{"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/multiview-detection-with-feature-perspective","title":"Multiview Detection with Feature Perspective Transformation","arxiv_id":"2007.07247","date":"2020-07-14","proceeding":"ECCV 2020 8","authors":["Yunzhong Hou","Liang Zheng","Stephen Gould"],"abstract":"Incorporating multiple camera views for detection alleviates the impact of occlusions in crowded scenes. In a multiview system, we need to answer two important questions when dealing with ambiguities that arise from occlusions. First, how should we aggregate cues from the multiple views? Second, how should we aggregate unreliable 2D and 3D spatial information that has been tainted by occlusions? To address these questions, we propose a novel multiview detection system, MVDet. For multiview aggregation, existing methods combine anchor box features from the image plane, which potentially limits performance due to inaccurate anchor box shapes and sizes. In contrast, we take an anchor-free approach to aggregate multiview information by projecting feature maps onto the ground plane (bird's eye view). To resolve any remaining spatial ambiguity, we apply large kernel convolutions on the ground plane feature map and infer locations from detection peaks. Our entire model is end-to-end learnable and achieves 88.2% MODA on the standard Wildtrack dataset, outperforming the state-of-the-art by 14.1%. We also provide detailed analysis of MVDet on a newly introduced synthetic dataset, MultiviewX, which allows us to control the level of occlusion. Code and MultiviewX dataset are available at https://github.com/hou-yz/MVDet.","url_abs":"https://arxiv.org/abs/2007.07247v2","url_pdf":"https://arxiv.org/pdf/2007.07247v2.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":"multiview-detection-with-feature-perspective","repo_url":"https://github.com/hou-yz/MVDet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multiview-detection-with-feature-perspective","repo_url":"https://github.com/hou-yz/multiviewx","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"multiview-detection-with-feature-perspective","repo_url":"https://github.com/shaojiawei07/tocom-tem","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"human-detection","task_name":"Human Detection"},{"task_slug":"multiview-detection","task_name":"Multiview Detection"},{"task_slug":"pedestrian-detection","task_name":"Pedestrian Detection"}],"methods":[],"datasets_introduced":[{"slug":"multiviewx","name":"MultiviewX","full_name":null}],"methods_introduced":[],"results":[{"leaderboard":"/sota/multiview-detection-on-cvcs","task":"Multiview Detection","dataset":"CVCS","model":"MVDet","rank_in_archive_order":5,"of":6,"metrics":{"F1_score (1m)":"60.9","MODA (1m)":"36.6","MODP (1m)":"71.0","Precision (1m)":"79.4","Recall (1m)":"49.4"},"uses_additional_data":false},{"leaderboard":"/sota/multiview-detection-on-citystreet","task":"Multiview Detection","dataset":"CityStreet","model":"MVDet","rank_in_archive_order":5,"of":5,"metrics":{"F1_score (2m)":"68.4","MODA (2m)":"44.6","MODP (2m)":"65.7","Precision (2m)":"79.8","Recall (2m)":"59.8"},"uses_additional_data":false},{"leaderboard":"/sota/multiview-detection-on-multiviewx","task":"Multiview Detection","dataset":"MultiviewX","model":"MVDet","rank_in_archive_order":6,"of":9,"metrics":{"MODA":"93.6","MODP":"79.6","Recall":"86.7"},"uses_additional_data":false},{"leaderboard":"/sota/multiview-detection-on-wildtrack","task":"Multiview Detection","dataset":"Wildtrack","model":"MVDet","rank_in_archive_order":9,"of":10,"metrics":{"MODA":"88.2","MODP":"75.7","Recall":"93.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.07247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.07247"}},"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/hou-yz/multiviewx","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hou-yz/MVDet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shaojiawei07/tocom-tem","reach":{"status":"ok"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"efc084e3bd24f19b","entry":"evaluate","repo":"hou-yz/MVDet","repo_kind":"official","path":"multiview_detector/evaluation/evaluate.py","file_url":"https://github.com/hou-yz/MVDet/blob/HEAD/multiview_detector/evaluation/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"efc084e3bd24f19b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}