{"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/optimization-planning-for-3d-convnets-1","title":"Optimization Planning for 3D ConvNets","arxiv_id":"2201.04021","date":"2022-01-11","proceeding":null,"authors":["Zhaofan Qiu","Ting Yao","Chong-Wah Ngo","Tao Mei"],"abstract":"It is not trivial to optimally learn a 3D Convolutional Neural Networks (3D ConvNets) due to high complexity and various options of the training scheme. The most common hand-tuning process starts from learning 3D ConvNets using short video clips and then is followed by learning long-term temporal dependency using lengthy clips, while gradually decaying the learning rate from high to low as training progresses. The fact that such process comes along with several heuristic settings motivates the study to seek an optimal \"path\" to automate the entire training. In this paper, we decompose the path into a series of training \"states\" and specify the hyper-parameters, e.g., learning rate and the length of input clips, in each state. The estimation of the knee point on the performance-epoch curve triggers the transition from one state to another. We perform dynamic programming over all the candidate states to plan the optimal permutation of states, i.e., optimization path. Furthermore, we devise a new 3D ConvNets with a unique design of dual-head classifier to improve spatial and temporal discrimination. Extensive experiments on seven public video recognition benchmarks demonstrate the advantages of our proposal. With the optimization planning, our 3D ConvNets achieves superior results when comparing to the state-of-the-art recognition methods. More remarkably, we obtain the top-1 accuracy of 80.5% and 82.7% on Kinetics-400 and Kinetics-600 datasets, respectively. Source code is available at https://github.com/ZhaofanQiu/Optimization-Planning-for-3D-ConvNets.","url_abs":"https://arxiv.org/abs/2201.04021v1","url_pdf":"https://arxiv.org/pdf/2201.04021v1.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":"optimization-planning-for-3d-convnets-1","repo_url":"https://github.com/zhaofanqiu/optimization-planning-for-3d-convnets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"video-recognition","task_name":"Video Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.04021","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.04021"}},"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/zhaofanqiu/optimization-planning-for-3d-convnets","reach":null}],"summary":{"ran":3,"ran_violates":1,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"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":8,"samples":[{"code_sha256_prefix":"27e9e8e851b8e930","entry":"BlockDecoder","repo":"zhaofanqiu/optimization-planning-for-3d-convnets","repo_kind":"official","path":"model/seq_p3d_eftnet.py","file_url":"https://github.com/zhaofanqiu/optimization-planning-for-3d-convnets/blob/HEAD/model/seq_p3d_eftnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"27e9e8e851b8e930"}},{"code_sha256_prefix":"d3671ab17b8f75a2","entry":"Conv3dStaticSamePadding","repo":"zhaofanqiu/optimization-planning-for-3d-convnets","repo_kind":"official","path":"model/seq_p3d_eftnet.py","file_url":"https://github.com/zhaofanqiu/optimization-planning-for-3d-convnets/blob/HEAD/model/seq_p3d_eftnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d3671ab17b8f75a2"}},{"code_sha256_prefix":"71f85132691ac17f","entry":"TemporalConvDW","repo":"zhaofanqiu/optimization-planning-for-3d-convnets","repo_kind":"official","path":"model/seq_p3d_eftnet.py","file_url":"https://github.com/zhaofanqiu/optimization-planning-for-3d-convnets/blob/HEAD/model/seq_p3d_eftnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"71f85132691ac17f"}},{"code_sha256_prefix":"f5555e4360d6910c","entry":"func","repo":"zhaofanqiu/optimization-planning-for-3d-convnets","repo_kind":"official","path":"train_3d_op.py","file_url":"https://github.com/zhaofanqiu/optimization-planning-for-3d-convnets/blob/HEAD/train_3d_op.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f5555e4360d6910c"}},{"code_sha256_prefix":"7826ff814e564735","entry":"get_same_padding_conv3d","repo":"zhaofanqiu/optimization-planning-for-3d-convnets","repo_kind":"official","path":"model/seq_p3d_eftnet.py","file_url":"https://github.com/zhaofanqiu/optimization-planning-for-3d-convnets/blob/HEAD/model/seq_p3d_eftnet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7826ff814e564735"}},{"code_sha256_prefix":"23f2cb856678d5d4","entry":"MBConvBlock","repo":"zhaofanqiu/optimization-planning-for-3d-convnets","repo_kind":"official","path":"model/seq_p3d_eftnet.py","file_url":"https://github.com/zhaofanqiu/optimization-planning-for-3d-convnets/blob/HEAD/model/seq_p3d_eftnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"23f2cb856678d5d4"}},{"code_sha256_prefix":"4701a0d49a1bd596","entry":"SeqEfficientNet","repo":"zhaofanqiu/optimization-planning-for-3d-convnets","repo_kind":"official","path":"model/seq_p3d_eftnet.py","file_url":"https://github.com/zhaofanqiu/optimization-planning-for-3d-convnets/blob/HEAD/model/seq_p3d_eftnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4701a0d49a1bd596"}},{"code_sha256_prefix":"f42bb12a252559be","entry":"load_checkpoint","repo":"zhaofanqiu/optimization-planning-for-3d-convnets","repo_kind":"official","path":"train_3d.py","file_url":"https://github.com/zhaofanqiu/optimization-planning-for-3d-convnets/blob/HEAD/train_3d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f42bb12a252559be"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}