{"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/referring-multi-object-tracking","title":"Referring Multi-Object Tracking","arxiv_id":"2303.03366","date":"2023-03-06","proceeding":"CVPR 2023 1","authors":["Dongming Wu","Wencheng Han","Tiancai Wang","Xingping Dong","Xiangyu Zhang","Jianbing Shen"],"abstract":"Existing referring understanding tasks tend to involve the detection of a single text-referred object. In this paper, we propose a new and general referring understanding task, termed referring multi-object tracking (RMOT). Its core idea is to employ a language expression as a semantic cue to guide the prediction of multi-object tracking. To the best of our knowledge, it is the first work to achieve an arbitrary number of referent object predictions in videos. To push forward RMOT, we construct one benchmark with scalable expressions based on KITTI, named Refer-KITTI. Specifically, it provides 18 videos with 818 expressions, and each expression in a video is annotated with an average of 10.7 objects. Further, we develop a transformer-based architecture TransRMOT to tackle the new task in an online manner, which achieves impressive detection performance and outperforms other counterparts. The dataset and code will be available at https://github.com/wudongming97/RMOT.","url_abs":"https://arxiv.org/abs/2303.03366v2","url_pdf":"https://arxiv.org/pdf/2303.03366v2.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":"referring-multi-object-tracking","repo_url":"https://github.com/wudongming97/rmot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"referring-multi-object-tracking","task_name":"Referring Multi-Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.03366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.03366"}},"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/wudongming97/rmot","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"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":8,"samples":[{"code_sha256_prefix":"9f1703b766ce5348","entry":"FeatureResizer","repo":"wudongming97/rmot","repo_kind":"official","path":"models/transrmot.py","file_url":"https://github.com/wudongming97/rmot/blob/HEAD/models/transrmot.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9f1703b766ce5348"}},{"code_sha256_prefix":"84a4da4b7084dfe8","entry":"Instances","repo":"wudongming97/rmot","repo_kind":"official","path":"models/transrmot.py","file_url":"https://github.com/wudongming97/rmot/blob/HEAD/models/transrmot.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"84a4da4b7084dfe8"}},{"code_sha256_prefix":"4b2a13b88ac5c502","entry":"PositionEmbeddingSine1D","repo":"wudongming97/rmot","repo_kind":"official","path":"models/transrmot.py","file_url":"https://github.com/wudongming97/rmot/blob/HEAD/models/transrmot.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4b2a13b88ac5c502"}},{"code_sha256_prefix":"84a66cc407dda6db","entry":"VisionLanguageFusionModule","repo":"wudongming97/rmot","repo_kind":"official","path":"models/transrmot.py","file_url":"https://github.com/wudongming97/rmot/blob/HEAD/models/transrmot.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"84a66cc407dda6db"}},{"code_sha256_prefix":"003345262cfce83d","entry":"nested_tensor_from_tensor_list","repo":"wudongming97/rmot","repo_kind":"official","path":"models/transrmot.py","file_url":"https://github.com/wudongming97/rmot/blob/HEAD/models/transrmot.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"003345262cfce83d"}},{"code_sha256_prefix":"b99d7716924e3983","entry":"RuntimeTrackerBase","repo":"wudongming97/rmot","repo_kind":"official","path":"models/transrmot.py","file_url":"https://github.com/wudongming97/rmot/blob/HEAD/models/transrmot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b99d7716924e3983"}},{"code_sha256_prefix":"a84ed583c3ec6cda","entry":"TrackerPostProcess","repo":"wudongming97/rmot","repo_kind":"official","path":"models/transrmot.py","file_url":"https://github.com/wudongming97/rmot/blob/HEAD/models/transrmot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a84ed583c3ec6cda"}},{"code_sha256_prefix":"54236702d7c5a22f","entry":"TransRMOT","repo":"wudongming97/rmot","repo_kind":"official","path":"models/transrmot.py","file_url":"https://github.com/wudongming97/rmot/blob/HEAD/models/transrmot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"54236702d7c5a22f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}