{"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/towards-temporally-consistent-referring-video","title":"Temporally Consistent Referring Video Object Segmentation with Hybrid Memory","arxiv_id":"2403.19407","date":"2024-03-28","proceeding":null,"authors":["Bo Miao","Mohammed Bennamoun","Yongsheng Gao","Mubarak Shah","Ajmal Mian"],"abstract":"Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects. We propose an end-to-end R-VOS paradigm that explicitly models temporal instance consistency alongside the referring segmentation. Specifically, we introduce a novel hybrid memory that facilitates inter-frame collaboration for robust spatio-temporal matching and propagation. Features of frames with automatically generated high-quality reference masks are propagated to segment the remaining frames based on multi-granularity association to achieve temporally consistent R-VOS. Furthermore, we propose a new Mask Consistency Score (MCS) metric to evaluate the temporal consistency of video segmentation. Extensive experiments demonstrate that our approach enhances temporal consistency by a significant margin, leading to top-ranked performance on popular R-VOS benchmarks, i.e., Ref-YouTube-VOS (67.1%) and Ref-DAVIS17 (65.6%). The code is available at https://github.com/bo-miao/HTR.","url_abs":"https://arxiv.org/abs/2403.19407v2","url_pdf":"https://arxiv.org/pdf/2403.19407v2.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":"towards-temporally-consistent-referring-video","repo_url":"https://github.com/bo-miao/HTR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"htr","task_name":"HTR"},{"task_slug":"object","task_name":"Object"},{"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"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/referring-expression-segmentation-on-davis","task":"Referring Expression Segmentation","dataset":"DAVIS 2017 (val)","model":"HTR","rank_in_archive_order":4,"of":18,"metrics":{"J&F 1st frame":"65.6"},"uses_additional_data":true},{"leaderboard":"/sota/referring-expression-segmentation-on-refer-1","task":"Referring Expression Segmentation","dataset":"Refer-YouTube-VOS (2021 public validation)","model":"HTR (Pre-training)","rank_in_archive_order":10,"of":33,"metrics":{"F":"68.9","J":"65.3","J&F":"67.1"},"uses_additional_data":false},{"leaderboard":"/sota/referring-video-object-segmentation-on-mevis","task":"Referring Video Object Segmentation","dataset":"MeViS","model":"HTR","rank_in_archive_order":9,"of":16,"metrics":{"F":"45.5","J":"39.9","J&F":"42.7"},"uses_additional_data":false},{"leaderboard":"/sota/referring-video-object-segmentation-on-refer","task":"Referring Video Object Segmentation","dataset":"Refer-YouTube-VOS","model":"HTR","rank_in_archive_order":5,"of":18,"metrics":{"F":"68.9","J":"65.3","J&F":"67.1"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.19407","atlas_url":"https://app.syntology.ai/?focus=2403.19407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19407"}},"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/bo-miao/HTR","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"ran":7,"ran_honours":1,"ran_violates":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":15,"ran":14,"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":0,"samples":[{"code_sha256_prefix":"29dbbaafa4be18e1","entry":"aligned_bilinear","repo":"bo-miao/HTR","repo_kind":"official","path":"models/htr.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/models/htr.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"29dbbaafa4be18e1"}},{"code_sha256_prefix":"ef1a3e10a9dbf4a9","entry":"box_cxcywh_to_xyxy","repo":"bo-miao/HTR","repo_kind":"official","path":"inference_davis.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/inference_davis.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef1a3e10a9dbf4a9"}},{"code_sha256_prefix":"d09cc4c762bea5ad","entry":"compute_list_and","repo":"bo-miao/HTR","repo_kind":"official","path":"get_mcs.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/get_mcs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d09cc4c762bea5ad"}},{"code_sha256_prefix":"1acc2d14b5949a5e","entry":"compute_list_mean","repo":"bo-miao/HTR","repo_kind":"official","path":"get_mcs.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/get_mcs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1acc2d14b5949a5e"}},{"code_sha256_prefix":"ed1a308adb65f645","entry":"compute_locations","repo":"bo-miao/HTR","repo_kind":"official","path":"models/htr.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/models/htr.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed1a308adb65f645"}},{"code_sha256_prefix":"ac8fe530cdad4d8c","entry":"dice_loss","repo":"bo-miao/HTR","repo_kind":"official","path":"models/segmentation.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/models/segmentation.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac8fe530cdad4d8c"}},{"code_sha256_prefix":"480db93fba382e34","entry":"get_norm","repo":"bo-miao/HTR","repo_kind":"official","path":"models/segmentation.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/models/segmentation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"480db93fba382e34"}},{"code_sha256_prefix":"46f34dc9f9a94b67","entry":"parse_dynamic_params","repo":"bo-miao/HTR","repo_kind":"official","path":"models/htr.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/models/htr.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"46f34dc9f9a94b67"}},{"code_sha256_prefix":"bd254b679b58f849","entry":"pick_key_frames_id","repo":"bo-miao/HTR","repo_kind":"official","path":"inference_davis.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/inference_davis.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd254b679b58f849"}},{"code_sha256_prefix":"2626a807bce7587a","entry":"rescale_bboxes","repo":"bo-miao/HTR","repo_kind":"official","path":"inference_davis.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/inference_davis.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2626a807bce7587a"}},{"code_sha256_prefix":"5c0711aada67957e","entry":"sigmoid_focal_loss","repo":"bo-miao/HTR","repo_kind":"official","path":"models/segmentation.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/models/segmentation.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"code_sha256_prefix":"50c37a861e9c7b30","entry":"vos_dice_loss","repo":"bo-miao/HTR","repo_kind":"official","path":"models/criterion.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/models/criterion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50c37a861e9c7b30"}},{"code_sha256_prefix":"f9fd6241d935f07b","entry":"window_partition","repo":"bo-miao/HTR","repo_kind":"official","path":"models/swin_transformer.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/models/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9fd6241d935f07b"}},{"code_sha256_prefix":"fb32094c6dbece71","entry":"window_reverse","repo":"bo-miao/HTR","repo_kind":"official","path":"models/swin_transformer.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/models/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb32094c6dbece71"}},{"code_sha256_prefix":"f6cb67c029ab76f1","entry":"evaluate_mcs","repo":"bo-miao/HTR","repo_kind":"official","path":"get_mcs.py","file_url":"https://github.com/bo-miao/HTR/blob/HEAD/get_mcs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6cb67c029ab76f1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}