{"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/cms-rcnn-contextual-multi-scale-region-based","title":"CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection","arxiv_id":"1606.05413","date":"2016-06-17","proceeding":null,"authors":["Chenchen Zhu","Yutong Zheng","Khoa Luu","Marios Savvides"],"abstract":"Robust face detection in the wild is one of the ultimate components to\nsupport various facial related problems, i.e. unconstrained face recognition,\nfacial periocular recognition, facial landmarking and pose estimation, facial\nexpression recognition, 3D facial model construction, etc. Although the face\ndetection problem has been intensely studied for decades with various\ncommercial applications, it still meets problems in some real-world scenarios\ndue to numerous challenges, e.g. heavy facial occlusions, extremely low\nresolutions, strong illumination, exceptionally pose variations, image or video\ncompression artifacts, etc. In this paper, we present a face detection approach\nnamed Contextual Multi-Scale Region-based Convolution Neural Network (CMS-RCNN)\nto robustly solve the problems mentioned above. Similar to the region-based\nCNNs, our proposed network consists of the region proposal component and the\nregion-of-interest (RoI) detection component. However, far apart of that\nnetwork, there are two main contributions in our proposed network that play a\nsignificant role to achieve the state-of-the-art performance in face detection.\nFirstly, the multi-scale information is grouped both in region proposal and RoI\ndetection to deal with tiny face regions. Secondly, our proposed network allows\nexplicit body contextual reasoning in the network inspired from the intuition\nof human vision system. The proposed approach is benchmarked on two recent\nchallenging face detection databases, i.e. the WIDER FACE Dataset which\ncontains high degree of variability, as well as the Face Detection Dataset and\nBenchmark (FDDB). The experimental results show that our proposed approach\ntrained on WIDER FACE Dataset outperforms strong baselines on WIDER FACE\nDataset by a large margin, and consistently achieves competitive results on\nFDDB against the recent state-of-the-art face detection methods.","url_abs":"http://arxiv.org/abs/1606.05413v1","url_pdf":"http://arxiv.org/pdf/1606.05413v1.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":[],"tasks":[{"task_slug":"face-detection","task_name":"Face Detection"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"facial-expression-recognition-1","task_name":"Facial Expression Recognition"},{"task_slug":"facial-expression-recognition","task_name":"Facial Expression Recognition (FER)"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"robust-face-recognition","task_name":"Robust Face Recognition"},{"task_slug":"video-compression","task_name":"Video Compression"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-detection-on-wider-face-hard","task":"Face Detection","dataset":"WIDER Face (Hard)","model":"CMS-RCNN","rank_in_archive_order":33,"of":40,"metrics":{"AP":"0.643"},"uses_additional_data":false},{"leaderboard":"/sota/face-detection-on-wider-face-medium","task":"Face Detection","dataset":"WIDER Face (Medium)","model":"CMS-RCNN","rank_in_archive_order":29,"of":37,"metrics":{"AP":"0.874"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"82fa1ec4e8ce596f0ce7cd3afb7586b69ba4137c8866b89ade173256f24eaca5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}