{"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/vision-language-transformer-and-query","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","arxiv_id":"2108.05565","date":"2021-08-12","proceeding":"ICCV 2021 10","authors":["Henghui Ding","Chang Liu","Suchen Wang","Xudong Jiang"],"abstract":"In this work, we address the challenging task of referring segmentation. The query expression in referring segmentation typically indicates the target object by describing its relationship with others. Therefore, to find the target one among all instances in the image, the model must have a holistic understanding of the whole image. To achieve this, we reformulate referring segmentation as a direct attention problem: finding the region in the image where the query language expression is most attended to. We introduce transformer and multi-head attention to build a network with an encoder-decoder attention mechanism architecture that \"queries\" the given image with the language expression. Furthermore, we propose a Query Generation Module, which produces multiple sets of queries with different attention weights that represent the diversified comprehensions of the language expression from different aspects. At the same time, to find the best way from these diversified comprehensions based on visual clues, we further propose a Query Balance Module to adaptively select the output features of these queries for a better mask generation. Without bells and whistles, our approach is light-weight and achieves new state-of-the-art performance consistently on three referring segmentation datasets, RefCOCO, RefCOCO+, and G-Ref. Our code is available at https://github.com/henghuiding/Vision-Language-Transformer.","url_abs":"https://arxiv.org/abs/2108.05565v1","url_pdf":"https://arxiv.org/pdf/2108.05565v1.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":"vision-language-transformer-and-query","repo_url":"https://github.com/henghuiding/Vision-Language-Transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"generalized-referring-expression","task_name":"Generalized Referring Expression Comprehension"},{"task_slug":"generalized-referring-expression-segmentation","task_name":"Generalized Referring Expression Segmentation"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalized-referring-expression","task":"Generalized Referring Expression Comprehension","dataset":"gRefCOCO","model":"VLT","rank_in_archive_order":4,"of":5,"metrics":{"N-acc.":"35.2","Precision@(F1=1, IoU≥0.5)":"36.6"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-referring-expression-segmentation","task":"Generalized Referring Expression Segmentation","dataset":"gRefCOCO","model":"VLT","rank_in_archive_order":12,"of":13,"metrics":{"cIoU":"52.51","gIoU":"52.00"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-5","task":"Referring Expression Segmentation","dataset":"RefCOCO+ test B","model":"VLT","rank_in_archive_order":21,"of":30,"metrics":{"Overall IoU":"49.36"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-4","task":"Referring Expression Segmentation","dataset":"RefCOCO+ testA","model":"VLT","rank_in_archive_order":22,"of":30,"metrics":{"Overall IoU":"59.20"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-3","task":"Referring Expression Segmentation","dataset":"RefCOCO+ val","model":"VLT","rank_in_archive_order":25,"of":33,"metrics":{"Overall IoU":"55.50"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcocog-1","task":"Referring Expression Segmentation","dataset":"RefCOCOg-test","model":"VLT (Darknet53)","rank_in_archive_order":16,"of":18,"metrics":{"Overall IoU":"56.65"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcocog","task":"Referring Expression Segmentation","dataset":"RefCOCOg-val","model":"VLT (Darknet53)","rank_in_archive_order":20,"of":23,"metrics":{"Overall IoU":"52.99"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco","task":"Referring Expression Segmentation","dataset":"RefCoCo val","model":"VLT","rank_in_archive_order":27,"of":37,"metrics":{"Overall IoU":"65.65"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.05565","atlas_url":"https://app.syntology.ai/?focus=2108.05565","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":"2108.05565"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2108.05565\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2108.05565"},"call":"get_concepts_for_paper(arxiv_id=\"2108.05565\")"}],"by_repo":[{"repo":"henghuiding/Vision-Language-Transformer","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2210.15871"],"harvested_for_calls":[{"arxiv_id":"2210.15871","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.15871"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.15871\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"8b9a48fbb97fcf2e6c19b75edb55d87f5fd7632d766ba7245c1457ce3507774e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}