{"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/detection-recovery-in-online-multi-object","title":"Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker","arxiv_id":"2205.00968","date":"2022-05-02","proceeding":null,"authors":["Jeongseok Hyun","Myunggu Kang","Dongyoon Wee","Dit-yan Yeung"],"abstract":"In existing joint detection and tracking methods, pairwise relational features are used to match previous tracklets to current detections. However, the features may not be discriminative enough for a tracker to identify a target from a large number of detections. Selecting only high-scored detections for tracking may lead to missed detections whose confidence score is low. Consequently, in the online setting, this results in disconnections of tracklets which cannot be recovered. In this regard, we present Sparse Graph Tracker (SGT), a novel online graph tracker using higher-order relational features which are more discriminative by aggregating the features of neighboring detections and their relations. SGT converts video data into a graph where detections, their connections, and the relational features of two connected nodes are represented by nodes, edges, and edge features, respectively. The strong edge features allow SGT to track targets with tracking candidates selected by top-K scored detections with large K. As a result, even low-scored detections can be tracked, and the missed detections are also recovered. The robustness of K value is shown through the extensive experiments. In the MOT16/17/20 and HiEve Challenge, SGT outperforms the state-of-the-art trackers with real-time inference speed. Especially, a large improvement in MOTA is shown in the MOT20 and HiEve Challenge. Code is available at https://github.com/HYUNJS/SGT.","url_abs":"https://arxiv.org/abs/2205.00968v3","url_pdf":"https://arxiv.org/pdf/2205.00968v3.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":"detection-recovery-in-online-multi-object","repo_url":"https://github.com/hyunjs/sgt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"online-multi-object-tracking","task_name":"Online Multi-Object Tracking"},{"task_slug":"motion-prediction","task_name":"motion prediction"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-object-tracking-on-hieve","task":"Multi-Object Tracking","dataset":"HiEve","model":"SGT","rank_in_archive_order":2,"of":4,"metrics":{"IDF1":"53.7","MOTA":"47.2"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-tracking-on-mot16","task":"Multi-Object Tracking","dataset":"MOT16","model":"SGT","rank_in_archive_order":3,"of":24,"metrics":{"IDF1":"73.5","MOTA":"76.8"},"uses_additional_data":true},{"leaderboard":"/sota/multi-object-tracking-on-mot17","task":"Multi-Object Tracking","dataset":"MOT17","model":"SGT","rank_in_archive_order":23,"of":48,"metrics":{"HOTA":"60.8","IDF1":"72.8","MOTA":"76.4"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-tracking-on-mot20-1","task":"Multi-Object Tracking","dataset":"MOT20","model":"SGT","rank_in_archive_order":19,"of":27,"metrics":{"HOTA":"57.0","IDF1":"70.6","MOTA":"72.8"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.00968","atlas_url":"https://app.syntology.ai/?focus=2205.00968","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":"2205.00968"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2205.00968\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2205.00968"},"call":"get_concepts_for_paper(arxiv_id=\"2205.00968\")"}],"by_repo":[{"repo":"hyunjs/sgt","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":"a5e274283bf495f5e47da096ed12f3885f66df6887ad98f3f69a847d3985875c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}