{"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":"/task/referring-video-object-segmentation","name":"Referring Video Object Segmentation","slug":"referring-video-object-segmentation","description_markdown":"Referring video object segmentation aims at segmenting an object in video with language expressions. Unlike the previous video object segmentation, the task exploits a different type of supervision, language expressions, to identify and segment an object referred by the given language expressions in a video.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":74,"papers_with_code":50,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/referring-video-object-segmentation-on-refer","slug":"referring-video-object-segmentation-on-refer","dataset":"Refer-YouTube-VOS","dataset_url":"/dataset/refer-youtube-vos","rows_in_archive":18,"metrics":["J&F","J","F"],"first_row_in_archive_order":{"model":"FindTrack","paper_title":"Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation","paper_url":"/paper/find-first-track-next-decoupling","paper_date":"2025-03-05","arxiv_id":"2503.03492","code_links":[{"title":"suhwan-cho/FindTrack","url":"https://github.com/suhwan-cho/FindTrack"}],"syntology":null}},{"leaderboard":"/sota/referring-video-object-segmentation-on-mevis","slug":"referring-video-object-segmentation-on-mevis","dataset":"MeViS","dataset_url":"/dataset/mevis","rows_in_archive":16,"metrics":["J&F","J","F"],"first_row_in_archive_order":{"model":"MPG-SAM 2","paper_title":"MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation","paper_url":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and","paper_date":"2025-01-23","arxiv_id":"2501.13667","code_links":[{"title":"rongfu-dsb/MPG-SAM2","url":"https://github.com/rongfu-dsb/MPG-SAM2"}],"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and#ran","syntology_url":"https://syntology.ai/paper/2501.13667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13667"}},"official":{"repos":["rongfu-dsb/MPG-SAM2"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/referring-video-object-segmentation-on-ref","slug":"referring-video-object-segmentation-on-ref","dataset":"Ref-DAVIS17","dataset_url":null,"rows_in_archive":11,"metrics":["J&F","J","F"],"first_row_in_archive_order":{"model":"FindTrack","paper_title":"Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation","paper_url":"/paper/find-first-track-next-decoupling","paper_date":"2025-03-05","arxiv_id":"2503.03492","code_links":[{"title":"suhwan-cho/FindTrack","url":"https://github.com/suhwan-cho/FindTrack"}],"syntology":null}},{"leaderboard":"/sota/referring-video-object-segmentation-on-revos","slug":"referring-video-object-segmentation-on-revos","dataset":"ReVOS","dataset_url":"/dataset/revos","rows_in_archive":9,"metrics":["J&F","J","F","R"],"first_row_in_archive_order":{"model":"VRS-HQ (Chat-UniVi-13B)","paper_title":"The Devil is in Temporal Token: High Quality Video Reasoning Segmentation","paper_url":"/paper/the-devil-is-in-temporal-token-high-quality","paper_date":"2025-01-15","arxiv_id":"2501.08549","code_links":[{"title":"sitonggong/vrs-hq","url":"https://github.com/sitonggong/vrs-hq"}],"syntology":null}},{"leaderboard":"/sota/referring-video-object-segmentation-on-long","slug":"referring-video-object-segmentation-on-long","dataset":"Long-RVOS","dataset_url":"/dataset/long-rvos","rows_in_archive":7,"metrics":["J&F","tIoU","vIoU"],"first_row_in_archive_order":{"model":"ReferMo","paper_title":"Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation","paper_url":"/paper/long-rvos-a-comprehensive-benchmark-for-long","paper_date":"2025-05-19","arxiv_id":"2505.12702","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/refer-youtube-vos","name":"Refer-YouTube-VOS","full_name":"","num_papers_in_archive":52},{"url":"/dataset/mevis","name":"MeViS","full_name":"Motion expressions Video Segmentation","num_papers_in_archive":46},{"url":"/dataset/revos","name":"ReVOS","full_name":"","num_papers_in_archive":18},{"url":"/dataset/long-rvos","name":"Long-RVOS","full_name":"","num_papers_in_archive":7}],"subtasks":[],"parent_tasks":[{"url":"/task/video-object-segmentation","name":"Video Object Segmentation"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":74,"of":74,"of_with_code":50,"tagged_in_all":74,"counts":{"archive_papers_tagged":74,"with_a_code_link":50,"where_syntology_ran_a_sample":22,"not_listed_spam_title":0,"listed":74,"listed_where_code_ran":22,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":19,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":19,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/visa-reasoning-video-object-segmentation-via","slug":"visa-reasoning-video-object-segmentation-via","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","date":"2024-07-16","arxiv_id":"2407.11325","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visa-reasoning-video-object-segmentation-via#ran","syntology_url":"https://syntology.ai/paper/2407.11325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11325"}},"official":{"repos":["cilinyan/VISA","cilinyan/revos-api"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/uniref-segment-every-reference-object-in","slug":"uniref-segment-every-reference-object-in","title":"UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces","date":"2023-12-25","arxiv_id":"2312.15715","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":2,"n_instrument":7,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uniref-segment-every-reference-object-in#ran","syntology_url":"https://syntology.ai/paper/2312.15715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15715"}},"official":{"repos":["foundationvision/uniref"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lisa-reasoning-segmentation-via-large","slug":"lisa-reasoning-segmentation-via-large","title":"LISA: Reasoning Segmentation via Large Language Model","date":"2023-08-01","arxiv_id":"2308.00692","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-referring-video-object","slug":"end-to-end-referring-video-object","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","date":"2021-11-29","arxiv_id":"2111.14821","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/end-to-end-referring-video-object#ran","syntology_url":"https://syntology.ai/paper/2111.14821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14821"}},"official":{"repos":["mttr2021/MTTR"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/videomolmo-spatio-temporal-grounding-meets","slug":"videomolmo-spatio-temporal-grounding-meets","title":"VideoMolmo: Spatio-Temporal Grounding Meets Pointing","date":"2025-06-05","arxiv_id":"2506.05336","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-referring-video-single-and-multi","slug":"few-shot-referring-video-single-and-multi","title":"Few-Shot Referring Video Single- and Multi-Object Segmentation via Cross-Modal Affinity with Instance Sequence Matching","date":"2025-04-18","arxiv_id":"2504.13710","repositories_listed":1,"syntology":null},{"url":"/paper/glus-global-local-reasoning-unified-into-a","slug":"glus-global-local-reasoning-unified-into-a","title":"GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation","date":"2025-04-10","arxiv_id":"2504.07962","repositories_listed":1,"syntology":{"n":12,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/glus-global-local-reasoning-unified-into-a#ran","syntology_url":"https://syntology.ai/paper/2504.07962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07962"}},"official":null}},{"url":"/paper/the-1st-solution-for-4th-pvuw-mevis-challenge","slug":"the-1st-solution-for-4th-pvuw-mevis-challenge","title":"The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video Segmentation","date":"2025-04-07","arxiv_id":"2504.05178","repositories_listed":1,"syntology":null},{"url":"/paper/4th-pvuw-mevis-3rd-place-report-sa2va","slug":"4th-pvuw-mevis-3rd-place-report-sa2va","title":"4th PVUW MeViS 3rd Place Report: Sa2VA","date":"2025-04-01","arxiv_id":"2504.00476","repositories_listed":1,"syntology":null},{"url":"/paper/referdino-plus-2nd-solution-for-4th-pvuw","slug":"referdino-plus-2nd-solution-for-4th-pvuw","title":"ReferDINO-Plus: 2nd Solution for 4th PVUW MeViS Challenge at CVPR 2025","date":"2025-03-30","arxiv_id":"2503.23509","repositories_listed":1,"syntology":null},{"url":"/paper/find-first-track-next-decoupling","slug":"find-first-track-next-decoupling","title":"Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation","date":"2025-03-05","arxiv_id":"2503.03492","repositories_listed":1,"syntology":null},{"url":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and","slug":"mpg-sam-2-adapting-sam-2-with-mask-priors-and","title":"MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation","date":"2025-01-23","arxiv_id":"2501.13667","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/mpg-sam-2-adapting-sam-2-with-mask-priors-and#ran","syntology_url":"https://syntology.ai/paper/2501.13667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13667"}},"official":{"repos":["rongfu-dsb/MPG-SAM2"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/internvideo2-5-empowering-video-mllms-with","slug":"internvideo2-5-empowering-video-mllms-with","title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","date":"2025-01-21","arxiv_id":"2501.12386","repositories_listed":1,"syntology":null},{"url":"/paper/the-devil-is-in-temporal-token-high-quality","slug":"the-devil-is-in-temporal-token-high-quality","title":"The Devil is in Temporal Token: High Quality Video Reasoning Segmentation","date":"2025-01-15","arxiv_id":"2501.08549","repositories_listed":1,"syntology":null},{"url":"/paper/multi-context-temporal-consistent-modeling","slug":"multi-context-temporal-consistent-modeling","title":"Multi-Context Temporal Consistent Modeling for Referring Video Object Segmentation","date":"2025-01-09","arxiv_id":"2501.04939","repositories_listed":1,"syntology":null},{"url":"/paper/sa2va-marrying-sam2-with-llava-for-dense","slug":"sa2va-marrying-sam2-with-llava-for-dense","title":"Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos","date":"2025-01-07","arxiv_id":"2501.04001","repositories_listed":1,"syntology":null},{"url":"/paper/dtos-dynamic-time-object-sensing-with-large","slug":"dtos-dynamic-time-object-sensing-with-large","title":"DTOS: Dynamic Time Object Sensing with Large Multimodal Model","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/referring-video-object-segmentation-via","slug":"referring-video-object-segmentation-via","title":"Referring Video Object Segmentation via Language-aligned Track Selection","date":"2024-12-02","arxiv_id":"2412.01136","repositories_listed":1,"syntology":null},{"url":"/paper/hyperseg-towards-universal-visual","slug":"hyperseg-towards-universal-visual","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","date":"2024-11-26","arxiv_id":"2411.17606","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":4,"n_honours":4,"n_violates":2,"n_no_contract":2,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hyperseg-towards-universal-visual#ran","syntology_url":"https://syntology.ai/paper/2411.17606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17606"}},"official":{"repos":["congvvc/HyperSeg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/samwise-infusing-wisdom-in-sam2-for-text","slug":"samwise-infusing-wisdom-in-sam2-for-text","title":"SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation","date":"2024-11-26","arxiv_id":"2411.17646","repositories_listed":1,"syntology":null},{"url":"/paper/one-token-to-seg-them-all-language-instructed","slug":"one-token-to-seg-them-all-language-instructed","title":"One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos","date":"2024-09-29","arxiv_id":"2409.19603","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":8,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/one-token-to-seg-them-all-language-instructed#ran","syntology_url":"https://syntology.ai/paper/2409.19603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19603"}},"official":{"repos":["showlab/videolisa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/actionvos-actions-as-prompts-for-video-object","slug":"actionvos-actions-as-prompts-for-video-object","title":"ActionVOS: Actions as Prompts for Video Object Segmentation","date":"2024-07-10","arxiv_id":"2407.07402","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":1,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":15,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/actionvos-actions-as-prompts-for-video-object#ran","syntology_url":"https://syntology.ai/paper/2407.07402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07402"}},"official":{"repos":["ut-vision/actionvos"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/1st-place-solution-for-mevis-track-in-cvpr","slug":"1st-place-solution-for-mevis-track-in-cvpr","title":"1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation","date":"2024-06-11","arxiv_id":"2406.07043","repositories_listed":1,"syntology":null},{"url":"/paper/improving-referring-image-segmentation-using","slug":"improving-referring-image-segmentation-using","title":"Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding","date":"2024-04-12","arxiv_id":"2404.08590","repositories_listed":1,"syntology":null},{"url":"/paper/decoupling-static-and-hierarchical-motion","slug":"decoupling-static-and-hierarchical-motion","title":"Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation","date":"2024-04-04","arxiv_id":"2404.03645","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/decoupling-static-and-hierarchical-motion#ran","syntology_url":"https://syntology.ai/paper/2404.03645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03645"}},"official":{"repos":["heshuting555/dshmp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-temporally-consistent-referring-video","slug":"towards-temporally-consistent-referring-video","title":"Temporally Consistent Referring Video Object Segmentation with Hybrid Memory","date":"2024-03-28","arxiv_id":"2403.19407","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":1,"n_honours":1,"n_violates":3,"n_no_contract":0,"n_pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 3 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-temporally-consistent-referring-video#ran","syntology_url":"https://syntology.ai/paper/2403.19407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19407"}},"official":{"repos":["bo-miao/HTR"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-pre-trained-text-to-video-diffusion","slug":"exploring-pre-trained-text-to-video-diffusion","title":"Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation","date":"2024-03-18","arxiv_id":"2403.12042","repositories_listed":1,"syntology":{"n":20,"n_ran":16,"n_constructed":5,"n_ran_checked":8,"n_instrument":8,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":20,"phrase":"16 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/exploring-pre-trained-text-to-video-diffusion#ran","syntology_url":"https://syntology.ai/paper/2403.12042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12042"}},"official":{"repos":["buxiangzhiren/vd-it"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":5,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/univs-unified-and-universal-video","slug":"univs-unified-and-universal-video","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","date":"2024-02-28","arxiv_id":"2402.18115","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/univs-unified-and-universal-video#ran","syntology_url":"https://syntology.ai/paper/2402.18115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18115"}},"official":{"repos":["minghanli/univs"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/1st-place-solution-for-5th-lsvos-challenge","slug":"1st-place-solution-for-5th-lsvos-challenge","title":"1st Place Solution for 5th LSVOS Challenge: Referring Video Object Segmentation","date":"2024-01-01","arxiv_id":"2401.00663","repositories_listed":1,"syntology":null},{"url":"/paper/tracking-with-human-intent-reasoning","slug":"tracking-with-human-intent-reasoning","title":"Tracking with Human-Intent Reasoning","date":"2023-12-29","arxiv_id":"2312.17448","repositories_listed":1,"syntology":null},{"url":"/paper/general-object-foundation-model-for-images","slug":"general-object-foundation-model-for-images","title":"General Object Foundation Model for Images and Videos at Scale","date":"2023-12-14","arxiv_id":"2312.09158","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/general-object-foundation-model-for-images#ran","syntology_url":"https://syntology.ai/paper/2312.09158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09158"}},"official":{"repos":["FoundationVision/GLEE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tracking-anything-with-decoupled-video","slug":"tracking-anything-with-decoupled-video","title":"Tracking Anything with Decoupled Video Segmentation","date":"2023-09-07","arxiv_id":"2309.03903","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tracking-anything-with-decoupled-video#ran","syntology_url":"https://syntology.ai/paper/2309.03903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03903"}},"official":{"repos":["hkchengrex/Tracking-Anything-with-DEVA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-cross-modal-affinity-for-referring","slug":"learning-cross-modal-affinity-for-referring","title":"Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samples","date":"2023-09-05","arxiv_id":"2309.02041","repositories_listed":1,"syntology":null},{"url":"/paper/mevis-a-large-scale-benchmark-for-video","slug":"mevis-a-large-scale-benchmark-for-video","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","date":"2023-08-16","arxiv_id":"2308.08544","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mevis-a-large-scale-benchmark-for-video#ran","syntology_url":"https://syntology.ai/paper/2308.08544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08544"}},"official":{"repos":["henghuiding/MeViS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/spectrum-guided-multi-granularity-referring","slug":"spectrum-guided-multi-granularity-referring","title":"Spectrum-guided Multi-granularity Referring Video Object Segmentation","date":"2023-07-25","arxiv_id":"2307.13537","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/spectrum-guided-multi-granularity-referring#ran","syntology_url":"https://syntology.ai/paper/2307.13537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.13537"}},"official":{"repos":["bo-miao/sgmg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/onlinerefer-a-simple-online-baseline-for","slug":"onlinerefer-a-simple-online-baseline-for","title":"OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation","date":"2023-07-18","arxiv_id":"2307.09356","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/onlinerefer-a-simple-online-baseline-for#ran","syntology_url":"https://syntology.ai/paper/2307.09356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09356"}},"official":{"repos":["wudongming97/onlinerefer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/refsam-efficiently-adapting-segmenting","slug":"refsam-efficiently-adapting-segmenting","title":"RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation","date":"2023-07-03","arxiv_id":"2307.00997","repositories_listed":1,"syntology":null},{"url":"/paper/losh-long-short-text-joint-prediction-network","slug":"losh-long-short-text-joint-prediction-network","title":"LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation","date":"2023-06-14","arxiv_id":"2306.08736","repositories_listed":1,"syntology":null},{"url":"/paper/soc-semantic-assisted-object-cluster-for","slug":"soc-semantic-assisted-object-cluster-for","title":"SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation","date":"2023-05-26","arxiv_id":"2305.17011","repositories_listed":1,"syntology":null},{"url":"/paper/referred-by-multi-modality-a-unified-temporal","slug":"referred-by-multi-modality-a-unified-temporal","title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","date":"2023-05-25","arxiv_id":"2305.16318","repositories_listed":1,"syntology":null},{"url":"/paper/universal-instance-perception-as-object","slug":"universal-instance-perception-as-object","title":"Universal Instance Perception as Object Discovery and Retrieval","date":"2023-03-12","arxiv_id":"2303.06674","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/universal-instance-perception-as-object#ran","syntology_url":"https://syntology.ai/paper/2303.06674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06674"}},"official":{"repos":["MasterBin-IIAU/UNINEXT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/1st-place-solution-for-youtubevos-challenge-1","slug":"1st-place-solution-for-youtubevos-challenge-1","title":"1st Place Solution for YouTubeVOS Challenge 2022: Referring Video Object Segmentation","date":"2022-12-27","arxiv_id":"2212.14679","repositories_listed":1,"syntology":null},{"url":"/paper/vlt-vision-language-transformer-and-query","slug":"vlt-vision-language-transformer-and-query","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","date":"2022-10-28","arxiv_id":"2210.15871","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vlt-vision-language-transformer-and-query#ran","syntology_url":"https://syntology.ai/paper/2210.15871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15871"}},"official":{"repos":["henghuiding/Vision-Language-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-attention-network-for-compressed-video","slug":"multi-attention-network-for-compressed-video","title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","date":"2022-07-26","arxiv_id":"2207.12622","repositories_listed":1,"syntology":null},{"url":"/paper/r-2vos-robust-referring-video-object","slug":"r-2vos-robust-referring-video-object","title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","date":"2022-07-04","arxiv_id":"2207.01203","repositories_listed":1,"syntology":null},{"url":"/paper/language-bridged-spatial-temporal-interaction-1","slug":"language-bridged-spatial-temporal-interaction-1","title":"Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation","date":"2022-06-08","arxiv_id":"2206.03789","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":3,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/language-bridged-spatial-temporal-interaction-1#ran","syntology_url":"https://syntology.ai/paper/2206.03789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03789"}},"official":{"repos":["dzh19990407/lbdt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/local-global-context-aware-transformer-for","slug":"local-global-context-aware-transformer-for","title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","date":"2022-03-18","arxiv_id":"2203.09773","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/local-global-context-aware-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2203.09773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09773"}},"official":{"repos":["leonnnop/locater"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/language-as-queries-for-referring-video","slug":"language-as-queries-for-referring-video","title":"Language as Queries for Referring Video Object Segmentation","date":"2022-01-03","arxiv_id":"2201.00487","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/language-as-queries-for-referring-video#ran","syntology_url":"https://syntology.ai/paper/2201.00487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00487"}},"official":{"repos":["wjn922/referformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/urvos-unified-referring-video-object","slug":"urvos-unified-referring-video-object","title":"URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark","date":"2020-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-self-attention-network-for","slug":"cross-modal-self-attention-network-for","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","date":"2019-04-09","arxiv_id":"1904.04745","repositories_listed":1,"syntology":null},{"url":null,"slug":"interrvos-interaction-aware-referring-video","title":"InterRVOS: Interaction-aware Referring Video Object Segmentation","date":"2025-06-03","arxiv_id":"2506.02356","repositories_listed":0,"syntology":null},{"url":"/paper/long-rvos-a-comprehensive-benchmark-for-long","slug":"long-rvos-a-comprehensive-benchmark-for-long","title":"Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation","date":"2025-05-19","arxiv_id":"2505.12702","repositories_listed":0,"syntology":null},{"url":"/paper/referdino-referring-video-object-segmentation","slug":"referdino-referring-video-object-segmentation","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","date":"2025-01-24","arxiv_id":"2501.14607","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupled-motion-expression-video","title":"Decoupled Motion Expression Video Segmentation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-and-sequential-alignment-for","title":"Semantic and Sequential Alignment for Referring Video Object Segmentation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lsvos-challenge-report-large-scale-complex","title":"LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation","date":"2024-09-09","arxiv_id":"2409.05847","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-2nd-solution-for-lsvos-challenge-rvos","title":"The 2nd Solution for LSVOS Challenge RVOS Track: Spatial-temporal Refinement for Consistent Semantic Segmentation","date":"2024-08-22","arxiv_id":"2408.12447","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-instance-centric-transformer-for-the-rvos","title":"The Instance-centric Transformer for the RVOS Track of LSVOS Challenge: 3rd Place Solution","date":"2024-08-20","arxiv_id":"2408.10541","repositories_listed":0,"syntology":null},{"url":null,"slug":"uninext-cutie-the-1st-solution-for-lsvos","title":"UNINEXT-Cutie: The 1st Solution for LSVOS Challenge RVOS Track","date":"2024-08-19","arxiv_id":"2408.10129","repositories_listed":0,"syntology":null},{"url":null,"slug":"2nd-place-solution-for-mevis-track-in-cvpr","title":"2nd Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation","date":"2024-06-20","arxiv_id":"2406.13939","repositories_listed":0,"syntology":null},{"url":"/paper/groprompt-efficient-grounded-prompting-and","slug":"groprompt-efficient-grounded-prompting-and","title":"GroPrompt: Efficient Grounded Prompting and Adaptation for Referring Video Object Segmentation","date":"2024-06-18","arxiv_id":"2406.12834","repositories_listed":0,"syntology":null},{"url":null,"slug":"3rd-place-solution-for-mevis-track-in-cvpr","title":"3rd Place Solution for MeViS Track in CVPR 2024 PVUW workshop: Motion Expression guided Video Segmentation","date":"2024-06-07","arxiv_id":"2406.04842","repositories_listed":0,"syntology":null},{"url":"/paper/driving-referring-video-object-segmentation","slug":"driving-referring-video-object-segmentation","title":"Harnessing Vision-Language Pretrained Models with Temporal-Aware Adaptation for Referring Video Object Segmentation","date":"2024-05-17","arxiv_id":"2405.10610","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-transformer-equipped-architecture-for","title":"Fully Transformer-Equipped Architecture for End-to-End Referring Video Object Segmentation","date":"2023-09-21","arxiv_id":"2309.11933","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-collection-and-distribution-for","title":"Temporal Collection and Distribution for Referring Video Object Segmentation","date":"2023-09-07","arxiv_id":"2309.03473","repositories_listed":0,"syntology":null},{"url":"/paper/epcformer-expression-prompt-collaboration","slug":"epcformer-expression-prompt-collaboration","title":"Expression Prompt Collaboration Transformer for Universal Referring Video Object Segmentation","date":"2023-08-08","arxiv_id":"2308.04162","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-referring-video-object-segmentation","title":"Learning Referring Video Object Segmentation from Weak Annotation","date":"2023-08-04","arxiv_id":"2308.02162","repositories_listed":0,"syntology":null},{"url":null,"slug":"referring-video-object-segmentation-with","title":"Bidirectional Correlation-Driven Inter-Frame Interaction Transformer for Referring Video Object Segmentation","date":"2023-07-02","arxiv_id":"2307.00536","repositories_listed":0,"syntology":null},{"url":"/paper/html-hybrid-temporal-scale-multimodal","slug":"html-hybrid-temporal-scale-multimodal","title":"HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-referring-video-object-segmentation","title":"Robust Referring Video Object Segmentation with Cyclic Structural Consensus","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/segment-every-reference-object-in-spatial-and","slug":"segment-every-reference-object-in-spatial-and","title":"Segment Every Reference Object in Spatial and Temporal Spaces","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-second-place-solution-for-the-4th-large","title":"The Second Place Solution for The 4th Large-scale Video Object Segmentation Challenge--Track 3: Referring Video Object Segmentation","date":"2022-06-24","arxiv_id":"2206.12035","repositories_listed":0,"syntology":null},{"url":"/paper/multi-level-representation-learning-with","slug":"multi-level-representation-learning-with","title":"Multi-Level Representation Learning With Semantic Alignment for Referring Video Object Segmentation","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-cross-modal-interaction-from-a-top","title":"Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation","date":"2021-06-02","arxiv_id":"2106.01061","repositories_listed":0,"syntology":null}],"syntology_records":22,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":3,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/referring-video-object-segmentation-on-refer","since_archive":"/sota/referring-video-object-segmentation-on-refer#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/referring-video-object-segmentation-on-mevis","since_archive":"/sota/referring-video-object-segmentation-on-mevis#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/referring-video-object-segmentation-on-ref","since_archive":"/sota/referring-video-object-segmentation-on-ref#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/referring-video-object-segmentation-on-revos","since_archive":"/sota/referring-video-object-segmentation-on-revos#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/referring-video-object-segmentation-on-long","since_archive":"/sota/referring-video-object-segmentation-on-long#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":22,"papers_where_code_ran_first_page":"/task/referring-video-object-segmentation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/referring-video-object-segmentation/papers/ran/1","json":"/task/referring-video-object-segmentation/papers/ran/1.json","rows":22}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"55c12adbdf2c9c39014d5ad186737e0dc3fc951a31c1c7059b54181a33aef5e3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}