{"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/diffusiontrack-diffusion-model-for-multi","title":"DiffusionTrack: Diffusion Model For Multi-Object Tracking","arxiv_id":"2308.09905","date":"2023-08-19","proceeding":null,"authors":["Run Luo","Zikai Song","Lintao Ma","JinLin Wei","Wei Yang","Min Yang"],"abstract":"Multi-object tracking (MOT) is a challenging vision task that aims to detect individual objects within a single frame and associate them across multiple frames. Recent MOT approaches can be categorized into two-stage tracking-by-detection (TBD) methods and one-stage joint detection and tracking (JDT) methods. Despite the success of these approaches, they also suffer from common problems, such as harmful global or local inconsistency, poor trade-off between robustness and model complexity, and lack of flexibility in different scenes within the same video. In this paper we propose a simple but robust framework that formulates object detection and association jointly as a consistent denoising diffusion process from paired noise boxes to paired ground-truth boxes. This novel progressive denoising diffusion strategy substantially augments the tracker's effectiveness, enabling it to discriminate between various objects. During the training stage, paired object boxes diffuse from paired ground-truth boxes to random distribution, and the model learns detection and tracking simultaneously by reversing this noising process. In inference, the model refines a set of paired randomly generated boxes to the detection and tracking results in a flexible one-step or multi-step denoising diffusion process. Extensive experiments on three widely used MOT benchmarks, including MOT17, MOT20, and Dancetrack, demonstrate that our approach achieves competitive performance compared to the current state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2308.09905v2","url_pdf":"https://arxiv.org/pdf/2308.09905v2.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":"diffusiontrack-diffusion-model-for-multi","repo_url":"https://github.com/rainbowluocs/diffusiontrack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"multi-object-tracking","task_name":"Multi-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":"model","task_name":"model"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.09905","atlas_url":"https://app.syntology.ai/?focus=2308.09905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09905"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/rainbowluocs/diffusiontrack","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":1,"ran_violates":3,"ran":1,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":"4d75570b4e91d0b4","entry":"FeedForward","repo":"rainbowluocs/diffusiontrack","repo_kind":"official","path":"diffusion/models/diffusion_models.py","file_url":"https://github.com/rainbowluocs/diffusiontrack/blob/HEAD/diffusion/models/diffusion_models.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4d75570b4e91d0b4"}},{"code_sha256_prefix":"d1ef6b8cb9a28a53","entry":"default","repo":"rainbowluocs/diffusiontrack","repo_kind":"official","path":"diffusion/models/diffusion_head.py","file_url":"https://github.com/rainbowluocs/diffusiontrack/blob/HEAD/diffusion/models/diffusion_head.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d1ef6b8cb9a28a53"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"rainbowluocs/diffusiontrack","repo_kind":"official","path":"diffusion/models/diffusion_models.py","file_url":"https://github.com/rainbowluocs/diffusiontrack/blob/HEAD/diffusion/models/diffusion_models.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"608e364a9d2376a3","entry":"exists","repo":"rainbowluocs/diffusiontrack","repo_kind":"official","path":"diffusion/models/diffusion_head.py","file_url":"https://github.com/rainbowluocs/diffusiontrack/blob/HEAD/diffusion/models/diffusion_head.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"608e364a9d2376a3"}},{"code_sha256_prefix":"774f31ba06110943","entry":"sigmoid_focal_loss","repo":"rainbowluocs/diffusiontrack","repo_kind":"official","path":"yolox/models/losses.py","file_url":"https://github.com/rainbowluocs/diffusiontrack/blob/HEAD/yolox/models/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"774f31ba06110943"}},{"code_sha256_prefix":"f9fd6241d935f07b","entry":"window_partition","repo":"rainbowluocs/diffusiontrack","repo_kind":"official","path":"diffusion/models/diffusion_models.py","file_url":"https://github.com/rainbowluocs/diffusiontrack/blob/HEAD/diffusion/models/diffusion_models.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f9fd6241d935f07b"}},{"code_sha256_prefix":"13c5bb713056a640","entry":"extract","repo":"rainbowluocs/diffusiontrack","repo_kind":"official","path":"diffusion/models/diffusion_head.py","file_url":"https://github.com/rainbowluocs/diffusiontrack/blob/HEAD/diffusion/models/diffusion_head.py","link_basis":"harvester_set","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":"13c5bb713056a640"}},{"code_sha256_prefix":"6e3d5f4c3ce305d7","entry":"get_activation","repo":"rainbowluocs/diffusiontrack","repo_kind":"official","path":"yolox/models/network_blocks.py","file_url":"https://github.com/rainbowluocs/diffusiontrack/blob/HEAD/yolox/models/network_blocks.py","link_basis":"harvester_set","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":"6e3d5f4c3ce305d7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}