{"id":"https://openalex.org/W7094939976","doi":"https://doi.org/10.1145/3746027.3755499","title":"DEPO: Enhancing E-commerce Image Background Generation with Short Trajectory Direct Expected Preference Optimization","display_name":"DEPO: Enhancing E-commerce Image Background Generation with Short Trajectory Direct Expected Preference Optimization","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W7094939976","doi":"https://doi.org/10.1145/3746027.3755499"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755499","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755499","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755499","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shikun Sun","orcid":"https://orcid.org/0009-0008-2370-8841"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shikun Sun","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chengrui Wang","orcid":"https://orcid.org/0000-0003-0618-0797"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengrui Wang","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Min Zhou","orcid":"https://orcid.org/0009-0004-7041-3959"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhou","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zixuan Wang","orcid":"https://orcid.org/0000-0001-7291-6198"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoyu Qin","orcid":"https://orcid.org/0000-0002-9720-3220"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Qin","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tiezheng Ge","orcid":"https://orcid.org/0000-0003-1381-2692"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiezheng Ge","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bo Zheng","orcid":"https://orcid.org/0000-0002-4037-6315"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zheng","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jia Jia","orcid":"https://orcid.org/0000-0001-7118-3666"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["BNRist,Tsinghua University, Key Laboratory of Pervasive Computing, Ministry of Education, Beijing, China"],"affiliations":[{"raw_affiliation_string":"BNRist,Tsinghua University, Key Laboratory of Pervasive Computing, Ministry of Education, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5568093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10239","last_page":"10247"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7038000226020813,"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":0.7038000226020813,"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/T11019","display_name":"Image Enhancement Techniques","score":0.053300000727176666,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.027000000700354576,"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/key","display_name":"Key (lock)","score":0.5260000228881836},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4878999888896942},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.4496000111103058},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43790000677108765},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.43720000982284546},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.43209999799728394},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.42010000348091125},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41819998621940613},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.40290001034736633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7069000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5630000233650208},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5260000228881836},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4505000114440918},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.43720000982284546},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.40290001034736633},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3756999969482422},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.36800000071525574},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3154999911785126},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3140999972820282},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25540000200271606},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755499","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755499","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755499","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755499","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G767264109","display_name":null,"funder_award_id":"No. 62425604","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1971159979","https://openalex.org/W2183341477","https://openalex.org/W2960974111","https://openalex.org/W2964082390","https://openalex.org/W2981478592","https://openalex.org/W3034684802","https://openalex.org/W4312933868","https://openalex.org/W4386072096","https://openalex.org/W4390136296","https://openalex.org/W4402753790","https://openalex.org/W4403792451"],"related_works":[],"abstract_inverted_index":{"Generating":[0],"high-quality,":[1],"user-preferred":[2],"backgrounds":[3],"for":[4,11],"e-commerce":[5],"product":[6],"images":[7],"poses":[8],"unique":[9],"challenges":[10],"diffusion":[12,40,77],"models,":[13],"particularly":[14],"in":[15,30,166],"aligning":[16,31],"outputs":[17],"with":[18,34,92,150],"human":[19,35],"visual":[20],"preferences.":[21],"While":[22],"Direct":[23,65],"Preference":[24,67],"Optimization":[25,68],"(DPO)":[26],"has":[27],"shown":[28],"promise":[29],"generative":[32],"models":[33,41,78],"feedback,":[36,102],"its":[37],"application":[38],"to":[39,76,95,106,118,129,138],"faces":[42],"key":[43],"limitations,":[44],"including":[45],"the":[46,108,121,168],"trade-off":[47],"between":[48],"reward":[49,101],"sparsity":[50],"and":[51,56,82,99,111,115,142,170],"supervision":[52],"quality,":[53],"mode":[54,113],"collapse,":[55,114],"training":[57,81,131],"instability.":[58],"To":[59],"tackle":[60],"these":[61],"issues,":[62],"we":[63],"propose":[64],"Expected":[66],"(DEPO),":[69],"a":[70,88],"novel":[71],"framework":[72],"that":[73,161],"adapts":[74],"DPO":[75],"through":[79],"redesigned":[80],"sampling":[83],"strategies.":[84],"Specifically,":[85],"DEPO":[86,89,146,162],"introduces":[87],"loss":[90],"combined":[91],"trajectory":[93],"segmentation":[94],"enable":[96],"more":[97],"frequent":[98],"informative":[100],"employs":[103],"Langevin":[104],"MCMC":[105],"broaden":[107],"exploration":[109],"space":[110,123],"mitigate":[112],"leverages":[116],"masks":[117],"effectively":[119],"constrain":[120],"search":[122],"while":[124,153],"incorporating":[125,143],"targeted":[126],"engineering":[127],"designs":[128],"improve":[130],"stability.":[132],"By":[133],"directly":[134],"linking":[135],"image-domain":[136],"evaluations":[137],"expected":[139],"log":[140],"probabilities":[141],"adversarial":[144],"training,":[145],"achieves":[147],"better":[148],"alignment":[149],"user":[151],"preferences":[152],"maintaining":[154],"high":[155],"image":[156],"fidelity.":[157],"Experimental":[158],"results":[159],"demonstrate":[160],"surpasses":[163],"existing":[164],"methods":[165],"both":[167],"diversity":[169],"quality":[171],"of":[172],"background":[173],"generation.":[174]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}