{"id":"https://openalex.org/W4391408865","doi":"https://doi.org/10.1145/3627631.3627634","title":"MMAG: Mutually Motivated Attention Gates for Simultaneous Extraction of Contextual and Spatial Information from a Monocular Image","display_name":"MMAG: Mutually Motivated Attention Gates for Simultaneous Extraction of Contextual and Spatial Information from a Monocular Image","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391408865","doi":"https://doi.org/10.1145/3627631.3627634"},"language":"en","primary_location":{"id":"doi:10.1145/3627631.3627634","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627631.3627634","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627631.3627634","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3627631.3627634","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036427078","display_name":"Aditya Singh","orcid":"https://orcid.org/0000-0001-6281-9431"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aditya Singh","raw_affiliation_strings":["IIIT Allahabad, IN"],"raw_orcid":"https://orcid.org/0000-0001-6281-9431","affiliations":[{"raw_affiliation_string":"IIIT Allahabad, IN","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081023191","display_name":"Saloni Mohan","orcid":"https://orcid.org/0009-0003-1387-6511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saloni Mohan","raw_affiliation_strings":["IIIT Allahabad, IN"],"raw_orcid":"https://orcid.org/0009-0003-1387-6511","affiliations":[{"raw_affiliation_string":"IIIT Allahabad, IN","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041478291","display_name":"Vandana Kushwaha","orcid":"https://orcid.org/0000-0001-8071-3585"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vandana Kushwaha","raw_affiliation_strings":["IIIT Allahabad, IN"],"raw_orcid":"https://orcid.org/0000-0001-8071-3585","affiliations":[{"raw_affiliation_string":"IIIT Allahabad, IN","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057674832","display_name":"G C Nandi","orcid":"https://orcid.org/0000-0002-3788-3834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G C Nandi","raw_affiliation_strings":["IIIT Allahabad, IN"],"raw_orcid":"https://orcid.org/0000-0002-3788-3834","affiliations":[{"raw_affiliation_string":"IIIT Allahabad, IN","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24442328,"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":"7"},"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":0.9997000098228455,"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":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network 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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.685392439365387},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6205813884735107},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6072449684143066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5904743671417236},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5622807145118713},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5124900341033936},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.48226219415664673},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4270312786102295},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.1305682361125946},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10245120525360107},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06008034944534302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685392439365387},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6205813884735107},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6072449684143066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5904743671417236},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5622807145118713},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5124900341033936},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.48226219415664673},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4270312786102295},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.1305682361125946},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10245120525360107},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06008034944534302},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627631.3627634","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627631.3627634","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627631.3627634","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3627631.3627634","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627631.3627634","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3627631.3627634","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391408865.pdf","grobid_xml":"https://content.openalex.org/works/W4391408865.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1686810756","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2171943915","https://openalex.org/W2559655401","https://openalex.org/W2605572715","https://openalex.org/W2609883120","https://openalex.org/W2793404847","https://openalex.org/W2798441115","https://openalex.org/W2885093229","https://openalex.org/W2937261546","https://openalex.org/W2961433270","https://openalex.org/W2963881378","https://openalex.org/W2964014680","https://openalex.org/W2964309882","https://openalex.org/W3035339581","https://openalex.org/W3121611132","https://openalex.org/W3129840128","https://openalex.org/W3160695845","https://openalex.org/W3177791215","https://openalex.org/W4224706184","https://openalex.org/W4301409532","https://openalex.org/W6811448375","https://openalex.org/W6843438455","https://openalex.org/W6922057760"],"related_works":["https://openalex.org/W200819717","https://openalex.org/W2032269556","https://openalex.org/W2944448661","https://openalex.org/W2064421702","https://openalex.org/W1991834176","https://openalex.org/W4253756925","https://openalex.org/W2805523177","https://openalex.org/W2131956013","https://openalex.org/W4381188157","https://openalex.org/W2036566443"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,14,33,77,96,123,170],"effectively":[3],"interact":[4],"with":[5,89],"its":[6,175],"environment,":[7],"an":[8,61],"agent":[9],"must":[10],"possess":[11],"the":[12,16,19,58,90,106,110,113,155,195],"ability":[13],"comprehend":[15],"\u2019what\u2019":[17],"and":[18,27,48,159,187],"\u2019where.\u2019":[20],"Two":[21],"vision-based":[22],"approaches,":[23],"namely":[24],"semantic":[25],"segmentation":[26],"depth":[28],"estimation,":[29],"can":[30],"be":[31,78],"employed":[32],"provide":[34],"this":[35,179],"information.":[36],"This":[37],"paper":[38],"introduces":[39],"a":[40,50,66,82],"unified":[41],"model":[42,59,114,180],"that":[43],"combines":[44],"these":[45],"two":[46],"tasks":[47,167],"utilizes":[49],"shared":[51,111],"latent":[52],"space.":[53],"The":[54,148],"chosen":[55],"approach":[56],"for":[57,100,141,184,192],"involves":[60],"encoder-decoder":[62],"architecture":[63],"accompanied":[64],"by":[65],"novel":[67],"attention":[68,92,143],"gate":[69],"mechanism":[70],"called":[71],"MMAG,":[72],"which":[73],"has":[74,151,188],"been":[75,152],"proven":[76],"highly":[79],"effective.":[80],"Furthermore,":[81],"common":[83],"skip":[84],"connection":[85],"method,":[86],"in":[87],"conjunction":[88],"proposed":[91],"gate,":[93],"is":[94,115,181],"included":[95],"emphasize":[97],"crucial":[98],"features":[99],"both":[101,166],"prediction":[102],"purposes.":[103],"By":[104],"leveraging":[105],"complementary":[107],"information":[108],"within":[109],"representations,":[112],"capable":[116],"of":[117],"generating":[118],"more":[119],"accurate":[120],"predictions":[121],"compared":[122,169],"other":[124,171],"joint-prediction":[125],"models,":[126],"all":[127],"while":[128],"utilizing":[129],"fewer":[130],"network":[131],"parameters.":[132],"To":[133],"enhance":[134],"performance,":[135],"dilated":[136],"layers":[137],"are":[138],"incorporated,":[139],"allowing":[140],"focused":[142],"through":[144],"different":[145],"receptive":[146],"fields.":[147],"model\u2019s":[149],"performance":[150],"evaluated":[153],"on":[154,165,194],"NYU":[156],"Depth":[157],"v2":[158],"Camvid":[160],"datasets,":[161],"demonstrating":[162],"improved":[163],"results":[164],"when":[168],"state-of-the-art":[172],"models.":[173],"With":[174],"reduced":[176],"parameter":[177],"count,":[178],"particularly":[182],"suitable":[183],"low-cost":[185],"robots":[186],"undergone":[189],"successful":[190],"testing":[191],"inference":[193],"LoCoBot":[196],"robot.":[197]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}