{"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":"/method/timesformer","slug":"timesformer","name":"TimeSformer","full_name":"TimeSformer","full_name_withheld":false,"description_markdown":"**TimeSformer** is a [convolution](https://paperswithcode.com/method/convolution)-free approach to video classification built exclusively on self-attention over space and time. It adapts the standard [Transformer](https://paperswithcode.com/method/transformer) architecture to video by enabling spatiotemporal feature learning directly from a sequence of frame-level patches. Specifically, the method adapts the image model [[Vision Transformer](https://paperswithcode.com/method/vision-transformer)](https//www.paperswithcode.com/method/vision-transformer) (ViT) to video by extending the self-attention mechanism from the image space to the space-time 3D volume. As in ViT, each patch is linearly mapped into an embedding and augmented with positional information. This makes it possible to interpret the resulting sequence of vector","description_state":"present","introduced_year":null,"introduced_by":{"title":"Is Space-Time Attention All You Need for Video Understanding?","paper":"/paper/is-space-time-attention-all-you-need-for","first_author":"Gedas Bertasius","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/is-space-time-attention-all-you-need-for"},"source":{"url":"https://arxiv.org/abs/2102.05095v4","title":"Is Space-Time Attention All You Need for Video Understanding?","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/pwc-1/paper1/tree/main/models/tapas","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Video Models","url":"/methods/category/generative-video-models","pwc_aliases":[]}],"n_papers_tagged":18,"archive_num_papers":18,"papers_newest_first":[{"paper":null,"slug":"dualx-vsr-dual-axial-spatial-times-temporal","title":"DualX-VSR: Dual Axial Spatial$\\times$Temporal Transformer for Real-World Video Super-Resolution without Motion Compensation","date":"2025-06-05","arxiv_id":"2506.04830","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-video-transformers-for-word-level","title":"Fine-Tuning Video Transformers for Word-Level Bangla Sign Language: A Comparative Analysis for Classification Tasks","date":"2025-06-04","arxiv_id":"2506.04367","n_code_links":0,"syntology":null},{"paper":null,"slug":"skillformer-unified-multi-view-video","title":"SkillFormer: Unified Multi-View Video Understanding for Proficiency Estimation","date":"2025-05-13","arxiv_id":"2505.08665","n_code_links":0,"syntology":null},{"paper":null,"slug":"fedda-tsformer-federated-domain-adaptation","title":"FedDA-TSformer: Federated Domain Adaptation with Vision TimeSformer for Left Ventricle Segmentation on Gated Myocardial Perfusion SPECT Image","date":"2025-02-23","arxiv_id":"2502.16709","n_code_links":0,"syntology":null},{"paper":null,"slug":"eitnet-an-iot-enhanced-framework-for-real","title":"EITNet: An IoT-Enhanced Framework for Real-Time Basketball Action Recognition","date":"2024-10-13","arxiv_id":"2410.09954","n_code_links":0,"syntology":null},{"paper":null,"slug":"3d-lsptm-an-automatic-framework-with-3d-large","title":"3D-LSPTM: An Automatic Framework with 3D-Large-Scale Pretrained Model for Laryngeal Cancer Detection Using Laryngoscopic Videos","date":"2024-09-02","arxiv_id":"2409.01459","n_code_links":0,"syntology":null},{"paper":"/paper/motion-meets-attention-video-motion-prompts","slug":"motion-meets-attention-video-motion-prompts","title":"Motion meets Attention: Video Motion Prompts","date":"2024-07-03","arxiv_id":"2407.03179","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":2,"n_instrument":7,"unverified":2,"pointer_only":7,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","official":{"repos":["q1xiangchen/vmps"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pig-aggression-classification-using-cnn","title":"Pig aggression classification using CNN, Transformers and Recurrent Networks","date":"2024-03-13","arxiv_id":"2403.08528","n_code_links":0,"syntology":null},{"paper":null,"slug":"p-age-pexels-dataset-for-robust-spatio","title":"P-Age: Pexels Dataset for Robust Spatio-Temporal Apparent Age Classification","date":"2023-11-04","arxiv_id":"2311.02432","n_code_links":0,"syntology":null},{"paper":null,"slug":"scalable-and-accurate-self-supervised","title":"Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data","date":"2023-04-04","arxiv_id":"2304.02080","n_code_links":0,"syntology":null},{"paper":null,"slug":"video-question-answering-using-clip-guided","title":"Video Question Answering Using CLIP-Guided Visual-Text Attention","date":"2023-03-06","arxiv_id":"2303.03131","n_code_links":0,"syntology":null},{"paper":"/paper/cholectriplet2022-show-me-a-tool-and-tell-me","slug":"cholectriplet2022-show-me-a-tool-and-tell-me","title":"CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection","date":"2023-02-13","arxiv_id":"2302.06294","n_code_links":2,"syntology":null},{"paper":"/paper/mintime-multi-identity-size-invariant-video","slug":"mintime-multi-identity-size-invariant-video","title":"MINTIME: Multi-Identity Size-Invariant Video Deepfake Detection","date":"2022-11-20","arxiv_id":"2211.10996","n_code_links":1,"syntology":null},{"paper":"/paper/one-model-is-not-enough-ensembles-for","slug":"one-model-is-not-enough-ensembles-for","title":"One Model is Not Enough: Ensembles for Isolated Sign Language Recognition","date":"2022-07-04","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"context-aware-proposal-network-for-temporal","title":"Context-aware Proposal Network for Temporal Action Detection","date":"2022-06-18","arxiv_id":"2206.09082","n_code_links":0,"syntology":null},{"paper":"/paper/vidi-a-video-dataset-of-incidents","slug":"vidi-a-video-dataset-of-incidents","title":"VIDI: A Video Dataset of Incidents","date":"2022-05-26","arxiv_id":"2205.13277","n_code_links":1,"syntology":null},{"paper":"/paper/ia-red-2-interpretability-aware-redundancy","slug":"ia-red-2-interpretability-aware-redundancy","title":"IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers","date":"2021-06-23","arxiv_id":"2106.12620","n_code_links":0,"syntology":null},{"paper":"/paper/is-space-time-attention-all-you-need-for","slug":"is-space-time-attention-all-you-need-for","title":"Is Space-Time Attention All You Need for Video Understanding?","date":"2021-02-09","arxiv_id":"2102.05095","n_code_links":16,"syntology":{"ran":35,"of":43,"n_ran_checked":21,"n_instrument":14,"unverified":8,"pointer_only":14,"phrase":"35 ran (of which 17 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 14 where Syntology's instrument failed) · 8 unverified","official":{"repos":["facebookresearch/TimeSformer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}}],"papers_shown":18,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":18,"with_a_code_link":5,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":18,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"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"},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/method/timesformer/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/timesformer/papers/ran/1","json":"/method/timesformer/papers/ran/1.json","rows":2}],"tasks":[{"task":"/task/action-recognition-in-videos","name":"Action Recognition","papers":3},{"task":"/task/classification-1","name":"Classification","papers":3},{"task":"/task/video-understanding","name":"Video Understanding","papers":3},{"task":"/task/action-classification","name":"Action Classification","papers":2},{"task":"/task/sign-language-recognition","name":"Sign Language Recognition","papers":2},{"task":"/task/video-classification","name":"Video Classification","papers":2},{"task":"/task/video-question-answering","name":"Video Question Answering","papers":2},{"task":"/task/action-detection","name":"Action Detection","papers":1},{"task":"/task/action-triplet-detection","name":"Action Triplet Detection","papers":1},{"task":"/task/action-triplet-recognition","name":"Action Triplet Recognition","papers":1},{"task":"/task/age-classification","name":"Age Classification","papers":1},{"task":"/task/age-estimation","name":"Age Estimation","papers":1},{"task":"/task/all","name":"All","papers":1},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":1},{"task":"/task/automatic-speech-recognition-2","name":"Automatic Speech Recognition","papers":1},{"task":"/task/automatic-speech-recognition","name":"Automatic Speech Recognition (ASR)","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/deepfake-detection","name":"DeepFake Detection","papers":1},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":1}],"tasks_shown":20,"n_tasks":46,"usage_by_year":[{"year":"2021","papers":2},{"year":"2022","papers":4},{"year":"2023","papers":4},{"year":"2024","papers":4},{"year":"2025","papers":4}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/timesformer"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=TimeSformer","read_at":"2026-10-05T01:03:06+00:00","query":"TimeSformer","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"TimeSformer","origin_arxiv_id":"2102.05095"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2102.05095","repositories":{"listed":5,"in_graph":16,"list_truncated":true,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2102.05095","citations":3291},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'TimeSformer'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2102.05095","page":"/paper/is-space-time-attention-all-you-need-for","syntology_url":"https://syntology.ai/paper/2102.05095","in_graph_layer":true,"samples":43,"ran":35,"n_ran_checked":21,"n_instrument":14,"unverified":8,"phrase":"35 ran (of which 17 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 14 where Syntology's instrument failed) · 8 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"repository known, no verified implementation (declared_code; repositories: 5 listed of 16 in the graph, strongest link: official). This answer is about arXiv:2102.05095, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"7ec798cbd977aa3d2caef91f9901dbe99aae323bb4e7583480f4dd110639ebda","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}