{"id":"https://openalex.org/W4226145338","doi":"https://doi.org/10.1145/3503961.3503972","title":"A Multi-scale Framework for Visual Grounding","display_name":"A Multi-scale Framework for Visual Grounding","publication_year":2021,"publication_date":"2021-11-19","ids":{"openalex":"https://openalex.org/W4226145338","doi":"https://doi.org/10.1145/3503961.3503972"},"language":"en","primary_location":{"id":"doi:10.1145/3503961.3503972","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503961.3503972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 3rd International Conference on Video, Signal and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100701367","display_name":"Baosheng Li","orcid":"https://orcid.org/0000-0001-9952-8312"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baosheng Li","raw_affiliation_strings":["State Grid Shandong Electric Power Company Laiwu Power Supply Company, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Shandong Electric Power Company Laiwu Power Supply Company, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778408","display_name":"Peng Qi","orcid":"https://orcid.org/0000-0002-6458-8320"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Qi","raw_affiliation_strings":["State Grid Shandong Electric Power Company Laiwu Power Supply Company, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Shandong Electric Power Company Laiwu Power Supply Company, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370498","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0002-8376-5898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["State Grid Shandong Electric Power Company Laiwu Power Supply Company, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Shandong Electric Power Company Laiwu Power Supply Company, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114339803","display_name":"Chong Tan","orcid":"https://orcid.org/0009-0002-9606-0456"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Tan","raw_affiliation_strings":["State Grid Shandong Electric Power Company Laiwu Power Supply Company, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Shandong Electric Power Company Laiwu Power Supply Company, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088267238","display_name":"Runze Qi","orcid":"https://orcid.org/0000-0001-6031-2370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Runze Qi","raw_affiliation_strings":["State Grid Shandong Electric Power Company Laiwu Power Supply Company, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Shandong Electric Power Company Laiwu Power Supply Company, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100366453","display_name":"Xiaolei Li","orcid":"https://orcid.org/0000-0001-9848-9200"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolei Li","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.22804216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"69"},"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":0.9994999766349792,"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"}},"topics":[{"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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"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":0.8115357756614685},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6379625797271729},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6156794428825378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5649663805961609},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5605270862579346},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5313209891319275},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5284283757209778},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49539196491241455},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.49437665939331055},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.48391562700271606},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4598369002342224},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41999220848083496},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.371337890625},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3624822497367859},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3448307514190674},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07407015562057495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115357756614685},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6379625797271729},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6156794428825378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5649663805961609},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5605270862579346},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5313209891319275},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5284283757209778},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49539196491241455},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.49437665939331055},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.48391562700271606},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4598369002342224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41999220848083496},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.371337890625},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3624822497367859},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3448307514190674},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07407015562057495},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503961.3503972","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503961.3503972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 3rd International Conference on Video, Signal and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1591801644","https://openalex.org/W2088049833","https://openalex.org/W2102605133","https://openalex.org/W2194775991","https://openalex.org/W2904910963","https://openalex.org/W2952524542","https://openalex.org/W2960655175","https://openalex.org/W2963735856","https://openalex.org/W2963914122","https://openalex.org/W2964276121","https://openalex.org/W2983358816","https://openalex.org/W2984121207","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W3046733348","https://openalex.org/W3100691103","https://openalex.org/W3195968859","https://openalex.org/W4205848079","https://openalex.org/W6628973269","https://openalex.org/W6651868023","https://openalex.org/W6683411478","https://openalex.org/W6691231616","https://openalex.org/W6731892127","https://openalex.org/W6740256410","https://openalex.org/W6750227808","https://openalex.org/W6785652829","https://openalex.org/W6795040662"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Visual":[0],"Grounding":[1],"aims":[2],"to":[3,12,73,85,125],"ground":[4],"the":[5,9,13,17,27,30,35,39,75,94,103,107],"right":[6],"region":[7],"of":[8,63,78,106],"image":[10,36],"according":[11],"query":[14],"that":[15],"describes":[16],"target.":[18],"Generally,":[19],"this":[20,57,100,118,120],"task":[21,43,58],"can":[22],"be":[23],"formalized":[24],"as":[25],"selecting":[26],"target":[28],"with":[29],"highest":[31],"matching":[32,76],"score":[33],"between":[34],"regions":[37],"and":[38,51,113],"language":[40],"queries.":[41],"This":[42],"is":[44,71],"based":[45,81],"on":[46,82,93],"object":[47,108],"detection,":[48],"word":[49,111],"embedding":[50,112],"multi-modal":[52,114],"data":[53,115],"fusion.":[54,116],"At":[55],"present,":[56],"has":[59],"a":[60],"wide":[61],"range":[62],"needs":[64],"in":[65],"real":[66],"life.":[67],"For":[68],"example,":[69],"it":[70],"necessary":[72],"search":[74],"content":[77],"surveillance":[79],"video":[80],"text":[83],"information":[84],"check":[86],"whether":[87],"certain":[88],"violations":[89],"have":[90],"occurred.":[91],"Based":[92],"current":[95],"advanced":[96],"one-stage":[97],"algorithm":[98,104],"ReSC,":[99],"paper":[101,121],"studies":[102],"details":[105],"detection":[109],"algorithm,":[110],"On":[117],"basis,":[119],"exploits":[122],"multi-scale":[123],"features":[124],"improve":[126],"performance.":[127]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
