{"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/late-temporal-modeling-in-3d-cnn","title":"Late Temporal Modeling in 3D CNN Architectures with BERT for Action Recognition","arxiv_id":"2008.01232","date":"2020-08-03","proceeding":null,"authors":["M. Esat Kalfaoglu","Sinan Kalkan","A. Aydin Alatan"],"abstract":"In this work, we combine 3D convolution with late temporal modeling for action recognition. For this aim, we replace the conventional Temporal Global Average Pooling (TGAP) layer at the end of 3D convolutional architecture with the Bidirectional Encoder Representations from Transformers (BERT) layer in order to better utilize the temporal information with BERT's attention mechanism. We show that this replacement improves the performances of many popular 3D convolution architectures for action recognition, including ResNeXt, I3D, SlowFast and R(2+1)D. Moreover, we provide the-state-of-the-art results on both HMDB51 and UCF101 datasets with 85.10% and 98.69% top-1 accuracy, respectively. The code is publicly available.","url_abs":"https://arxiv.org/abs/2008.01232v3","url_pdf":"https://arxiv.org/pdf/2008.01232v3.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":"late-temporal-modeling-in-3d-cnn","repo_url":"https://github.com/artest08/LateTemporalModeling3DCNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"late-temporal-modeling-in-3d-cnn","repo_url":"https://github.com/kietngt00/hmdb51-recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"}],"methods":[{"method_slug":"2-1-d-convolution","method_name":"(2+1)D Convolution"},{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"3d-convolution","method_name":"3D Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"r-2-1-d","method_name":"R(2+1)D"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"resnext","method_name":"ResNeXt"},{"method_slug":"resnext-block","method_name":"ResNeXt Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-recognition-in-videos-on-hmdb-51","task":"Action Recognition","dataset":"HMDB-51","model":"R2+1D-BERT","rank_in_archive_order":7,"of":77,"metrics":{"Average accuracy of 3 splits":"85.10"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-on-ucf-101","task":"Action Recognition","dataset":"UCF 101","model":"R2+1D-BERT","rank_in_archive_order":1,"of":1,"metrics":{"3-fold Accuracy":"98.69"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2008.01232","atlas_url":"https://app.syntology.ai/?focus=2008.01232","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":"2008.01232"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2008.01232\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2008.01232"},"call":"get_concepts_for_paper(arxiv_id=\"2008.01232\")"}],"by_repo":[{"repo":"artest08/LateTemporalModeling3DCNN","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"kietngt00/hmdb51-recognition","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1711.11248","2103.03206"],"harvested_for_calls":[{"arxiv_id":"1711.11248","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1711.11248"},"call":"get_harvested_code_for_paper(arxiv_id=\"1711.11248\")"},{"arxiv_id":"2103.03206","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.03206"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.03206\")"}]}],"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":"5cec8fe2ef695c4e33d74e90328a1a78996f735df1f0b0d357021c7f42310d20","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}