{"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/deft-detection-embeddings-for-tracking","title":"DEFT: Detection Embeddings for Tracking","arxiv_id":"2102.02267","date":"2021-02-03","proceeding":null,"authors":["Mohamed Chaabane","Peter Zhang","J. Ross Beveridge","Stephen O'Hara"],"abstract":"Most modern multiple object tracking (MOT) systems follow the tracking-by-detection paradigm, consisting of a detector followed by a method for associating detections into tracks. There is a long history in tracking of combining motion and appearance features to provide robustness to occlusions and other challenges, but typically this comes with the trade-off of a more complex and slower implementation. Recent successes on popular 2D tracking benchmarks indicate that top-scores can be achieved using a state-of-the-art detector and relatively simple associations relying on single-frame spatial offsets -- notably outperforming contemporary methods that leverage learned appearance features to help re-identify lost tracks. In this paper, we propose an efficient joint detection and tracking model named DEFT, or \"Detection Embeddings for Tracking.\" Our approach relies on an appearance-based object matching network jointly-learned with an underlying object detection network. An LSTM is also added to capture motion constraints. DEFT has comparable accuracy and speed to the top methods on 2D online tracking leaderboards while having significant advantages in robustness when applied to more challenging tracking data. DEFT raises the bar on the nuScenes monocular 3D tracking challenge, more than doubling the performance of the previous top method. Code is publicly available.","url_abs":"https://arxiv.org/abs/2102.02267v2","url_pdf":"https://arxiv.org/pdf/2102.02267v2.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":"deft-detection-embeddings-for-tracking","repo_url":"https://github.com/MedChaabane/DEFT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-multi-object-tracking","task_name":"3D Multi-Object Tracking"},{"task_slug":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-multi-object-tracking-on-nuscenes","task":"3D Multi-Object Tracking","dataset":"nuScenes","model":"DEFT","rank_in_archive_order":104,"of":115,"metrics":{"AMOTA":"0.18"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-tracking-on-mot16","task":"Multi-Object Tracking","dataset":"MOT16","model":"DEFT","rank_in_archive_order":11,"of":24,"metrics":{"MOTA":"68.03"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-tracking-on-mot17","task":"Multi-Object Tracking","dataset":"MOT17","model":"DEFT","rank_in_archive_order":39,"of":48,"metrics":{"MOTA":"66.6"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-object-tracking-on-kitti-test-online","task":"Multiple Object Tracking","dataset":"KITTI Test (Online Methods)","model":"DEFT","rank_in_archive_order":14,"of":34,"metrics":{"HOTA":"74.23 ","MOTA":"88.95"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2102.02267","atlas_url":"https://app.syntology.ai/?focus=2102.02267","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":"2102.02267"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2102.02267\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2102.02267"},"call":"get_concepts_for_paper(arxiv_id=\"2102.02267\")"}],"by_repo":[{"repo":"MedChaabane/DEFT","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1603.00831"],"harvested_for_calls":[{"arxiv_id":"1603.00831","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1603.00831"},"call":"get_harvested_code_for_paper(arxiv_id=\"1603.00831\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"5e3aef4b8d042c8921fba78f6de1d854090d6d6f06c011e21a9553784ff36e70","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}