{"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/citetracker-correlating-image-and-text-for","title":"CiteTracker: Correlating Image and Text for Visual Tracking","arxiv_id":"2308.11322","date":"2023-08-22","proceeding":"ICCV 2023 1","authors":["Xin Li","Yuqing Huang","Zhenyu He","YaoWei Wang","Huchuan Lu","Ming-Hsuan Yang"],"abstract":"Existing visual tracking methods typically take an image patch as the reference of the target to perform tracking. However, a single image patch cannot provide a complete and precise concept of the target object as images are limited in their ability to abstract and can be ambiguous, which makes it difficult to track targets with drastic variations. In this paper, we propose the CiteTracker to enhance target modeling and inference in visual tracking by connecting images and text. Specifically, we develop a text generation module to convert the target image patch into a descriptive text containing its class and attribute information, providing a comprehensive reference point for the target. In addition, a dynamic description module is designed to adapt to target variations for more effective target representation. We then associate the target description and the search image using an attention-based correlation module to generate the correlated features for target state reference. Extensive experiments on five diverse datasets are conducted to evaluate the proposed algorithm and the favorable performance against the state-of-the-art methods demonstrates the effectiveness of the proposed tracking method.","url_abs":"https://arxiv.org/abs/2308.11322v1","url_pdf":"https://arxiv.org/pdf/2308.11322v1.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":"citetracker-correlating-image-and-text-for","repo_url":"https://github.com/norahgreen/citetracker","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.11322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11322"}},"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":"deterministic:regex_extraction","url":"https://github.com/NorahGreen/CiteTracker","reach":{"status":"ok"}}],"summary":{"ran":10,"ran_honours":1},"by_repo_kind":{"official":{"samples":11,"ran":11,"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":11,"samples":[{"code_sha256_prefix":"305742bafecf04f8","entry":"adjust_keep_rate","repo":"NorahGreen/CiteTracker","repo_kind":"official","path":"lib/utils/ce_utils.py","file_url":"https://github.com/NorahGreen/CiteTracker/blob/HEAD/lib/utils/ce_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"305742bafecf04f8"}},{"code_sha256_prefix":"e0a06ded5d4f6c3c","entry":"box_cxcywh_to_xyxy","repo":"NorahGreen/CiteTracker","repo_kind":"official","path":"lib/utils/box_ops.py","file_url":"https://github.com/NorahGreen/CiteTracker/blob/HEAD/lib/utils/box_ops.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e0a06ded5d4f6c3c"}},{"code_sha256_prefix":"40c655a7fe309e49","entry":"box_xywh_to_xyxy","repo":"NorahGreen/CiteTracker","repo_kind":"official","path":"lib/utils/box_ops.py","file_url":"https://github.com/NorahGreen/CiteTracker/blob/HEAD/lib/utils/box_ops.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"40c655a7fe309e49"}},{"code_sha256_prefix":"b48a27604b9574e0","entry":"box_xyxy_to_xywh","repo":"NorahGreen/CiteTracker","repo_kind":"official","path":"lib/utils/box_ops.py","file_url":"https://github.com/NorahGreen/CiteTracker/blob/HEAD/lib/utils/box_ops.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b48a27604b9574e0"}},{"code_sha256_prefix":"f0de0cc660ea9823","entry":"compute_grids","repo":"NorahGreen/CiteTracker","repo_kind":"official","path":"lib/utils/heapmap_utils.py","file_url":"https://github.com/NorahGreen/CiteTracker/blob/HEAD/lib/utils/heapmap_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f0de0cc660ea9823"}},{"code_sha256_prefix":"d8da96a9ed23308f","entry":"generate_bbox_mask","repo":"NorahGreen/CiteTracker","repo_kind":"official","path":"lib/utils/ce_utils.py","file_url":"https://github.com/NorahGreen/CiteTracker/blob/HEAD/lib/utils/ce_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d8da96a9ed23308f"}},{"code_sha256_prefix":"02f602286c531143","entry":"generate_heatmap","repo":"NorahGreen/CiteTracker","repo_kind":"official","path":"lib/utils/heapmap_utils.py","file_url":"https://github.com/NorahGreen/CiteTracker/blob/HEAD/lib/utils/heapmap_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"02f602286c531143"}},{"code_sha256_prefix":"90e571943800f79c","entry":"generate_mask_cond","repo":"NorahGreen/CiteTracker","repo_kind":"official","path":"lib/utils/ce_utils.py","file_url":"https://github.com/NorahGreen/CiteTracker/blob/HEAD/lib/utils/ce_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"90e571943800f79c"}},{"code_sha256_prefix":"8ed1a71ee932713a","entry":"get_center3x3","repo":"NorahGreen/CiteTracker","repo_kind":"official","path":"lib/utils/heapmap_utils.py","file_url":"https://github.com/NorahGreen/CiteTracker/blob/HEAD/lib/utils/heapmap_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8ed1a71ee932713a"}},{"code_sha256_prefix":"2e6c35cccbde1c71","entry":"get_qkv","repo":"NorahGreen/CiteTracker","repo_kind":"official","path":"lib/utils/merge.py","file_url":"https://github.com/NorahGreen/CiteTracker/blob/HEAD/lib/utils/merge.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e6c35cccbde1c71"}},{"code_sha256_prefix":"c66db0b9eb9bb36a","entry":"merge_template_search","repo":"NorahGreen/CiteTracker","repo_kind":"official","path":"lib/utils/merge.py","file_url":"https://github.com/NorahGreen/CiteTracker/blob/HEAD/lib/utils/merge.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c66db0b9eb9bb36a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}