","dataset":"ActivityNet","dataset_url":"/dataset/activitynet","rows_in_archive":5,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"BIKE","paper_title":"Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models","paper_url":"/paper/bidirectional-cross-modal-knowledge","paper_date":"2022-12-31","arxiv_id":"2301.00182","code_links":[{"title":"whwu95/Cap4Video","url":"https://github.com/whwu95/Cap4Video"},{"title":"whwu95/text4vis","url":"https://github.com/whwu95/text4vis"},{"title":"whwu95/GPT4Vis","url":"https://github.com/whwu95/GPT4Vis"},{"title":"whwu95/BIKE","url":"https://github.com/whwu95/BIKE"},{"title":"whwu95/ATM","url":"https://github.com/whwu95/ATM"}],"syntology":null}},{"leaderboard":"/sota/zero-shot-action-recognition-on-charades-1","slug":"zero-shot-action-recognition-on-charades-1","dataset":"Charades","dataset_url":"/dataset/charades","rows_in_archive":4,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MSQNet","paper_title":"Actor-agnostic Multi-label Action Recognition with Multi-modal Query","paper_url":"/paper/msqnet-actor-agnostic-action-recognition-with","paper_date":"2023-07-20","arxiv_id":"2307.10763","code_links":[{"title":"mondalanindya/msqnet","url":"https://github.com/mondalanindya/msqnet"}],"syntology":null}},{"leaderboard":"/sota/zero-shot-action-recognition-on-thumos-14","slug":"zero-shot-action-recognition-on-thumos-14","dataset":"THUMOS' 14","dataset_url":"/dataset/thumos14-1","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MSQNet","paper_title":"Actor-agnostic Multi-label Action Recognition with Multi-modal Query","paper_url":"/paper/msqnet-actor-agnostic-action-recognition-with","paper_date":"2023-07-20","arxiv_id":"2307.10763","code_links":[{"title":"mondalanindya/msqnet","url":"https://github.com/mondalanindya/msqnet"}],"syntology":null}}],"datasets":[{"url":"/dataset/ucf101","name":"UCF101","full_name":"UCF101 Human Actions dataset","num_papers_in_archive":1863},{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/hmdb51","name":"HMDB51","full_name":"","num_papers_in_archive":839},{"url":"/dataset/activitynet","name":"ActivityNet","full_name":"","num_papers_in_archive":807},{"url":"/dataset/charades","name":"Charades","full_name":"","num_papers_in_archive":428},{"url":"/dataset/thumos14-1","name":"THUMOS14","full_name":"","num_papers_in_archive":318}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":83,"of":83,"of_with_code":40,"tagged_in_all":83,"counts":{"archive_papers_tagged":83,"with_a_code_link":40,"where_syntology_ran_a_sample":18,"not_listed_spam_title":0,"listed":83,"listed_where_code_ran":18,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":15,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":15,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/languagebind-extending-video-language","slug":"languagebind-extending-video-language","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","date":"2023-10-03","arxiv_id":"2310.01852","repositories_listed":6,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/languagebind-extending-video-language#ran","syntology_url":"https://syntology.ai/paper/2310.01852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01852"}},"official":{"repos":["pku-yuangroup/languagebind"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/bidirectional-cross-modal-knowledge","slug":"bidirectional-cross-modal-knowledge","title":"Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models","date":"2022-12-31","arxiv_id":"2301.00182","repositories_listed":5,"syntology":null},{"url":"/paper/transferring-textual-knowledge-for-visual","slug":"transferring-textual-knowledge-for-visual","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","date":"2022-07-04","arxiv_id":"2207.01297","repositories_listed":5,"syntology":null},{"url":"/paper/eva-clip-improved-training-techniques-for","slug":"eva-clip-improved-training-techniques-for","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","date":"2023-03-27","arxiv_id":"2303.15389","repositories_listed":4,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/eva-clip-improved-training-techniques-for#ran","syntology_url":"https://syntology.ai/paper/2303.15389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15389"}},"official":{"repos":["baaivision/eva"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/learning-a-deep-embedding-model-for-zero-shot","slug":"learning-a-deep-embedding-model-for-zero-shot","title":"Learning a Deep Embedding Model for Zero-Shot Learning","date":"2016-11-15","arxiv_id":"1611.05088","repositories_listed":4,"syntology":null},{"url":"/paper/leveraging-temporal-contextualization-for","slug":"leveraging-temporal-contextualization-for","title":"Leveraging Temporal Contextualization for Video Action Recognition","date":"2024-04-15","arxiv_id":"2404.09490","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/leveraging-temporal-contextualization-for#ran","syntology_url":"https://syntology.ai/paper/2404.09490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09490"}},"official":{"repos":["naver-ai/tc-clip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/expanding-language-image-pretrained-models","slug":"expanding-language-image-pretrained-models","title":"Expanding Language-Image Pretrained Models for General Video Recognition","date":"2022-08-04","arxiv_id":"2208.02816","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/expanding-language-image-pretrained-models#ran","syntology_url":"https://syntology.ai/paper/2208.02816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02816"}},"official":{"repos":["microsoft/videox"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fitclip-refining-large-scale-pretrained-image","slug":"fitclip-refining-large-scale-pretrained-image","title":"FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks","date":"2022-03-24","arxiv_id":"2203.13371","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fitclip-refining-large-scale-pretrained-image#ran","syntology_url":"https://syntology.ai/paper/2203.13371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13371"}},"official":{"repos":["bryant1410/fitclip","bryant1410/tclip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bridgeformer-bridging-video-text-retrieval","slug":"bridgeformer-bridging-video-text-retrieval","title":"Bridging Video-text Retrieval with Multiple Choice Questions","date":"2022-01-13","arxiv_id":"2201.04850","repositories_listed":2,"syntology":{"n":24,"n_ran":13,"n_constructed":8,"n_ran_checked":9,"n_instrument":4,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":6,"phrase":"13 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/bridgeformer-bridging-video-text-retrieval#ran","syntology_url":"https://syntology.ai/paper/2201.04850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.04850"}},"official":{"repos":["tencentarc/mcq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/actionclip-a-new-paradigm-for-video-action","slug":"actionclip-a-new-paradigm-for-video-action","title":"ActionCLIP: A New Paradigm for Video Action Recognition","date":"2021-09-17","arxiv_id":"2109.08472","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/actionclip-a-new-paradigm-for-video-action#ran","syntology_url":"https://syntology.ai/paper/2109.08472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08472"}},"official":{"repos":["sallymmx/actionclip"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/label-embedding-for-image-classification","slug":"label-embedding-for-image-classification","title":"Label-Embedding for Image Classification","date":"2015-03-30","arxiv_id":"1503.08677","repositories_listed":2,"syntology":null},{"url":"/paper/evaluation-of-output-embeddings-for-fine","slug":"evaluation-of-output-embeddings-for-fine","title":"Evaluation of Output Embeddings for Fine-Grained Image Classification","date":"2014-09-30","arxiv_id":"1409.8403","repositories_listed":2,"syntology":null},{"url":"/paper/building-a-multi-modal-spatiotemporal-expert","slug":"building-a-multi-modal-spatiotemporal-expert","title":"Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP","date":"2024-12-13","arxiv_id":"2412.09895","repositories_listed":1,"syntology":null},{"url":"/paper/locate-gat-modeling-multi-scale-local-context","slug":"locate-gat-modeling-multi-scale-local-context","title":"LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition","date":"2024-11-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tdsm-triplet-diffusion-for-skeleton-text","slug":"tdsm-triplet-diffusion-for-skeleton-text","title":"TDSM: Triplet Diffusion for Skeleton-Text Matching in Zero-Shot Action Recognition","date":"2024-11-16","arxiv_id":"2411.10745","repositories_listed":1,"syntology":null},{"url":"/paper/part-aware-unified-representation-of-language-1","slug":"part-aware-unified-representation-of-language-1","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","date":"2024-06-19","arxiv_id":"2406.13327","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/part-aware-unified-representation-of-language-1#ran","syntology_url":"https://syntology.ai/paper/2406.13327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13327"}},"official":{"repos":["azzh1/purls"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ez-clip-efficient-zeroshot-video-action","slug":"ez-clip-efficient-zeroshot-video-action","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","date":"2023-12-13","arxiv_id":"2312.08010","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":0,"n_instrument":9,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ez-clip-efficient-zeroshot-video-action#ran","syntology_url":"https://syntology.ai/paper/2312.08010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08010"}},"official":{"repos":["shahzadnit/ez-clip"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/ost-refining-text-knowledge-with-optimal","slug":"ost-refining-text-knowledge-with-optimal","title":"OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition","date":"2023-11-30","arxiv_id":"2312.00096","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ost-refining-text-knowledge-with-optimal#ran","syntology_url":"https://syntology.ai/paper/2312.00096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00096"}},"official":{"repos":["tomchen-ctj/OST"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/telling-stories-for-common-sense-zero-shot","slug":"telling-stories-for-common-sense-zero-shot","title":"Telling Stories for Common Sense Zero-Shot Action Recognition","date":"2023-09-29","arxiv_id":"2309.17327","repositories_listed":1,"syntology":null},{"url":"/paper/orthogonal-temporal-interpolation-for-zero","slug":"orthogonal-temporal-interpolation-for-zero","title":"Orthogonal Temporal Interpolation for Zero-Shot Video Recognition","date":"2023-08-14","arxiv_id":"2308.06897","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/orthogonal-temporal-interpolation-for-zero#ran","syntology_url":"https://syntology.ai/paper/2308.06897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06897"}},"official":{"repos":["sweetorangezhuyan/mm2023_oti"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/msqnet-actor-agnostic-action-recognition-with","slug":"msqnet-actor-agnostic-action-recognition-with","title":"Actor-agnostic Multi-label Action Recognition with Multi-modal Query","date":"2023-07-20","arxiv_id":"2307.10763","repositories_listed":1,"syntology":null},{"url":"/paper/internvid-a-large-scale-video-text-dataset","slug":"internvid-a-large-scale-video-text-dataset","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","date":"2023-07-13","arxiv_id":"2307.06942","repositories_listed":1,"syntology":null},{"url":"/paper/vita-clip-video-and-text-adaptive-clip-via","slug":"vita-clip-video-and-text-adaptive-clip-via","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","date":"2023-04-06","arxiv_id":"2304.03307","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/vita-clip-video-and-text-adaptive-clip-via#ran","syntology_url":"https://syntology.ai/paper/2304.03307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03307"}},"official":{"repos":["talalwasim/vita-clip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/match-expand-and-improve-unsupervised","slug":"match-expand-and-improve-unsupervised","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","date":"2023-03-15","arxiv_id":"2303.08914","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/match-expand-and-improve-unsupervised#ran","syntology_url":"https://syntology.ai/paper/2303.08914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08914"}},"official":{"repos":["wlin-at/maxi"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/global-semantic-descriptors-for-zero-shot","slug":"global-semantic-descriptors-for-zero-shot","title":"Global Semantic Descriptors for Zero-Shot Action Recognition","date":"2022-09-24","arxiv_id":"2209.12061","repositories_listed":1,"syntology":null},{"url":"/paper/a-clip-hitchhiker-s-guide-to-long-video","slug":"a-clip-hitchhiker-s-guide-to-long-video","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","date":"2022-05-17","arxiv_id":"2205.08508","repositories_listed":1,"syntology":null},{"url":"/paper/miles-visual-bert-pre-training-with-injected","slug":"miles-visual-bert-pre-training-with-injected","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","date":"2022-04-26","arxiv_id":"2204.12408","repositories_listed":1,"syntology":null},{"url":"/paper/alignment-uniformity-aware-representation","slug":"alignment-uniformity-aware-representation","title":"Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification","date":"2022-03-29","arxiv_id":"2203.15381","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/alignment-uniformity-aware-representation#ran","syntology_url":"https://syntology.ai/paper/2203.15381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15381"}},"official":{"repos":["ShipuLoveMili/CVPR2022-AURL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/rethinking-zero-shot-action-recognition","slug":"rethinking-zero-shot-action-recognition","title":"Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions","date":"2022-03-28","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-action-recognition-with-transformer","slug":"zero-shot-action-recognition-with-transformer","title":"End-to-End Semantic Video Transformer for Zero-Shot Action Recognition","date":"2022-03-10","arxiv_id":"2203.05156","repositories_listed":1,"syntology":null},{"url":"/paper/tell-me-what-you-see-a-zero-shot-action","slug":"tell-me-what-you-see-a-zero-shot-action","title":"Tell me what you see: A zero-shot action recognition method based on natural language descriptions","date":"2021-12-18","arxiv_id":"2112.09976","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-action-recognition-from-diverse","slug":"zero-shot-action-recognition-from-diverse","title":"Zero-Shot Action Recognition from Diverse Object-Scene Compositions","date":"2021-10-26","arxiv_id":"2110.13479","repositories_listed":1,"syntology":null},{"url":"/paper/elaborative-rehearsal-for-zero-shot-action","slug":"elaborative-rehearsal-for-zero-shot-action","title":"Elaborative Rehearsal for Zero-shot Action Recognition","date":"2021-08-05","arxiv_id":"2108.02833","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/elaborative-rehearsal-for-zero-shot-action#ran","syntology_url":"https://syntology.ai/paper/2108.02833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02833"}},"official":{"repos":["DeLightCMU/ElaborativeRehearsal"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/a-new-split-for-evaluating-true-zero-shot","slug":"a-new-split-for-evaluating-true-zero-shot","title":"A New Split for Evaluating True Zero-Shot Action Recognition","date":"2021-07-27","arxiv_id":"2107.13029","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-zero-shot-video-classification-end","slug":"rethinking-zero-shot-video-classification-end","title":"Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications","date":"2020-03-03","arxiv_id":"2003.01455","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/rethinking-zero-shot-video-classification-end#ran","syntology_url":"https://syntology.ai/paper/2003.01455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01455"}},"official":{"repos":["bbrattoli/ZeroShotVideoClassification"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-spatiotemporal-features-via-video","slug":"learning-spatiotemporal-features-via-video","title":"Learning Spatiotemporal Features via Video and Text Pair Discrimination","date":"2020-01-16","arxiv_id":"2001.05691","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-spatiotemporal-features-via-video#ran","syntology_url":"https://syntology.ai/paper/2001.05691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.05691"}},"official":{"repos":["MCG-NJU/CPD-Video"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/i-know-the-relationships-zero-shot-action","slug":"i-know-the-relationships-zero-shot-action","title":"I Know the Relationships: Zero-Shot Action Recognition via Two-Stream Graph Convolutional Networks and Knowledge Graphs","date":"2019-07-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/out-of-distribution-detection-for-generalized","slug":"out-of-distribution-detection-for-generalized","title":"Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition","date":"2019-04-18","arxiv_id":"1904.08703","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/out-of-distribution-detection-for-generalized#ran","syntology_url":"https://syntology.ai/paper/1904.08703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08703"}},"official":{"repos":["naraysa/gzsl-od"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-modal-and-hierarchical-modeling-of","slug":"cross-modal-and-hierarchical-modeling-of","title":"Cross-Modal and Hierarchical Modeling of Video and Text","date":"2018-10-16","arxiv_id":"1810.07212","repositories_listed":1,"syntology":null},{"url":"/paper/an-embarrassingly-simple-approach-to-zero","slug":"an-embarrassingly-simple-approach-to-zero","title":"An embarrassingly simple approach to zero-shot learning","date":"2015-07-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"the-role-of-video-generation-in-enhancing","title":"The Role of Video Generation in Enhancing Data-Limited Action Understanding","date":"2025-05-26","arxiv_id":"2505.19495","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-masking-background-and-object-reduce","title":"Can masking background and object reduce static bias for zero-shot action recognition?","date":"2025-01-22","arxiv_id":"2501.12681","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-guided-cross-modal-prompt-learning","title":"Semantic-guided Cross-Modal Prompt Learning for Skeleton-based Zero-shot Action Recognition","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-action-recognition-in-surveillance","title":"Zero-Shot Action Recognition in Surveillance Videos","date":"2024-10-28","arxiv_id":"2410.21113","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-learning-improves-zero-shot-action","title":"Continual Learning Improves Zero-Shot Action Recognition","date":"2024-10-14","arxiv_id":"2410.10497","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-skeleton-based-action-recognition-1","title":"Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment","date":"2024-09-22","arxiv_id":"2409.14336","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-enhanced-zero-shot-action-recognition-a","title":"Text-Enhanced Zero-Shot Action Recognition: A training-free approach","date":"2024-08-29","arxiv_id":"2408.16412","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-information-compensation-framework-for","title":"An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition","date":"2024-06-02","arxiv_id":"2406.00639","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cross-dataset-study-for-text-based-3d-human","title":"A Cross-Dataset Study for Text-based 3D Human Motion Retrieval","date":"2024-05-27","arxiv_id":"2405.16909","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-compositionality-in-zero-shot","title":"The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks","date":"2024-05-14","arxiv_id":"2405.08695","repositories_listed":0,"syntology":null},{"url":"/paper/fine-grained-side-information-guided-dual","slug":"fine-grained-side-information-guided-dual","title":"Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition","date":"2024-04-11","arxiv_id":"2404.07487","repositories_listed":0,"syntology":null},{"url":null,"slug":"actionhub-a-large-scale-action-video","title":"ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition","date":"2024-01-22","arxiv_id":"2401.11654","repositories_listed":0,"syntology":null},{"url":"/paper/alternating-gradient-descent-and-mixture-of","slug":"alternating-gradient-descent-and-mixture-of","title":"Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception","date":"2023-05-10","arxiv_id":"2305.06324","repositories_listed":0,"syntology":null},{"url":"/paper/synthetic-sample-selection-for-generalized","slug":"synthetic-sample-selection-for-generalized","title":"Synthetic Sample Selection for Generalized Zero-Shot Learning","date":"2023-04-06","arxiv_id":"2304.02846","repositories_listed":0,"syntology":null},{"url":"/paper/victr-video-conditioned-text-representations","slug":"victr-video-conditioned-text-representations","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","date":"2023-04-05","arxiv_id":"2304.02560","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-accuracy-of-zero-shot-action","title":"Improving Zero-Shot Action Recognition using Human Instruction with Text Description","date":"2023-01-21","arxiv_id":"2301.08874","repositories_listed":0,"syntology":null},{"url":"/paper/video-text-modeling-with-zero-shot-transfer","slug":"video-text-modeling-with-zero-shot-transfer","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","date":"2022-12-09","arxiv_id":"2212.04979","repositories_listed":0,"syntology":null},{"url":null,"slug":"rest-retrieve-self-train-for-generative","title":"REST: REtrieve & Self-Train for generative action recognition","date":"2022-09-29","arxiv_id":"2209.15000","repositories_listed":0,"syntology":null},{"url":"/paper/multimodal-open-vocabulary-video","slug":"multimodal-open-vocabulary-video","title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models","date":"2022-07-15","arxiv_id":"2207.07646","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-using-privileged-information-for","title":"Learning Using Privileged Information for Zero-Shot Action Recognition","date":"2022-06-17","arxiv_id":"2206.08632","repositories_listed":0,"syntology":null},{"url":"/paper/cross-modal-representation-learning-for-zero","slug":"cross-modal-representation-learning-for-zero","title":"Cross-modal Representation Learning for Zero-shot Action Recognition","date":"2022-05-03","arxiv_id":"2205.01657","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-prototype-transport-for-zero-shot","title":"Universal Prototype Transport for Zero-Shot Action Recognition and Localization","date":"2022-03-08","arxiv_id":"2203.03971","repositories_listed":0,"syntology":null},{"url":null,"slug":"reformulating-zero-shot-action-recognition","title":"Reformulating Zero-shot Action Recognition for Multi-label Actions","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transductive-universal-transport-for-zero","title":"Transductive Universal Transport for Zero-Shot Action Recognition","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gan-for-vision-kg-for-relation-a-two-stage","title":"GAN for Vision, KG for Relation: a Two-stage Deep Network for Zero-shot Action Recognition","date":"2021-05-25","arxiv_id":"2105.11789","repositories_listed":0,"syntology":null},{"url":"/paper/claster-clustering-with-reinforcement","slug":"claster-clustering-with-reinforcement","title":"CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition","date":"2021-01-18","arxiv_id":"2101.07042","repositories_listed":0,"syntology":null},{"url":"/paper/all-about-knowledge-graphs-for-actions","slug":"all-about-knowledge-graphs-for-actions","title":"All About Knowledge Graphs for Actions","date":"2020-08-28","arxiv_id":"2008.12432","repositories_listed":0,"syntology":null},{"url":null,"slug":"skeleton-based-zero-shot-action-recognition","title":"Skeleton based Zero Shot Action Recognition in Joint Pose-Language Semantic Space","date":"2019-11-26","arxiv_id":"1911.11344","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-action-recognition-in-videos-a","title":"Zero-Shot Action Recognition in Videos: A Survey","date":"2019-09-13","arxiv_id":"1909.06423","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-recognition-in-untrimmed-videos-with","title":"Action Recognition in Untrimmed Videos with Composite Self-Attention Two-Stream Framework","date":"2019-08-04","arxiv_id":"1908.04353","repositories_listed":0,"syntology":null},{"url":"/paper/tarn-temporal-attentive-relation-network-for","slug":"tarn-temporal-attentive-relation-network-for","title":"TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition","date":"2019-07-21","arxiv_id":"1907.09021","repositories_listed":0,"syntology":null},{"url":null,"slug":"action2vec-a-crossmodal-embedding-approach-to","title":"Action2Vec: A Crossmodal Embedding Approach to Action Learning","date":"2019-01-02","arxiv_id":"1901.00484","repositories_listed":0,"syntology":null},{"url":"/paper/towards-universal-representation-for-unseen","slug":"towards-universal-representation-for-unseen","title":"Towards Universal Representation for Unseen Action Recognition","date":"2018-03-22","arxiv_id":"1803.08460","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generative-approach-to-zero-shot-and-few","title":"A Generative Approach to Zero-Shot and Few-Shot Action Recognition","date":"2018-01-27","arxiv_id":"1801.09086","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-language-descriptions-for-human","title":"Natural Language Descriptions for Human Activities in Video Streams","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/zero-shot-action-recognition-with-error","slug":"zero-shot-action-recognition-with-error","title":"Zero-Shot Action Recognition With Error-Correcting Output Codes","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/alternative-semantic-representations-for-zero","slug":"alternative-semantic-representations-for-zero","title":"Alternative Semantic Representations for Zero-Shot Human Action Recognition","date":"2017-06-28","arxiv_id":"1706.09317","repositories_listed":0,"syntology":null},{"url":"/paper/multi-task-zero-shot-action-recognition-with","slug":"multi-task-zero-shot-action-recognition-with","title":"Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation","date":"2016-11-26","arxiv_id":"1611.08663","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-a-pose-lexicon-for-semantic-action","title":"Learning a Pose Lexicon for Semantic Action Recognition","date":"2016-04-01","arxiv_id":"1604.00147","repositories_listed":0,"syntology":null},{"url":null,"slug":"transductive-zero-shot-action-recognition-by","title":"Transductive Zero-Shot Action Recognition by Word-Vector Embedding","date":"2015-11-13","arxiv_id":"1511.04458","repositories_listed":0,"syntology":null},{"url":"/paper/objects2action-classifying-and-localizing","slug":"objects2action-classifying-and-localizing","title":"Objects2action: Classifying and localizing actions without any video example","date":"2015-10-23","arxiv_id":"1510.06939","repositories_listed":0,"syntology":null},{"url":"/paper/semantic-embedding-space-for-zero-shot-action","slug":"semantic-embedding-space-for-zero-shot-action","title":"Semantic Embedding Space for Zero-Shot Action Recognition","date":"2015-02-05","arxiv_id":"1502.01540","repositories_listed":0,"syntology":null},{"url":"/paper/devise-a-deep-visual-semantic-embedding-model","slug":"devise-a-deep-visual-semantic-embedding-model","title":"DeViSE: A Deep Visual-Semantic Embedding Model","date":"2013-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":18,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/zero-shot-action-recognition-on-activitynet","since_archive":"/sota/zero-shot-action-recognition-on-activitynet#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":18,"papers_where_code_ran_first_page":"/task/zero-shot-action-recognition/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/zero-shot-action-recognition/papers/ran/1","json":"/task/zero-shot-action-recognition/papers/ran/1.json","rows":18}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"a32d690842c0e5dd74d85be05f8b5da52beb2511e42e5fa3bf2197c3aa829f7a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}