{"id":"https://openalex.org/W4417484940","doi":"https://doi.org/10.1109/iccv51701.2025.01918","title":"Towards Video Thinking Test: A Holistic Benchmark for Advanced Video Reasoning and Understanding","display_name":"Towards Video Thinking Test: A Holistic Benchmark for Advanced Video Reasoning and Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417484940","doi":"https://doi.org/10.1109/iccv51701.2025.01918"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.15028","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052895725","display_name":"Yuanhan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuanhan Zhang","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yunice Chew","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yunice Chew","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101838988","display_name":"Yuhao Dong","orcid":"https://orcid.org/0000-0003-0564-4369"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuhao Dong","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077632342","display_name":"A. Lewis Leo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aria Leo","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049438048","display_name":"Bo Hu","orcid":"https://orcid.org/0000-0002-3862-1350"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Hu","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115589625","display_name":"Ziwei Liu","orcid":"https://orcid.org/0009-0005-4275-4710"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ziwei Liu","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20626","last_page":"20636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5221999883651733,"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":0.5221999883651733,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.10859999805688858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.08760000020265579,"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/correctness","display_name":"Correctness","score":0.7865999937057495},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7519000172615051},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6482999920845032},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.5422000288963318},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4390999972820282},{"id":"https://openalex.org/keywords/human-intelligence","display_name":"Human intelligence","score":0.36959999799728394}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7865999937057495},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7519000172615051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390000224113464},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6482999920845032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5957000255584717},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C105409693","wikidata":"https://www.wikidata.org/wiki/Q5937824","display_name":"Human intelligence","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34389999508857727},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2621000111103058},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccv51701.2025.01918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.15028","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15028","pdf_url":"https://arxiv.org/pdf/2507.15028","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.15028","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15028","pdf_url":"https://arxiv.org/pdf/2507.15028","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Human":[0],"intelligence":[1,53],"requires":[2],"correctness":[3,17,56],"and":[4,25,51,57,91,109,116,128],"robustness,":[5],"with":[6,105],"the":[7,12,19,46,64],"former":[8],"being":[9],"foundational":[10],"for":[11],"latter.":[13],"In":[14],"video":[15,36,60,72,126],"understanding,":[16],"ensures":[18],"accurate":[20],"interpretation":[21],"of":[22],"visual":[23,89,115],"content,":[24],"robustness":[26,58,93],"maintains":[27],"consistent":[28],"performance":[29],"in":[30,35,54,59,86],"challenging":[31],"conditions.":[32],"Despite":[33],"advances":[34],"large":[37],"language":[38],"models":[39,50],"(video":[40],"LLMs),":[41],"existing":[42],"benchmarks":[43],"inadequately":[44],"reflect":[45],"gap":[47,124],"between":[48,125],"these":[49],"human":[52,129],"maintaining":[55],"interpretation.":[61],"We":[62],"introduce":[63],"Video":[65],"Thinking":[66],"Test":[67],"(Video-TT),":[68],"to":[69],"assess":[70],"if":[71],"LLMs":[73,127],"can":[74],"interpret":[75],"real-world":[76],"videos":[77],"as":[78,80],"effectively":[79],"humans.":[81],"Video-TT":[82,98],"reflects":[83],"genuine":[84],"gaps":[85],"understanding":[87],"complex":[88],"narratives,":[90],"evaluates":[92],"against":[94],"natural":[95],"adversarial":[96,111],"questions.":[97],"comprises":[99],"1,000":[100],"YouTube":[101],"Shorts":[102],"videos,":[103],"each":[104],"one":[106],"open-ended":[107],"question":[108],"four":[110],"questions":[112],"that":[113],"probe":[114],"narrative":[117],"complexity.":[118],"Our":[119],"evaluation":[120],"shows":[121],"a":[122],"significant":[123],"performance.":[130]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}