{"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/more-is-less-learning-efficient-video-1","title":"More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation","arxiv_id":"1912.00869","date":"2019-12-02","proceeding":"NeurIPS 2019 12","authors":["Quanfu Fan","Chun-Fu Chen","Hilde Kuehne","Marco Pistoia","David Cox"],"abstract":"Current state-of-the-art models for video action recognition are mostly based on expensive 3D ConvNets. This results in a need for large GPU clusters to train and evaluate such architectures. To address this problem, we present a lightweight and memory-friendly architecture for action recognition that performs on par with or better than current architectures by using only a fraction of resources. The proposed architecture is based on a combination of a deep subnet operating on low-resolution frames with a compact subnet operating on high-resolution frames, allowing for high efficiency and accuracy at the same time. We demonstrate that our approach achieves a reduction by $3\\sim4$ times in FLOPs and $\\sim2$ times in memory usage compared to the baseline. This enables training deeper models with more input frames under the same computational budget. To further obviate the need for large-scale 3D convolutions, a temporal aggregation module is proposed to model temporal dependencies in a video at very small additional computational costs. Our models achieve strong performance on several action recognition benchmarks including Kinetics, Something-Something and Moments-in-time. The code and models are available at https://github.com/IBM/bLVNet-TAM.","url_abs":"https://arxiv.org/abs/1912.00869v1","url_pdf":"https://arxiv.org/pdf/1912.00869v1.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":"more-is-less-learning-efficient-video-1","repo_url":"https://github.com/IBM/bLVNet-TAM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"bLVNet Fan et al. (2019)","rank_in_archive_order":168,"of":207,"metrics":{"Acc@1":"73.5","Acc@5":"91.2"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"bLVNet","rank_in_archive_order":90,"of":123,"metrics":{"Top-1 Accuracy":"65.2"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.00869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00869"}},"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/IBM/bLVNet-TAM","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"f9d7c39899b76464","entry":"accuracy","repo":"IBM/bLVNet-TAM","repo_kind":"official","path":"core/video_utils.py","file_url":"https://github.com/IBM/bLVNet-TAM/blob/HEAD/core/video_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9d7c39899b76464"}},{"code_sha256_prefix":"88e0b6615c11d561","entry":"blvnet_tam_backbone","repo":"IBM/bLVNet-TAM","repo_kind":"official","path":"core/models/blvnet_tam_backbone.py","file_url":"https://github.com/IBM/bLVNet-TAM/blob/HEAD/core/models/blvnet_tam_backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"88e0b6615c11d561"}},{"code_sha256_prefix":"48d6462978ea5c3b","entry":"build_model","repo":"IBM/bLVNet-TAM","repo_kind":"official","path":"core/video_utils.py","file_url":"https://github.com/IBM/bLVNet-TAM/blob/HEAD/core/video_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"48d6462978ea5c3b"}},{"code_sha256_prefix":"ad3e2f9e9ecf926f","entry":"get_augmentor","repo":"IBM/bLVNet-TAM","repo_kind":"official","path":"core/video_utils.py","file_url":"https://github.com/IBM/bLVNet-TAM/blob/HEAD/core/video_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ad3e2f9e9ecf926f"}},{"code_sha256_prefix":"3f3f0085bff43541","entry":"get_frame_list","repo":"IBM/bLVNet-TAM","repo_kind":"official","path":"core/models/blvnet_tam_backbone.py","file_url":"https://github.com/IBM/bLVNet-TAM/blob/HEAD/core/models/blvnet_tam_backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3f3f0085bff43541"}},{"code_sha256_prefix":"7edc2bcdea46f6ba","entry":"random_clip","repo":"IBM/bLVNet-TAM","repo_kind":"official","path":"core/video_dataset.py","file_url":"https://github.com/IBM/bLVNet-TAM/blob/HEAD/core/video_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7edc2bcdea46f6ba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}