{"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/exploring-enhanced-contextual-information-for-1","title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","arxiv_id":"2412.11023","date":"2024-12-15","proceeding":"AAAI2025 2024 12","authors":["Ben Kang","Xin Chen","Simiao Lai","Yang Liu","Yi Liu","Dong Wang"],"abstract":"Contextual information at the video level has become increasingly crucial for visual object tracking. However, existing methods typically use only a few tokens to convey this information, which can lead to information loss and limit their ability to fully capture the context. To address this issue, we propose a new video-level visual object tracking framework called MCITrack. It leverages Mamba's hidden states to continuously record and transmit extensive contextual information throughout the video stream, resulting in more robust object tracking. The core component of MCITrack is the Contextual Information Fusion module, which consists of the mamba layer and the cross-attention layer. The mamba layer stores historical contextual information, while the cross-attention layer integrates this information into the current visual features of each backbone block. This module enhances the model's ability to capture and utilize contextual information at multiple levels through deep integration with the backbone. Experiments demonstrate that MCITrack achieves competitive performance across numerous benchmarks. For instance, it gets 76.6% AUC on LaSOT and 80.0% AO on GOT-10k, establishing a new state-of-the-art performance. Code and models are available at https://github.com/kangben258/MCITrack.","url_abs":"https://arxiv.org/abs/2412.11023v1","url_pdf":"https://arxiv.org/pdf/2412.11023v1.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":"exploring-enhanced-contextual-information-for-1","repo_url":"https://github.com/kangben258/MCITrack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object Segmentation"},{"task_slug":"video-object-tracking","task_name":"Video Object Tracking"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[{"method_slug":"ao","method_name":"AO"},{"method_slug":"mamba","method_name":"Mamba"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-15","task":"Semi-Supervised Video Object Segmentation","dataset":"VOT2020","model":"MCITrack-L384","rank_in_archive_order":2,"of":20,"metrics":{"EAO":"0.624"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-15","task":"Semi-Supervised Video Object Segmentation","dataset":"VOT2020","model":"MCITrack-B224","rank_in_archive_order":4,"of":20,"metrics":{"EAO":"0.619"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-got-10k","task":"Visual Object Tracking","dataset":"GOT-10k","model":"MCITrack-L384","rank_in_archive_order":6,"of":42,"metrics":{"Average Overlap":"80.0","Success Rate 0.5":"88.5","Success Rate 0.75":"80.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-got-10k","task":"Visual Object Tracking","dataset":"GOT-10k","model":"MCITrack-B224","rank_in_archive_order":11,"of":42,"metrics":{"Average Overlap":"77.9","Success Rate 0.5":"88.2","Success Rate 0.75":"76.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot","task":"Visual Object Tracking","dataset":"LaSOT","model":"MCITrack-L384","rank_in_archive_order":3,"of":46,"metrics":{"AUC":"76.6","Normalized Precision":"86.1","Precision":"85.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot","task":"Visual Object Tracking","dataset":"LaSOT","model":"MCITrack-B224","rank_in_archive_order":5,"of":46,"metrics":{"AUC":"75.3","Normalized Precision":"85.6","Precision":"83.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot-ext","task":"Visual Object Tracking","dataset":"LaSOT-ext","model":"MCITrack-L384","rank_in_archive_order":6,"of":18,"metrics":{"AUC":"55.7","Normalized Precision":"66.5","Precision":"62.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot-ext","task":"Visual Object Tracking","dataset":"LaSOT-ext","model":"MCITrack-B224","rank_in_archive_order":8,"of":18,"metrics":{"AUC":"54.6","Normalized Precision":"65.7","Precision":"62.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-tnl2k","task":"Visual Object Tracking","dataset":"TNL2K","model":"MCITrack-L384","rank_in_archive_order":1,"of":16,"metrics":{"AUC":"65.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-tnl2k","task":"Visual Object Tracking","dataset":"TNL2K","model":"MCITrack-B224","rank_in_archive_order":4,"of":16,"metrics":{"AUC":"62.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-trackingnet","task":"Visual Object Tracking","dataset":"TrackingNet","model":"MCITrack-L384","rank_in_archive_order":1,"of":40,"metrics":{"Accuracy":"87.9","Normalized Precision":"92.1","Precision":"89.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-trackingnet","task":"Visual Object Tracking","dataset":"TrackingNet","model":"MCITrack-B224","rank_in_archive_order":4,"of":40,"metrics":{"Accuracy":"86.3","Normalized Precision":"90.9","Precision":"86.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.11023","atlas_url":"https://app.syntology.ai/?focus=2412.11023","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":"2412.11023"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2412.11023\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2412.11023"},"call":"get_concepts_for_paper(arxiv_id=\"2412.11023\")"}],"by_repo":[{"repo":"kangben258/MCITrack","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":"8ea0e644c99d7f6f75a3be9bbf73ac3693ddceed30785df18cb38550e803377c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}