{"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/multiview-detection-with-shadow-transformer","title":"Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)","arxiv_id":"2108.05888","date":"2021-08-12","proceeding":null,"authors":["Yunzhong Hou","Liang Zheng"],"abstract":"Multiview detection incorporates multiple camera views to deal with occlusions, and its central problem is multiview aggregation. Given feature map projections from multiple views onto a common ground plane, the state-of-the-art method addresses this problem via convolution, which applies the same calculation regardless of object locations. However, such translation-invariant behaviors might not be the best choice, as object features undergo various projection distortions according to their positions and cameras. In this paper, we propose a novel multiview detector, MVDeTr, that adopts a newly introduced shadow transformer to aggregate multiview information. Unlike convolutions, shadow transformer attends differently at different positions and cameras to deal with various shadow-like distortions. We propose an effective training scheme that includes a new view-coherent data augmentation method, which applies random augmentations while maintaining multiview consistency. On two multiview detection benchmarks, we report new state-of-the-art accuracy with the proposed system. Code is available at https://github.com/hou-yz/MVDeTr.","url_abs":"https://arxiv.org/abs/2108.05888v1","url_pdf":"https://arxiv.org/pdf/2108.05888v1.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-shadow-transformer","repo_url":"https://github.com/hou-yz/mvdetr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"multiview-detection","task_name":"Multiview Detection"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multiview-detection-on-cvcs","task":"Multiview Detection","dataset":"CVCS","model":"MVDeTr","rank_in_archive_order":4,"of":6,"metrics":{"F1_score (1m)":"61.0","MODA (1m)":"39.8","MODP (1m)":"84.1","Precision (1m)":"95.3","Recall (1m)":"44.9"},"uses_additional_data":false},{"leaderboard":"/sota/multiview-detection-on-citystreet","task":"Multiview Detection","dataset":"CityStreet","model":"MVDeTr","rank_in_archive_order":2,"of":5,"metrics":{"F1_score (2m)":"75.2","MODA (2m)":"58.3","MODP (2m)":"74.1","Precision (2m)":"92.8","Recall (2m)":"63.2"},"uses_additional_data":false},{"leaderboard":"/sota/multiview-detection-on-multiviewx","task":"Multiview Detection","dataset":"MultiviewX","model":"MVDeTr","rank_in_archive_order":5,"of":9,"metrics":{"MODA":"93.7","MODP":"91.3","Recall":"94.2"},"uses_additional_data":false},{"leaderboard":"/sota/multiview-detection-on-wildtrack","task":"Multiview Detection","dataset":"Wildtrack","model":"MVDeTr","rank_in_archive_order":6,"of":10,"metrics":{"MODA":"91.5","MODP":"82.1","Recall":"94.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.05888","atlas_url":"https://app.syntology.ai/?focus=2108.05888","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2108.05888"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2108.05888\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2108.05888"},"call":"get_concepts_for_paper(arxiv_id=\"2108.05888\")"}],"by_repo":[{"repo":"hou-yz/mvdetr","kind":"official","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":"173e8d8c38fbddc47620847ca8efabf1e0d30f9436571e84966da0456bb33a94","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}