{"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/vipnas-efficient-video-pose-estimation-via","title":"ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search","arxiv_id":"2105.10154","date":"2021-05-21","proceeding":"CVPR 2021 1","authors":["Lumin Xu","Yingda Guan","Sheng Jin","Wentao Liu","Chen Qian","Ping Luo","Wanli Ouyang","Xiaogang Wang"],"abstract":"Human pose estimation has achieved significant progress in recent years. However, most of the recent methods focus on improving accuracy using complicated models and ignoring real-time efficiency. To achieve a better trade-off between accuracy and efficiency, we propose a novel neural architecture search (NAS) method, termed ViPNAS, to search networks in both spatial and temporal levels for fast online video pose estimation. In the spatial level, we carefully design the search space with five different dimensions including network depth, width, kernel size, group number, and attentions. In the temporal level, we search from a series of temporal feature fusions to optimize the total accuracy and speed across multiple video frames. To the best of our knowledge, we are the first to search for the temporal feature fusion and automatic computation allocation in videos. Extensive experiments demonstrate the effectiveness of our approach on the challenging COCO2017 and PoseTrack2018 datasets. Our discovered model family, S-ViPNAS and T-ViPNAS, achieve significantly higher inference speed (CPU real-time) without sacrificing the accuracy compared to the previous state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2105.10154v1","url_pdf":"https://arxiv.org/pdf/2105.10154v1.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":"vipnas-efficient-video-pose-estimation-via","repo_url":"https://github.com/luminxu/ViPNAS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"vipnas-efficient-video-pose-estimation-via","repo_url":"https://github.com/Insaniauser/ViPNAS_mindspore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"vipnas-efficient-video-pose-estimation-via","repo_url":"https://github.com/open-mmlab/mmpose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"vipnas-efficient-video-pose-estimation-via","repo_url":"https://github.com/yangyucheng000/ViPNAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pose-estimation-on-coco-test-dev","task":"Pose Estimation","dataset":"COCO test-dev","model":"S-ViPNAS-HRNetW32","rank_in_archive_order":24,"of":47,"metrics":{"AP":"73.9","AP50":"91.7","AP75":"82","APL":"79.5","APM":"70.5","AR":"80.4"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-coco-test-dev","task":"Pose Estimation","dataset":"COCO test-dev","model":"S-ViPNAS-Res50","rank_in_archive_order":33,"of":47,"metrics":{"AP":"70.3","AP50":"90.7","AP75":"78.8","APL":"75.5","APM":"67.3","AR":"77.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.10154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.10154"}},"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/open-mmlab/mmpose","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/luminxu/ViPNAS","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyucheng000/ViPNAS","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Insaniauser/ViPNAS_mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1},"listed":{"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":"b233be21e561cea7","entry":"flip_back","repo":"Insaniauser/ViPNAS_mindspore","repo_kind":"listed","path":"vipnas_heatmap_simple_head.py","file_url":"https://github.com/Insaniauser/ViPNAS_mindspore/blob/HEAD/vipnas_heatmap_simple_head.py","link_basis":"harvester_set","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":"b233be21e561cea7"}},{"code_sha256_prefix":"013910f6b74f646c","entry":"keypoint_pck_accuracy","repo":"Insaniauser/ViPNAS_mindspore","repo_kind":"listed","path":"vipnas_heatmap_simple_head.py","file_url":"https://github.com/Insaniauser/ViPNAS_mindspore/blob/HEAD/vipnas_heatmap_simple_head.py","link_basis":"harvester_set","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":"013910f6b74f646c"}},{"code_sha256_prefix":"2c442c9510c3730d","entry":"oks_iou","repo":"Insaniauser/ViPNAS_mindspore","repo_kind":"listed","path":"vipnas_image_load.py","file_url":"https://github.com/Insaniauser/ViPNAS_mindspore/blob/HEAD/vipnas_image_load.py","link_basis":"harvester_set","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":"2c442c9510c3730d"}},{"code_sha256_prefix":"8deae1f6709d3f56","entry":"oks_nms","repo":"Insaniauser/ViPNAS_mindspore","repo_kind":"listed","path":"vipnas_image_load.py","file_url":"https://github.com/Insaniauser/ViPNAS_mindspore/blob/HEAD/vipnas_image_load.py","link_basis":"harvester_set","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":"8deae1f6709d3f56"}},{"code_sha256_prefix":"0fda65413560cdd1","entry":"pose_pck_accuracy","repo":"Insaniauser/ViPNAS_mindspore","repo_kind":"listed","path":"vipnas_heatmap_simple_head.py","file_url":"https://github.com/Insaniauser/ViPNAS_mindspore/blob/HEAD/vipnas_heatmap_simple_head.py","link_basis":"harvester_set","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":"0fda65413560cdd1"}},{"code_sha256_prefix":"000768447d5adf6c","entry":"process_face_det_results","repo":"luminxu/ViPNAS","repo_kind":"official","path":"demo/face_img_demo.py","file_url":"https://github.com/luminxu/ViPNAS/blob/HEAD/demo/face_img_demo.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":true,"mcp_get_code":{"code_sha256":"000768447d5adf6c"}},{"code_sha256_prefix":"2b42edd873dec4be","entry":"process_mmdet_results","repo":"luminxu/ViPNAS","repo_kind":"official","path":"demo/top_down_img_demo_with_mmdet.py","file_url":"https://github.com/luminxu/ViPNAS/blob/HEAD/demo/top_down_img_demo_with_mmdet.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":true,"mcp_get_code":{"code_sha256":"2b42edd873dec4be"}},{"code_sha256_prefix":"1d92f8786335935f","entry":"soft_oks_nms","repo":"Insaniauser/ViPNAS_mindspore","repo_kind":"listed","path":"vipnas_image_load.py","file_url":"https://github.com/Insaniauser/ViPNAS_mindspore/blob/HEAD/vipnas_image_load.py","link_basis":"harvester_set","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":"1d92f8786335935f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}