{"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/motionsqueeze-neural-motion-feature-learning","title":"MotionSqueeze: Neural Motion Feature Learning for Video Understanding","arxiv_id":"2007.09933","date":"2020-07-20","proceeding":"ECCV 2020 8","authors":["Heeseung Kwon","Manjin Kim","Suha Kwak","Minsu Cho"],"abstract":"Motion plays a crucial role in understanding videos and most state-of-the-art neural models for video classification incorporate motion information typically using optical flows extracted by a separate off-the-shelf method. As the frame-by-frame optical flows require heavy computation, incorporating motion information has remained a major computational bottleneck for video understanding. In this work, we replace external and heavy computation of optical flows with internal and light-weight learning of motion features. We propose a trainable neural module, dubbed MotionSqueeze, for effective motion feature extraction. Inserted in the middle of any neural network, it learns to establish correspondences across frames and convert them into motion features, which are readily fed to the next downstream layer for better prediction. We demonstrate that the proposed method provides a significant gain on four standard benchmarks for action recognition with only a small amount of additional cost, outperforming the state of the art on Something-Something-V1&V2 datasets.","url_abs":"https://arxiv.org/abs/2007.09933v1","url_pdf":"https://arxiv.org/pdf/2007.09933v1.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":"motionsqueeze-neural-motion-feature-learning","repo_url":"https://github.com/arunos728/MotionSqueeze","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"motionsqueeze-neural-motion-feature-learning","repo_url":"https://github.com/arunos728/arunos728.github.io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"CC0-1.0"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"MSNet-R50 (16 frames, ImageNet pretrained)","rank_in_archive_order":148,"of":207,"metrics":{"Acc@1":"76.4"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-hmdb-51","task":"Action Recognition","dataset":"HMDB-51","model":"MSNet-R50 (16 frames, ImageNet pretrained)","rank_in_archive_order":32,"of":77,"metrics":{"Average accuracy of 3 splits":"77.4"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"MSNet-R50En (ensemble)","rank_in_archive_order":28,"of":74,"metrics":{"Top 1 Accuracy":"55.1"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"MSNet-R50En (8+16 ensemble, ImageNet pretrained)","rank_in_archive_order":31,"of":74,"metrics":{"Top 1 Accuracy":"54.4","Top 5 Accuracy":"83.8"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"MSNet-R50 (16 frames, ImageNet pretrained)","rank_in_archive_order":44,"of":74,"metrics":{"Top 1 Accuracy":"52.1","Top 5 Accuracy":"82.3"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"MSNet-R50 (8 frames, ImageNet pretrained)","rank_in_archive_order":49,"of":74,"metrics":{"Top 1 Accuracy":"50.9","Top 5 Accuracy":"80.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"MSNet-R50En (8+16 ensemble, ImageNet pretrained)","rank_in_archive_order":77,"of":123,"metrics":{"Top-1 Accuracy":"66.6","Top-5 Accuracy":"90.6"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"MSNet-R50 (16 frames, ImageNet pretrained)","rank_in_archive_order":93,"of":123,"metrics":{"Top-1 Accuracy":"64.7","Top-5 Accuracy":"89.4"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"MSNet-R50 (8 frames, ImageNet pretrained)","rank_in_archive_order":100,"of":123,"metrics":{"Top-1 Accuracy":"63","Top-5 Accuracy":"88.4"},"uses_additional_data":true},{"leaderboard":"/sota/video-classification-on-something-something","task":"Video Classification","dataset":"Something-Something V1","model":"MSNet-R50En (ours)","rank_in_archive_order":1,"of":1,"metrics":{"Top-5 Accuracy":"84"},"uses_additional_data":false},{"leaderboard":"/sota/video-classification-on-something-something-1","task":"Video Classification","dataset":"Something-Something V2","model":"MSNet-R50En (ours)","rank_in_archive_order":1,"of":1,"metrics":{"Top-5 Accuracy":"91"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.09933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.09933"}},"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/arunos728/arunos728.github.io","reach":{"status":"ok","spdx":"CC0-1.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arunos728/MotionSqueeze","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"ran_draft_wrong":3,"unverified":5},"by_repo_kind":{"listed":{"samples":8,"ran":3,"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":"d9def42110729a85","entry":"conv1x1","repo":"arunos728/MotionSqueeze","repo_kind":"listed","path":"resnet_TSM.py","file_url":"https://github.com/arunos728/MotionSqueeze/blob/HEAD/resnet_TSM.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"dfcfb80c1514fe42","entry":"conv1x1x1","repo":"arunos728/MotionSqueeze","repo_kind":"listed","path":"resnet_TSM.py","file_url":"https://github.com/arunos728/MotionSqueeze/blob/HEAD/resnet_TSM.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"dfcfb80c1514fe42"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"arunos728/MotionSqueeze","repo_kind":"listed","path":"resnet_TSM.py","file_url":"https://github.com/arunos728/MotionSqueeze/blob/HEAD/resnet_TSM.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"89dc3a28ff96065c","entry":"count_upsample","repo":"arunos728/MotionSqueeze","repo_kind":"listed","path":"thop/count_hooks.py","file_url":"https://github.com/arunos728/MotionSqueeze/blob/HEAD/thop/count_hooks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"89dc3a28ff96065c"}},{"code_sha256_prefix":"caa19f19123b3bc6","entry":"get_grad_hook","repo":"arunos728/MotionSqueeze","repo_kind":"listed","path":"ops/utils.py","file_url":"https://github.com/arunos728/MotionSqueeze/blob/HEAD/ops/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"caa19f19123b3bc6"}},{"code_sha256_prefix":"9f13fea718cf70fb","entry":"log_add","repo":"arunos728/MotionSqueeze","repo_kind":"listed","path":"ops/utils.py","file_url":"https://github.com/arunos728/MotionSqueeze/blob/HEAD/ops/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9f13fea718cf70fb"}},{"code_sha256_prefix":"2fc0c71db48a9af8","entry":"softmax","repo":"arunos728/MotionSqueeze","repo_kind":"listed","path":"ops/utils.py","file_url":"https://github.com/arunos728/MotionSqueeze/blob/HEAD/ops/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2fc0c71db48a9af8"}},{"code_sha256_prefix":"dbc79f862a94c80a","entry":"tsm","repo":"arunos728/MotionSqueeze","repo_kind":"listed","path":"tsm_util.py","file_url":"https://github.com/arunos728/MotionSqueeze/blob/HEAD/tsm_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"dbc79f862a94c80a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}