{"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/language-as-queries-for-referring-video","title":"Language as Queries for Referring Video Object Segmentation","arxiv_id":"2201.00487","date":"2022-01-03","proceeding":"CVPR 2022 1","authors":["Jiannan Wu","Yi Jiang","Peize Sun","Zehuan Yuan","Ping Luo"],"abstract":"Referring video object segmentation (R-VOS) is an emerging cross-modal task that aims to segment the target object referred by a language expression in all video frames. In this work, we propose a simple and unified framework built upon Transformer, termed ReferFormer. It views the language as queries and directly attends to the most relevant regions in the video frames. Concretely, we introduce a small set of object queries conditioned on the language as the input to the Transformer. In this manner, all the queries are obligated to find the referred objects only. They are eventually transformed into dynamic kernels which capture the crucial object-level information, and play the role of convolution filters to generate the segmentation masks from feature maps. The object tracking is achieved naturally by linking the corresponding queries across frames. This mechanism greatly simplifies the pipeline and the end-to-end framework is significantly different from the previous methods. Extensive experiments on Ref-Youtube-VOS, Ref-DAVIS17, A2D-Sentences and JHMDB-Sentences show the effectiveness of ReferFormer. On Ref-Youtube-VOS, Refer-Former achieves 55.6J&F with a ResNet-50 backbone without bells and whistles, which exceeds the previous state-of-the-art performance by 8.4 points. In addition, with the strong Swin-Large backbone, ReferFormer achieves the best J&F of 64.2 among all existing methods. Moreover, we show the impressive results of 55.0 mAP and 43.7 mAP on A2D-Sentences andJHMDB-Sentences respectively, which significantly outperforms the previous methods by a large margin. Code is publicly available at https://github.com/wjn922/ReferFormer.","url_abs":"https://arxiv.org/abs/2201.00487v2","url_pdf":"https://arxiv.org/pdf/2201.00487v2.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":"language-as-queries-for-referring-video","repo_url":"https://github.com/wjn922/referformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"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-instance-segmentation","task_name":"Video Instance Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/referring-expression-segmentation-on-a2d","task":"Referring Expression Segmentation","dataset":"A2D Sentences","model":"ReferFormer (Video-Swin-B)","rank_in_archive_order":3,"of":27,"metrics":{"AP":"0.550","IoU mean":"0.703","IoU overall":"0.786","Precision@0.5":"0.831","Precision@0.6":"0.804","Precision@0.7":"0.741","Precision@0.8":"0.579","Precision@0.9":"0.212"},"uses_additional_data":true},{"leaderboard":"/sota/referring-expression-segmentation-on-davis","task":"Referring Expression Segmentation","dataset":"DAVIS 2017 (val)","model":"ReferFormer","rank_in_archive_order":7,"of":18,"metrics":{"J&F 1st frame":"61.1"},"uses_additional_data":true},{"leaderboard":"/sota/referring-expression-segmentation-on-refer-1","task":"Referring Expression Segmentation","dataset":"Refer-YouTube-VOS (2021 public validation)","model":"ReferFormer (ResNet-101)","rank_in_archive_order":25,"of":33,"metrics":{"F":"58.4","J":"56.1","J&F":"57.3"},"uses_additional_data":true},{"leaderboard":"/sota/referring-expression-segmentation-on-refer-1","task":"Referring Expression Segmentation","dataset":"Refer-YouTube-VOS (2021 public validation)","model":"ReferFormer (ResNet-50)","rank_in_archive_order":27,"of":33,"metrics":{"F":"56.6","J":"54.8","J&F":"55.6"},"uses_additional_data":true},{"leaderboard":"/sota/referring-video-object-segmentation-on-mevis","task":"Referring Video Object Segmentation","dataset":"MeViS","model":"ReferFormer","rank_in_archive_order":13,"of":16,"metrics":{"F":"32.2","J":"29.8","J&F":"31.0"},"uses_additional_data":false},{"leaderboard":"/sota/referring-video-object-segmentation-on-revos","task":"Referring Video Object Segmentation","dataset":"ReVOS","model":"ReferFormer (Video-Swin-B)","rank_in_archive_order":7,"of":9,"metrics":{"F":"29.9","J":"26.2","J&F":"28.1","R":"8.8"},"uses_additional_data":false},{"leaderboard":"/sota/referring-video-object-segmentation-on-ref","task":"Referring Video Object Segmentation","dataset":"Ref-DAVIS17","model":"ReferFormer","rank_in_archive_order":9,"of":11,"metrics":{"F":"64.1","J":"58.1","J&F":"61.1"},"uses_additional_data":false},{"leaderboard":"/sota/referring-video-object-segmentation-on-refer","task":"Referring Video Object Segmentation","dataset":"Refer-YouTube-VOS","model":"ReferFormer (Large)","rank_in_archive_order":12,"of":18,"metrics":{"F":"64.6","J":"61.3","J&F":"62.9"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.00487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00487"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wjn922/referformer","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/wjn922/ReferFormer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"ran":5,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":8,"samples":[{"code_sha256_prefix":"29dbbaafa4be18e1","entry":"aligned_bilinear","repo":"wjn922/ReferFormer","repo_kind":"official","path":"models/referformer.py","file_url":"https://github.com/wjn922/ReferFormer/blob/HEAD/models/referformer.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":false,"mcp_get_code":{"code_sha256":"29dbbaafa4be18e1"}},{"code_sha256_prefix":"ef1a3e10a9dbf4a9","entry":"box_cxcywh_to_xyxy","repo":"wjn922/ReferFormer","repo_kind":"official","path":"inference_davis.py","file_url":"https://github.com/wjn922/ReferFormer/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":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"ef1a3e10a9dbf4a9"}},{"code_sha256_prefix":"ed1a308adb65f645","entry":"compute_locations","repo":"wjn922/ReferFormer","repo_kind":"official","path":"models/referformer.py","file_url":"https://github.com/wjn922/ReferFormer/blob/HEAD/models/referformer.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":false,"mcp_get_code":{"code_sha256":"ed1a308adb65f645"}},{"code_sha256_prefix":"6296ea80154ae7f9","entry":"dice_coef","repo":"wjn922/ReferFormer","repo_kind":"official","path":"models/matcher.py","file_url":"https://github.com/wjn922/ReferFormer/blob/HEAD/models/matcher.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":false,"mcp_get_code":{"code_sha256":"6296ea80154ae7f9"}},{"code_sha256_prefix":"46f34dc9f9a94b67","entry":"parse_dynamic_params","repo":"wjn922/ReferFormer","repo_kind":"official","path":"models/referformer.py","file_url":"https://github.com/wjn922/ReferFormer/blob/HEAD/models/referformer.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":false,"mcp_get_code":{"code_sha256":"46f34dc9f9a94b67"}},{"code_sha256_prefix":"2626a807bce7587a","entry":"rescale_bboxes","repo":"wjn922/ReferFormer","repo_kind":"official","path":"inference_davis.py","file_url":"https://github.com/wjn922/ReferFormer/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":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"2626a807bce7587a"}},{"code_sha256_prefix":"9502374fe12f11e4","entry":"sigmoid_focal_coef","repo":"wjn922/ReferFormer","repo_kind":"official","path":"models/matcher.py","file_url":"https://github.com/wjn922/ReferFormer/blob/HEAD/models/matcher.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":false,"mcp_get_code":{"code_sha256":"9502374fe12f11e4"}},{"code_sha256_prefix":"ccbe959ea69981ad","entry":"vis_add_mask","repo":"wjn922/ReferFormer","repo_kind":"official","path":"inference_davis.py","file_url":"https://github.com/wjn922/ReferFormer/blob/HEAD/inference_davis.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":false,"mcp_get_code":{"code_sha256":"ccbe959ea69981ad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}