{"id":"https://openalex.org/W7160614695","doi":"https://doi.org/10.1145/3805622.3810595","title":"From Diffusion to Rectified Flow: Rethinking Text-Based Segmentation","display_name":"From Diffusion to Rectified Flow: Rethinking Text-Based Segmentation","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7160614695","doi":"https://doi.org/10.1145/3805622.3810595"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810595","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810595","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810595","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135645248","display_name":"Zishen Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zishen Qu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-9403-4462","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135672779","display_name":"Xuesong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuesong Li","raw_affiliation_strings":["bytedance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-8565-3119","affiliations":[{"raw_affiliation_string":"bytedance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135705968","display_name":"Haijian Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongwei Kang","raw_affiliation_strings":["bytedance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7150-5506","affiliations":[{"raw_affiliation_string":"bytedance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135643191","display_name":"Hongwei Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijian Gu","raw_affiliation_strings":["Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-5154-2004","affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026974898","display_name":"Quan Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan Meng","raw_affiliation_strings":["bytedance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-5498-3498","affiliations":[{"raw_affiliation_string":"bytedance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046827942","display_name":"Tianrui Niu","orcid":"https://orcid.org/0000-0001-7743-3822"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianrui Niu","raw_affiliation_strings":["bytedance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7743-3822","affiliations":[{"raw_affiliation_string":"bytedance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135657173","display_name":"Xin Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Yang","raw_affiliation_strings":["bytedance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-7025-1820","affiliations":[{"raw_affiliation_string":"bytedance, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135691253","display_name":"Ruidong Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruidong Pan","raw_affiliation_strings":["bytedance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-5171-7078","affiliations":[{"raw_affiliation_string":"bytedance, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6766603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1241","last_page":"1250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3447999954223633,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3447999954223633,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10729999840259552,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07339999824762344,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.8141999840736389},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8065000176429749},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.637499988079071},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.583899974822998},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.558899998664856},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5527999997138977},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5436000227928162},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.5435000061988831},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5131999850273132}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8141999840736389},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8065000176429749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7189000248908997},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6826000213623047},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.637499988079071},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.558899998664856},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5527999997138977},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5436000227928162},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.5435000061988831},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4936999976634979},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.3797000050544739},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26589998602867126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3805622.3810595","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810595","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2605.04590","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.04590","pdf_url":"https://arxiv.org/pdf/2605.04590","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810595","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810595","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7726241946220398}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-based":[0],"image":[1,10,91],"segmentation":[2,25,54,71,94,164],"aims":[3],"to":[4,22,44,69,85,92,112,161,169],"delineate":[5],"object":[6],"boundaries":[7],"within":[8,96],"an":[9,138],"from":[11,89,105],"text":[12],"prompts,":[13],"offering":[14],"higher":[15,146],"flexibility":[16],"and":[17,109,137,177],"broader":[18],"application":[19,175],"scope":[20],"compared":[21],"traditional":[23],"fixed-category":[24],"tasks.":[26,55,72],"Recent":[27],"studies":[28,45],"have":[29],"shown":[30],"that":[31,66,81],"diffusion":[32,48,64,118],"models":[33,49,65],"(e.g.,":[34],"Stable":[35],"Diffusion)":[36],"can":[37],"provide":[38],"rich":[39],"multimodal":[40],"semantic":[41],"features,":[42],"leading":[43],"of":[46,63,117],"using":[47],"as":[50],"feature":[51],"extractors":[52],"for":[53],"Such":[56],"methods,":[57,128],"however,":[58],"inherit":[59],"the":[60,90,93,97,106,110,114,143,162],"generative":[61,159],"natures":[62],"are":[67],"harmful":[68],"discriminative":[70,163],"In":[73],"response,":[74],"we":[75],"propose":[76],"RLFSeg,":[77],"a":[78,150,157],"novel":[79],"framework":[80,155],"leverages":[82],"Rectified":[83],"Flow":[84],"learn":[86],"direct":[87],"mapping":[88],"mask":[95],"latent":[98],"space.":[99],"The":[100,154],"model":[101,144,160,170],"is":[102],"thus":[103,172],"freed":[104],"noise-denoise":[107],"process":[108],"need":[111],"optimize":[113],"time":[115],"step":[116],"models,":[119],"resulting":[120],"in":[121],"substantially":[122],"better":[123],"performance":[124],"than":[125],"previous":[126],"diffusion-based":[127],"especially":[129],"on":[130,149],"zero-shot":[131],"scenarios.":[132],"By":[133],"introducing":[134],"label":[135],"refinement":[136],"Adaptive":[139],"One-Step":[140],"Sampling":[141],"strategy,":[142],"achieves":[145],"accuracy":[147],"even":[148],"single":[151],"inference":[152],"step.":[153],"redirects":[156],"pretrained":[158],"task":[165],"with":[166],"zero":[167],"modification":[168],"structure,":[171],"reveals":[173],"promising":[174],"potential":[176],"significant":[178],"research":[179],"value.":[180]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-05-09T00:00:00"}