{"id":"https://openalex.org/W4416137260","doi":"https://doi.org/10.1109/ipta66025.2025.11222071","title":"Landmark-Based Fast LIP Reading with CTC Loss","display_name":"Landmark-Based Fast LIP Reading with CTC Loss","publication_year":2025,"publication_date":"2025-10-13","ids":{"openalex":"https://openalex.org/W4416137260","doi":"https://doi.org/10.1109/ipta66025.2025.11222071"},"language":null,"primary_location":{"id":"doi:10.1109/ipta66025.2025.11222071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipta66025.2025.11222071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Fourteenth International Conference on Image Processing, Theory, Tools &amp;amp; Applications (IPTA)","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/A5113030546","display_name":"O\u011fuz Ali Arslan","orcid":null},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Oguz Ali Arslan","raw_affiliation_strings":["Istanbul Technical University,Department of AI and Data Engineering,&#x0130;stanbul,T&#x00FC;rkiye"],"affiliations":[{"raw_affiliation_string":"Istanbul Technical University,Department of AI and Data Engineering,&#x0130;stanbul,T&#x00FC;rkiye","institution_ids":["https://openalex.org/I48912391"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120594609","display_name":"Doruk Uzgun","orcid":null},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Doruk Uzgun","raw_affiliation_strings":["Istanbul Technical University,Department of AI and Data Engineering,&#x0130;stanbul,T&#x00FC;rkiye"],"affiliations":[{"raw_affiliation_string":"Istanbul Technical University,Department of AI and Data Engineering,&#x0130;stanbul,T&#x00FC;rkiye","institution_ids":["https://openalex.org/I48912391"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075053608","display_name":"Batuhan Cengiz","orcid":"https://orcid.org/0000-0003-0228-9138"},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Batuhan Cengiz","raw_affiliation_strings":["Istanbul Technical University,Department of AI and Data Engineering,&#x0130;stanbul,T&#x00FC;rkiye"],"affiliations":[{"raw_affiliation_string":"Istanbul Technical University,Department of AI and Data Engineering,&#x0130;stanbul,T&#x00FC;rkiye","institution_ids":["https://openalex.org/I48912391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070786755","display_name":"Cihan Topal","orcid":"https://orcid.org/0000-0002-6329-5251"},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Cihan Topal","raw_affiliation_strings":["Istanbul Technical University,Department of AI and Data Engineering,&#x0130;stanbul,T&#x00FC;rkiye"],"affiliations":[{"raw_affiliation_string":"Istanbul Technical University,Department of AI and Data Engineering,&#x0130;stanbul,T&#x00FC;rkiye","institution_ids":["https://openalex.org/I48912391"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113030546"],"corresponding_institution_ids":["https://openalex.org/I48912391"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44633391,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9211000204086304,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9211000204086304,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11448","display_name":"Face recognition and analysis","score":0.05510000139474869,"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/T12301","display_name":"Facial Nerve Paralysis Treatment and Research","score":0.007699999958276749,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.8296999931335449},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6503999829292297},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6410999894142151},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5507000088691711},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4848000109195709},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46779999136924744},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.459199994802475},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42500001192092896},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.41760000586509705}],"concepts":[{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.8296999931335449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979999780654907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6888999938964844},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6503999829292297},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6410999894142151},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5776000022888184},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4848000109195709},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46779999136924744},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43209999799728394},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3765999972820282},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.34950000047683716},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2870999872684479},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipta66025.2025.11222071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipta66025.2025.11222071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Fourteenth International Conference on Image Processing, Theory, Tools &amp;amp; Applications (IPTA)","raw_type":"proceedings-article"},{"id":"pmh:oai:polen.itu.edu.tr:11527/32031","is_oa":false,"landing_page_url":"https://hdl.handle.net/11527/32031","pdf_url":null,"source":{"id":"https://openalex.org/S4306400460","display_name":"Istanbul Technical University Academic Open Archive (Istanbul Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I48912391","host_organization_name":"Istanbul Technical University","host_organization_lineage":["https://openalex.org/I48912391"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W124434589","https://openalex.org/W816265349","https://openalex.org/W2096651761","https://openalex.org/W2127141656","https://openalex.org/W2142075667","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2963030892","https://openalex.org/W2963785710","https://openalex.org/W2972756321","https://openalex.org/W3016011581","https://openalex.org/W3097385349","https://openalex.org/W4312638101","https://openalex.org/W4379116955","https://openalex.org/W4380373744"],"related_works":[],"abstract_inverted_index":{"Lip":[0],"reading":[1],"is":[2,85],"a":[3,19,72,89,110,155],"challenging":[4],"visual":[5,25,55],"recognition":[6,27],"task":[7],"that":[8,132],"typically":[9],"requires":[10],"substantial":[11],"computational":[12,50],"resources.":[13],"In":[14],"this":[15],"study,":[16],"we":[17,101],"propose":[18],"lightweight":[20],"and":[21,63,97],"efficient":[22,157],"approach":[23],"to":[24],"speech":[26],"by":[28],"leveraging":[29],"facial":[30,41],"landmark":[31,64],"coordinates":[32],"instead":[33],"of":[34,69,123],"raw":[35],"video":[36],"input.":[37],"By":[38],"representing":[39,71],"full":[40],"movements":[42],"through":[43],"these":[44],"coordinates,":[45],"our":[46,133],"method":[47,153],"significantly":[48,147],"reduces":[49],"complexity":[51],"while":[52],"retaining":[53],"essential":[54],"information.":[56],"Our":[57],"pipeline":[58],"begins":[59],"with":[60,116,146],"face":[61],"detection":[62],"extraction":[65],"for":[66,161],"each":[67],"batch":[68],"frames":[70],"single":[73],"word.":[74],"The":[75,151],"extracted":[76],"landmarks":[77],"are":[78],"organized":[79],"into":[80,88],"an":[81],"input":[82],"matrix,":[83],"which":[84],"then":[86],"fed":[87],"spatio-temporal":[90],"neural":[91],"network.":[92],"To":[93],"model":[94,135],"temporal":[95],"dynamics":[96],"perform":[98],"word":[99],"recognition,":[100],"employ":[102,109],"Connectionist":[103,117],"Temporal":[104,118],"Classification":[105,119],"(CTC)":[106,120],"loss.":[107],"We":[108],"compact":[111],"spatiotemporal":[112],"CNN-RNN":[113],"network":[114],"trained":[115],"loss-allowing":[121],"alignment":[122],"variable-length":[124],"inputs.":[125],"Experiments":[126],"on":[127],"the":[128],"MIRACL-VC1":[129],"dataset":[130],"demonstrate":[131],"CTC-based":[134],"achieves":[136],"<tex":[137],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{9":[139],"3.":[140],"3":[141,142],"\\%}$</tex>":[143],"word-level":[144],"accuracy":[145],"reduced":[148],"inference":[149],"time.":[150],"proposed":[152],"delivers":[154],"highly":[156],"lip-reading":[158],"pipeline,":[159],"ideal":[160],"real-time":[162],"or":[163],"edgedevice":[164],"deployment.":[165]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-10T00:00:00"}