{"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/the-devil-is-in-temporal-token-high-quality","title":"The Devil is in Temporal Token: High Quality Video Reasoning Segmentation","arxiv_id":"2501.08549","date":"2025-01-15","proceeding":"CVPR 2025 1","authors":["Sitong Gong","Yunzhi Zhuge","Lu Zhang","Zongxin Yang","Pingping Zhang","Huchuan Lu"],"abstract":"Existing methods for Video Reasoning Segmentation rely heavily on a single special token to represent the object in the keyframe or the entire video, inadequately capturing spatial complexity and inter-frame motion. To overcome these challenges, we propose VRS-HQ, an end-to-end video reasoning segmentation approach that leverages Multimodal Large Language Models (MLLMs) to inject rich spatiotemporal features into hierarchical tokens.Our key innovations include a Temporal Dynamic Aggregation (TDA) and a Token-driven Keyframe Selection (TKS). Specifically, we design frame-level <SEG> and temporal-level <TAK> tokens that utilize MLLM's autoregressive learning to effectively capture both local and global information. Subsequently, we apply a similarity-based weighted fusion and frame selection strategy, then utilize SAM2 to perform keyframe segmentation and propagation. To enhance keyframe localization accuracy, the TKS filters keyframes based on SAM2's occlusion scores during inference. VRS-HQ achieves state-of-the-art performance on ReVOS, surpassing VISA by 5.9%/12.5%/9.1% in J&F scores across the three subsets. These results highlight the strong temporal reasoning and segmentation capabilities of our method. Code and model weights will be released at VRS-HQ.","url_abs":"https://arxiv.org/abs/2501.08549v1","url_pdf":"https://arxiv.org/pdf/2501.08549v1.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":"the-devil-is-in-temporal-token-high-quality","repo_url":"https://github.com/sitonggong/vrs-hq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"reasoning-segmentation","task_name":"Reasoning Segmentation"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"referring-video-object-segmentation","task_name":"Referring Video Object Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/referring-expression-segmentation-on-refer-1","task":"Referring Expression Segmentation","dataset":"Refer-YouTube-VOS (2021 public validation)","model":"VRS-HQ (Chat-UniVi-13B)","rank_in_archive_order":2,"of":33,"metrics":{"F":"73.1","J":"69","J&F":"71"},"uses_additional_data":false},{"leaderboard":"/sota/referring-video-object-segmentation-on-mevis","task":"Referring Video Object Segmentation","dataset":"MeViS","model":"VRS-HQ (Chat-UniVi-13B)","rank_in_archive_order":4,"of":16,"metrics":{"F":"53.7","J":"48","J&F":"50.9"},"uses_additional_data":false},{"leaderboard":"/sota/referring-video-object-segmentation-on-revos","task":"Referring Video Object Segmentation","dataset":"ReVOS","model":"VRS-HQ (Chat-UniVi-13B)","rank_in_archive_order":1,"of":9,"metrics":{"F":"62.5","J":"57.6","J&F":"60","R":"18.9"},"uses_additional_data":false},{"leaderboard":"/sota/referring-video-object-segmentation-on-revos","task":"Referring Video Object Segmentation","dataset":"ReVOS","model":"VRS-HQ (Chat-UniVi-7B)","rank_in_archive_order":2,"of":9,"metrics":{"F":"61.6","J":"56.6","J&F":"59.1","R":"19.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2501.08549","atlas_url":"https://app.syntology.ai/?focus=2501.08549","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":"2501.08549"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2501.08549\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2501.08549"},"call":"get_concepts_for_paper(arxiv_id=\"2501.08549\")"}],"by_repo":[{"repo":"sitonggong/vrs-hq","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":"6ac9dd098aee9fc72db337a621b6d1df5723643a2a926bdeff3caa15c265a57b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}