{"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/flow-guided-feature-aggregation-for-video","title":"Flow-Guided Feature Aggregation for Video Object Detection","arxiv_id":"1703.10025","date":"2017-03-29","proceeding":"ICCV 2017 10","authors":["Xizhou Zhu","Yujie Wang","Jifeng Dai","Lu Yuan","Yichen Wei"],"abstract":"Extending state-of-the-art object detectors from image to video is\nchallenging. The accuracy of detection suffers from degenerated object\nappearances in videos, e.g., motion blur, video defocus, rare poses, etc.\nExisting work attempts to exploit temporal information on box level, but such\nmethods are not trained end-to-end. We present flow-guided feature aggregation,\nan accurate and end-to-end learning framework for video object detection. It\nleverages temporal coherence on feature level instead. It improves the\nper-frame features by aggregation of nearby features along the motion paths,\nand thus improves the video recognition accuracy. Our method significantly\nimproves upon strong single-frame baselines in ImageNet VID, especially for\nmore challenging fast moving objects. Our framework is principled, and on par\nwith the best engineered systems winning the ImageNet VID challenges 2016,\nwithout additional bells-and-whistles. The proposed method, together with Deep\nFeature Flow, powered the winning entry of ImageNet VID challenges 2017. The\ncode is available at\nhttps://github.com/msracver/Flow-Guided-Feature-Aggregation.","url_abs":"http://arxiv.org/abs/1703.10025v2","url_pdf":"http://arxiv.org/pdf/1703.10025v2.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":"flow-guided-feature-aggregation-for-video","repo_url":"https://github.com/msracver/Flow-Guided-Feature-Aggregation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"flow-guided-feature-aggregation-for-video","repo_url":"https://github.com/open-mmlab/mmtracking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"video-object-detection","task_name":"Video Object Detection"},{"task_slug":"video-recognition","task_name":"Video Recognition"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-object-detection-on-imagenet-vid","task":"Video Object Detection","dataset":"ImageNet VID","model":"FGFA + Seq-NMS","rank_in_archive_order":29,"of":33,"metrics":{"MAP ":"80.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.10025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.10025"}},"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/msracver/Flow-Guided-Feature-Aggregation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmtracking","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"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":3,"samples":[{"code_sha256_prefix":"a4a7686e6b1d66b2","entry":"bbox_overlaps_py","repo":"msracver/Flow-Guided-Feature-Aggregation","repo_kind":"official","path":"lib/bbox/bbox_transform.py","file_url":"https://github.com/msracver/Flow-Guided-Feature-Aggregation/blob/HEAD/lib/bbox/bbox_transform.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"a4a7686e6b1d66b2"}},{"code_sha256_prefix":"16007fcf12b066d0","entry":"clip_boxes","repo":"msracver/Flow-Guided-Feature-Aggregation","repo_kind":"official","path":"lib/bbox/bbox_transform.py","file_url":"https://github.com/msracver/Flow-Guided-Feature-Aggregation/blob/HEAD/lib/bbox/bbox_transform.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"16007fcf12b066d0"}},{"code_sha256_prefix":"bbf8005ce03c08cf","entry":"get_rcnn_names","repo":"msracver/Flow-Guided-Feature-Aggregation","repo_kind":"official","path":"fgfa_rfcn/core/metric.py","file_url":"https://github.com/msracver/Flow-Guided-Feature-Aggregation/blob/HEAD/fgfa_rfcn/core/metric.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"bbf8005ce03c08cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}