{"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":"/paper/beyond-short-snippets-deep-networks-for-video","title":"Beyond Short Snippets: Deep Networks for Video Classification","arxiv_id":"1503.08909","date":"2015-03-31","proceeding":"CVPR 2015 6","authors":["Joe Yue-Hei Ng","Matthew Hausknecht","Sudheendra Vijayanarasimhan","Oriol Vinyals","Rajat Monga","George Toderici"],"abstract":"Convolutional neural networks (CNNs) have been extensively applied for image\nrecognition problems giving state-of-the-art results on recognition, detection,\nsegmentation and retrieval. In this work we propose and evaluate several deep\nneural network architectures to combine image information across a video over\nlonger time periods than previously attempted. We propose two methods capable\nof handling full length videos. The first method explores various convolutional\ntemporal feature pooling architectures, examining the various design choices\nwhich need to be made when adapting a CNN for this task. The second proposed\nmethod explicitly models the video as an ordered sequence of frames. For this\npurpose we employ a recurrent neural network that uses Long Short-Term Memory\n(LSTM) cells which are connected to the output of the underlying CNN. Our best\nnetworks exhibit significant performance improvements over previously published\nresults on the Sports 1 million dataset (73.1% vs. 60.9%) and the UCF-101\ndatasets with (88.6% vs. 88.0%) and without additional optical flow information\n(82.6% vs. 72.8%).","url_abs":"http://arxiv.org/abs/1503.08909v2","url_pdf":"http://arxiv.org/pdf/1503.08909v2.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":"beyond-short-snippets-deep-networks-for-video","repo_url":"https://github.com/shobrook/sequitur","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"video-classification","task_name":"Video Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-recognition-in-videos-on-sports-1m","task":"Action Recognition","dataset":"Sports-1M","model":"Conv pooling","rank_in_archive_order":5,"of":9,"metrics":{"Video hit@1 ":"71.7","Video hit@5":"90.4"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-ucf101","task":"Action Recognition","dataset":"UCF101","model":"Two-stream+LSTM","rank_in_archive_order":73,"of":91,"metrics":{"3-fold Accuracy":"88.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1503.08909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1503.08909"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shobrook/sequitur","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"590bbf6f7d2ddc13","entry":"compute_output_dim","repo":"shobrook/sequitur","repo_kind":"listed","path":"sequitur/models/conv_ae.py","file_url":"https://github.com/shobrook/sequitur/blob/HEAD/sequitur/models/conv_ae.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"590bbf6f7d2ddc13"}},{"code_sha256_prefix":"160b87704a7f2036","entry":"get_encodings","repo":"shobrook/sequitur","repo_kind":"listed","path":"sequitur/quick_train.py","file_url":"https://github.com/shobrook/sequitur/blob/HEAD/sequitur/quick_train.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"160b87704a7f2036"}},{"code_sha256_prefix":"481ed07ba498c9d1","entry":"instantiate_model","repo":"shobrook/sequitur","repo_kind":"listed","path":"sequitur/quick_train.py","file_url":"https://github.com/shobrook/sequitur/blob/HEAD/sequitur/quick_train.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"481ed07ba498c9d1"}},{"code_sha256_prefix":"f030dab388fecfc9","entry":"train_model","repo":"shobrook/sequitur","repo_kind":"listed","path":"sequitur/quick_train.py","file_url":"https://github.com/shobrook/sequitur/blob/HEAD/sequitur/quick_train.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f030dab388fecfc9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}