{"id":"https://openalex.org/W4408353181","doi":"https://doi.org/10.1109/icassp49660.2025.10888913","title":"TGDrag: Adding Semantic Control into Point-based Image Editing via Text Guidance","display_name":"TGDrag: Adding Semantic Control into Point-based Image Editing via Text Guidance","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353181","doi":"https://doi.org/10.1109/icassp49660.2025.10888913"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046723920","display_name":"Chenhao Lin","orcid":"https://orcid.org/0000-0002-6265-7345"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenhao Lin","raw_affiliation_strings":["Xi’an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087850504","display_name":"Yanjie Zhu","orcid":"https://orcid.org/0000-0002-9131-689X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjie Zhu","raw_affiliation_strings":["Xi’an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101231610","display_name":"Yingmao Miao","orcid":"https://orcid.org/0000-0003-3483-2385"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingmao Miao","raw_affiliation_strings":["Xi’an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058084433","display_name":"Zhengyu Zhao","orcid":"https://orcid.org/0000-0003-0745-4294"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyu Zhao","raw_affiliation_strings":["Xi’an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004735889","display_name":"Shuai Liu","orcid":"https://orcid.org/0000-0002-0327-6729"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Liu","raw_affiliation_strings":["Xi’an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101843177","display_name":"Chao Shen","orcid":"https://orcid.org/0000-0002-6959-0569"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Shen","raw_affiliation_strings":["Xi’an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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":0.02948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9855999946594238,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9855999946594238,"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":0.9714999794960022,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9577000141143799,"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/computer-science","display_name":"Computer science","score":0.807748556137085},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5760124325752258},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5546379685401917},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4818938374519348},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4619596004486084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44358137249946594},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4418197572231293},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.41472315788269043},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3419203758239746},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0748150646686554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807748556137085},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5760124325752258},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5546379685401917},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4818938374519348},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4619596004486084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44358137249946594},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4418197572231293},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.41472315788269043},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3419203758239746},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0748150646686554},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2962770929","https://openalex.org/W2985068832","https://openalex.org/W3035574324","https://openalex.org/W3096831136","https://openalex.org/W3173241699","https://openalex.org/W4286611278","https://openalex.org/W4312282373","https://openalex.org/W4312740349","https://openalex.org/W4312933868","https://openalex.org/W4313172221","https://openalex.org/W4328029562","https://openalex.org/W4385535562","https://openalex.org/W4386057725","https://openalex.org/W4402727040","https://openalex.org/W4402753848","https://openalex.org/W4404024919","https://openalex.org/W4404582562","https://openalex.org/W6631190155","https://openalex.org/W6677618333","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6791353385","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6841366371","https://openalex.org/W6854226172"],"related_works":["https://openalex.org/W4319453795","https://openalex.org/W4205104112","https://openalex.org/W4406058807","https://openalex.org/W1974870326","https://openalex.org/W2770776392","https://openalex.org/W3176454756","https://openalex.org/W2772330423","https://openalex.org/W3163523050","https://openalex.org/W3006381446","https://openalex.org/W3015353979"],"abstract_inverted_index":{"Controllable":[0],"image":[1,14,27,68],"generation":[2],"has":[3],"emerged":[4],"as":[5,18],"a":[6,59,86,113],"cutting-edge":[7],"subject":[8],"of":[9,45,78,104,138],"interest.":[10],"Current":[11],"interactive":[12],"point-based":[13,33,67],"editing":[15,69],"frameworks,":[16],"such":[17],"DragGAN,":[19],"achieve":[20],"impressive":[21],"results":[22,130],"in":[23],"fine-grained":[24],"and":[25,80,97,125],"controllable":[26],"editing.":[28],"However,":[29],"relying":[30],"solely":[31],"on":[32,107],"manipulations":[34],"can":[35],"lead":[36],"to":[37,41,62,74,99,117],"unintended":[38],"outcomes":[39],"due":[40],"the":[42,46,76,95,101,119,122,126,135],"inherent":[43],"lack":[44],"users\u2019":[47],"semantic":[48,64,105,139],"intent.":[49],"To":[50],"address":[51],"this":[52],"issue,":[53],"we":[54,84,111],"introduce":[55,112],"Text-Guided":[56],"Drag":[57],"(TGDrag),":[58],"novel":[60],"approach":[61],"adding":[63],"control":[65,106,140],"into":[66],"by":[70],"using":[71],"text":[72,96,114,127],"prompts":[73],"guide":[75],"manipulation":[77],"handle":[79],"target":[81],"points.":[82],"Specifically,":[83],"design":[85],"channel":[87],"correlation":[88],"calculator":[89],"that":[90,132],"adaptively":[91],"selects":[92],"channels":[93],"for":[94],"points":[98],"mitigate":[100],"potential":[102],"influence":[103],"point":[108,145],"control.":[109,146],"Furthermore,":[110],"loss":[115],"function":[116,137],"minimize":[118],"discrepancy":[120],"between":[121],"generated":[123],"images":[124],"prompts.":[128],"Experimental":[129],"demonstrate":[131],"TGDrag":[133],"achieves":[134],"expected":[136],"while":[141],"maintaining":[142],"effectiveness":[143],"regarding":[144]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}