{"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/video-classification-with-channel-separated","title":"Video Classification with Channel-Separated Convolutional Networks","arxiv_id":"1904.02811","date":"2019-04-04","proceeding":"ICCV 2019 10","authors":["Du Tran","Heng Wang","Lorenzo Torresani","Matt Feiszli"],"abstract":"Group convolution has been shown to offer great computational savings in various 2D convolutional architectures for image classification. It is natural to ask: 1) if group convolution can help to alleviate the high computational cost of video classification networks; 2) what factors matter the most in 3D group convolutional networks; and 3) what are good computation/accuracy trade-offs with 3D group convolutional networks. This paper studies the effects of different design choices in 3D group convolutional networks for video classification. We empirically demonstrate that the amount of channel interactions plays an important role in the accuracy of 3D group convolutional networks. Our experiments suggest two main findings. First, it is a good practice to factorize 3D convolutions by separating channel interactions and spatiotemporal interactions as this leads to improved accuracy and lower computational cost. Second, 3D channel-separated convolutions provide a form of regularization, yielding lower training accuracy but higher test accuracy compared to 3D convolutions. These two empirical findings lead us to design an architecture -- Channel-Separated Convolutional Network (CSN) -- which is simple, efficient, yet accurate. On Sports1M, Kinetics, and Something-Something, our CSNs are comparable with or better than the state-of-the-art while being 2-3 times more efficient.","url_abs":"https://arxiv.org/abs/1904.02811v4","url_pdf":"https://arxiv.org/pdf/1904.02811v4.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":"video-classification-with-channel-separated","repo_url":"https://github.com/facebookresearch/VMZ","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"caffe2","reach":null},{"paper_slug":"video-classification-with-channel-separated","repo_url":"https://github.com/BB-Repos/BBaction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"video-classification-with-channel-separated","repo_url":"https://github.com/facebookresearch/R2Plus1D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"video-classification-with-channel-separated","repo_url":"https://github.com/salinasJJ/BBaction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"video-classification-with-channel-separated","repo_url":"https://github.com/Mind23-2/MindCode-62","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"video-classification-with-channel-separated","repo_url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/r2plus1d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"video-classification-with-channel-separated","repo_url":"https://github.com/open-mmlab/mmaction2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"ir-CSN-152 (IG-65M pretraining)","rank_in_archive_order":75,"of":207,"metrics":{"Acc@1":"82.6"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"ip-CSN-152 (IG-65M pretraining)","rank_in_archive_order":76,"of":207,"metrics":{"Acc@1":"82.5","Acc@5":"95.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"R[2+1]D-152 (IG-65M pretraining)","rank_in_archive_order":85,"of":207,"metrics":{"Acc@1":"81.3","Acc@5":"95.1"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"ip-CSN-152 (Sports-1M pretraining)","rank_in_archive_order":115,"of":207,"metrics":{"Acc@1":"79.2","Acc@5":"93.8"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"ip-CSN-152","rank_in_archive_order":133,"of":207,"metrics":{"Acc@1":"77.8","Acc@5":"92.8"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"ip-CSN-152 (IG-65M pretraining)","rank_in_archive_order":38,"of":74,"metrics":{"Top 1 Accuracy":"53.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"ir-CSN-152 (IG-65M pretraining)","rank_in_archive_order":45,"of":74,"metrics":{"Top 1 Accuracy":"52.1"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"R(2+1)D-152 (IG-65M pretraining)","rank_in_archive_order":48,"of":74,"metrics":{"Top 1 Accuracy":"51.6"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"ir-CSN-152","rank_in_archive_order":58,"of":74,"metrics":{"Top 1 Accuracy":"49.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"ir-CSN-101","rank_in_archive_order":61,"of":74,"metrics":{"Top 1 Accuracy":"48.4"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-sports-1m","task":"Action Recognition","dataset":"Sports-1M","model":"ip-CSN-152 (RGB)","rank_in_archive_order":1,"of":9,"metrics":{"Video hit@1 ":"75.5","Video hit@5":"92.8"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-sports-1m","task":"Action Recognition","dataset":"Sports-1M","model":"ip-CSN-101 (RGB)","rank_in_archive_order":2,"of":9,"metrics":{"Video hit@1 ":"74.9","Video hit@5":"92.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.02811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02811"}},"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/facebookresearch/VMZ","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BB-Repos/BBaction","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-62","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/R2Plus1D","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/r2plus1d","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmaction2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/salinasJJ/BBaction","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":3,"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":"33fb556271040441","entry":"create_model","repo":"facebookresearch/VMZ","repo_kind":"official","path":"c2/lib/models/c3d_model.py","file_url":"https://github.com/facebookresearch/VMZ/blob/HEAD/c2/lib/models/c3d_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"33fb556271040441"}},{"code_sha256_prefix":"5baa7042c409d2e7","entry":"filter_params","repo":"BB-Repos/BBaction","repo_kind":"listed","path":"bbaction/utils.py","file_url":"https://github.com/BB-Repos/BBaction/blob/HEAD/bbaction/utils.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":"5baa7042c409d2e7"}},{"code_sha256_prefix":"12bb8e0fc99d6746","entry":"get_type","repo":"BB-Repos/BBaction","repo_kind":"listed","path":"bbaction/utils.py","file_url":"https://github.com/BB-Repos/BBaction/blob/HEAD/bbaction/utils.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":"12bb8e0fc99d6746"}},{"code_sha256_prefix":"581a651c6ef2acf8","entry":"type_check","repo":"BB-Repos/BBaction","repo_kind":"listed","path":"bbaction/utils.py","file_url":"https://github.com/BB-Repos/BBaction/blob/HEAD/bbaction/utils.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":"581a651c6ef2acf8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}