{"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/onlinerefer-a-simple-online-baseline-for","title":"OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation","arxiv_id":"2307.09356","date":"2023-07-18","proceeding":"ICCV 2023 1","authors":["Dongming Wu","Tiancai Wang","Yuang Zhang","Xiangyu Zhang","Jianbing Shen"],"abstract":"Referring video object segmentation (RVOS) aims at segmenting an object in a video following human instruction. Current state-of-the-art methods fall into an offline pattern, in which each clip independently interacts with text embedding for cross-modal understanding. They usually present that the offline pattern is necessary for RVOS, yet model limited temporal association within each clip. In this work, we break up the previous offline belief and propose a simple yet effective online model using explicit query propagation, named OnlineRefer. Specifically, our approach leverages target cues that gather semantic information and position prior to improve the accuracy and ease of referring predictions for the current frame. Furthermore, we generalize our online model into a semi-online framework to be compatible with video-based backbones. To show the effectiveness of our method, we evaluate it on four benchmarks, \\ie, Refer-Youtube-VOS, Refer-DAVIS17, A2D-Sentences, and JHMDB-Sentences. Without bells and whistles, our OnlineRefer with a Swin-L backbone achieves 63.5 J&F and 64.8 J&F on Refer-Youtube-VOS and Refer-DAVIS17, outperforming all other offline methods.","url_abs":"https://arxiv.org/abs/2307.09356v1","url_pdf":"https://arxiv.org/pdf/2307.09356v1.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":"onlinerefer-a-simple-online-baseline-for","repo_url":"https://github.com/wudongming97/onlinerefer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"referring-video-object-segmentation","task_name":"Referring Video Object Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"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":"OnlineRefer (Swin-L, online)","rank_in_archive_order":21,"of":33,"metrics":{"F":"65.5","J":"61.6","J&F":"63.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.09356","atlas_url":"https://app.syntology.ai/?focus=2307.09356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09356"}},"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/wudongming97/onlinerefer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":3,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":"wudongming97/onlinerefer","repo_kind":"official","path":"models/onlinerefer.py","file_url":"https://github.com/wudongming97/onlinerefer/blob/HEAD/models/onlinerefer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"29dbbaafa4be18e1"}},{"code_sha256_prefix":"ef1a3e10a9dbf4a9","entry":"box_cxcywh_to_xyxy","repo":"wudongming97/onlinerefer","repo_kind":"official","path":"inference_davis_online.py","file_url":"https://github.com/wudongming97/onlinerefer/blob/HEAD/inference_davis_online.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ef1a3e10a9dbf4a9"}},{"code_sha256_prefix":"ed1a308adb65f645","entry":"compute_locations","repo":"wudongming97/onlinerefer","repo_kind":"official","path":"models/onlinerefer.py","file_url":"https://github.com/wudongming97/onlinerefer/blob/HEAD/models/onlinerefer.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ed1a308adb65f645"}},{"code_sha256_prefix":"46f34dc9f9a94b67","entry":"parse_dynamic_params","repo":"wudongming97/onlinerefer","repo_kind":"official","path":"models/onlinerefer.py","file_url":"https://github.com/wudongming97/onlinerefer/blob/HEAD/models/onlinerefer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"46f34dc9f9a94b67"}},{"code_sha256_prefix":"79016404390adaca","entry":"pos2posemb","repo":"wudongming97/onlinerefer","repo_kind":"official","path":"models/deformable_transformer_plus.py","file_url":"https://github.com/wudongming97/onlinerefer/blob/HEAD/models/deformable_transformer_plus.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"79016404390adaca"}},{"code_sha256_prefix":"2626a807bce7587a","entry":"rescale_bboxes","repo":"wudongming97/onlinerefer","repo_kind":"official","path":"inference_davis_online.py","file_url":"https://github.com/wudongming97/onlinerefer/blob/HEAD/inference_davis_online.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2626a807bce7587a"}},{"code_sha256_prefix":"ccbe959ea69981ad","entry":"vis_add_mask","repo":"wudongming97/onlinerefer","repo_kind":"official","path":"inference_davis_online.py","file_url":"https://github.com/wudongming97/onlinerefer/blob/HEAD/inference_davis_online.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ccbe959ea69981ad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}