{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/mars-motion-augmented-rgb-stream-for-action","title":"MARS: Motion-Augmented RGB Stream for Action Recognition","arxiv_id":null,"date":"2019-06-01","proceeding":"CVPR 2019 6","authors":["Nieves Crasto"," Philippe Weinzaepfel"," Karteek Alahari"," Cordelia Schmid"],"abstract":"Most state-of-the-art methods for action recognition consist of a two-stream architecture with 3D convolutions: an appearance stream for RGB frames and a motion stream for optical flow frames.  Although combining flow with RGB improves the performance, the cost of computing accurate optical flow is high, and increases action recognition latency. This limits the usage of two-stream approaches in real-world applications requiring low latency. In this paper, we introduce two learning approaches to train a standard 3D CNN, operating on RGB frames, that mimics the motion stream, and as a result avoids flow computation at test time.  First, by minimizing a feature-based loss compared to the Flow stream, we show that the network reproduces the motion stream with high fidelity.  Second, to leverage both appearance and motion information effectively, we train with a linear combination of the feature-based loss and the standard cross-entropy loss for action recognition. We denote the stream trained using this combined loss as Motion-Augmented RGB Stream (MARS). As a single stream, MARS performs better than RGB or Flow alone, for instance with 72.7% accuracy on Kinetics compared to 72.0% and 65.6% with RGB and Flow streams respectively.\r","url_abs":"http://openaccess.thecvf.com/content_CVPR_2019/html/Crasto_MARS_Motion-Augmented_RGB_Stream_for_Action_Recognition_CVPR_2019_paper.html","url_pdf":"http://openaccess.thecvf.com/content_CVPR_2019/papers/Crasto_MARS_Motion-Augmented_RGB_Stream_for_Action_Recognition_CVPR_2019_paper.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":"mars-motion-augmented-rgb-stream-for-action","repo_url":"https://github.com/craston/MARS","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":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"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":"MARS+RGB+Flow (64 frames)","rank_in_archive_order":159,"of":207,"metrics":{"Acc@1":"74.9"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"MARS+RGB+Flow (16 frames)","rank_in_archive_order":182,"of":207,"metrics":{"Acc@1":"68.9"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-minikinetics","task":"Action Classification","dataset":"MiniKinetics","model":"MARS+RGB+Flow (16 frames)","rank_in_archive_order":1,"of":1,"metrics":{"Top-1 Accuracy":"73.5"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-hmdb-51","task":"Action Recognition","dataset":"HMDB-51","model":"MARS+RGB+FLow (64 frames, Kinetics pretrained)","rank_in_archive_order":19,"of":77,"metrics":{"Average accuracy of 3 splits":"80.9"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"MARS+RGB+Flow (64 frames, Kinetics pretrained)","rank_in_archive_order":39,"of":74,"metrics":{"Top 1 Accuracy":"53.0"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"MARS+RGB+Flow (16 frames, Kinetics pretrained)","rank_in_archive_order":73,"of":74,"metrics":{"Top 1 Accuracy":"40.4"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-ucf101","task":"Action Recognition","dataset":"UCF101","model":"MARS+RGB+Flow (64 frames, Kinetics pretrained)","rank_in_archive_order":13,"of":91,"metrics":{"3-fold Accuracy":"97.8"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-ucf101","task":"Action Recognition","dataset":"UCF101","model":"MARS+RGB+Flow (16 frames)","rank_in_archive_order":41,"of":91,"metrics":{"3-fold Accuracy":"95.8"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"craston/MARS","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"81822fccf1f58f68abbec49f8b284f9e0c46d84ab408c566bb6ad206f68be4e8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}