{"id":"https://openalex.org/W2910182281","doi":"https://doi.org/10.1145/3291064.3291067","title":"Multimodal Deep Learning in Semantic Image Segmentation","display_name":"Multimodal Deep Learning in Semantic Image Segmentation","publication_year":2018,"publication_date":"2018-10-29","ids":{"openalex":"https://openalex.org/W2910182281","doi":"https://doi.org/10.1145/3291064.3291067","mag":"2910182281"},"language":"en","primary_location":{"id":"doi:10.1145/3291064.3291067","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3291064.3291067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Cloud Computing and Internet of Things","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/A5112506703","display_name":"Vishal Raman","orcid":null},"institutions":[{"id":"https://openalex.org/I36909309","display_name":"National Institute of Technology Hamirpur","ror":"https://ror.org/01nc8zs04","country_code":"IN","type":"education","lineage":["https://openalex.org/I36909309","https://openalex.org/I4210152752"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vishal Raman","raw_affiliation_strings":["NIT Hamirpur, Hamirpur, Himachal Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NIT Hamirpur, Hamirpur, Himachal Pradesh, India","institution_ids":["https://openalex.org/I36909309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110612676","display_name":"Madhu Kumari","orcid":"https://orcid.org/0009-0006-2989-9883"},"institutions":[{"id":"https://openalex.org/I36909309","display_name":"National Institute of Technology Hamirpur","ror":"https://ror.org/01nc8zs04","country_code":"IN","type":"education","lineage":["https://openalex.org/I36909309","https://openalex.org/I4210152752"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Madhu Kumari","raw_affiliation_strings":["NIT Hamirpur, Hamirpur, Himachal Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NIT Hamirpur, Hamirpur, Himachal Pradesh, India","institution_ids":["https://openalex.org/I36909309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.16864248,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994999766349792,"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":0.998199999332428,"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":0.7088945508003235},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6414346694946289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6389740705490112},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.53660649061203},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5311499834060669},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4811474084854126},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.48078101873397827},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.4705650806427002},{"id":"https://openalex.org/keywords/image-texture","display_name":"Image texture","score":0.4685289263725281},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.4653525948524475},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4360068142414093},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41723254323005676},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.3665764629840851},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34124499559402466}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7088945508003235},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6414346694946289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6389740705490112},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.53660649061203},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5311499834060669},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4811474084854126},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.48078101873397827},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.4705650806427002},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.4685289263725281},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4653525948524475},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4360068142414093},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41723254323005676},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3665764629840851},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34124499559402466},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3291064.3291067","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3291064.3291067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Cloud Computing and Internet of Things","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W47989428","https://openalex.org/W60493759","https://openalex.org/W1836465849","https://openalex.org/W1964858464","https://openalex.org/W2014103885","https://openalex.org/W2109586012","https://openalex.org/W2120109874","https://openalex.org/W2124964692","https://openalex.org/W2147069236","https://openalex.org/W2465570449","https://openalex.org/W2534195370","https://openalex.org/W2559655401","https://openalex.org/W2562630055","https://openalex.org/W2578005801","https://openalex.org/W2605127024","https://openalex.org/W2619383789","https://openalex.org/W2623808377","https://openalex.org/W2739837873","https://openalex.org/W2767290858","https://openalex.org/W2768799425","https://openalex.org/W2791155853","https://openalex.org/W2793146153","https://openalex.org/W2798365772","https://openalex.org/W2806997312","https://openalex.org/W2809473392","https://openalex.org/W2949117887","https://openalex.org/W2951127645","https://openalex.org/W2963826681","https://openalex.org/W2964204553","https://openalex.org/W3099268463"],"related_works":["https://openalex.org/W1987618107","https://openalex.org/W2204605857","https://openalex.org/W2416959398","https://openalex.org/W3196005494","https://openalex.org/W2355370993","https://openalex.org/W1595732891","https://openalex.org/W2093085045","https://openalex.org/W2170380303","https://openalex.org/W3017192027","https://openalex.org/W2184524617"],"abstract_inverted_index":{"In":[0,64],"recent":[1],"years,":[2],"there":[3],"has":[4,49],"been":[5],"a":[6,51,70],"lot":[7],"of":[8,13,40,56],"research":[9,57],"in":[10,85],"the":[11,37,82],"area":[12],"semantic":[14,77],"image":[15,22,41,47,78,86],"segmentation,":[16],"which":[17],"involves":[18],"breaking":[19],"down":[20],"an":[21],"into":[23],"its":[24,34],"discrete":[25],"components,":[26],"such":[27],"that":[28],"humans":[29],"can":[30],"give":[31],"meaning":[32],"to":[33,76],"contents.":[35],"From":[36],"humble":[38],"beginnings":[39],"search":[42,87],"using":[43],"human-provided":[44],"captions,":[45],"content-based":[46],"retrieval":[48],"come":[50],"long":[52],"way.":[53],"Yet,":[54],"areas":[55],"and":[58,88],"improvement":[59],"are":[60,80],"far":[61],"from":[62],"diminishing.":[63],"this":[65],"paper":[66],"we":[67],"will":[68],"take":[69],"look":[71],"at":[72],"how":[73],"multi-modal":[74],"approaches":[75],"segmentation":[79],"setting":[81],"new":[83],"standard":[84],"retrieval.":[89]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
