{"id":"https://openalex.org/W4415269727","doi":"https://doi.org/10.48550/arxiv.2510.12160","title":"State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding","display_name":"State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W4415269727","doi":"https://doi.org/10.48550/arxiv.2510.12160"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.12160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.12160","pdf_url":"https://arxiv.org/pdf/2510.12160","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.12160","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055004003","display_name":"Jiahuan Zhou","orcid":"https://orcid.org/0000-0002-3301-747X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhou, Jiahuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040938127","display_name":"Kai Zhu","orcid":"https://orcid.org/0000-0002-9451-0890"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Kai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101909436","display_name":"Zhenyu Cui","orcid":"https://orcid.org/0000-0001-5078-717X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Zhenyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101818312","display_name":"Zichen Liu","orcid":"https://orcid.org/0009-0009-1093-9744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zichen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110378924","display_name":"Xu Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081114810","display_name":"Gang Hua","orcid":"https://orcid.org/0000-0001-9522-6157"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hua, Gang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5055004003"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.987500011920929,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.987500011920929,"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":0.9829000234603882,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9805999994277954,"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/discriminative-model","display_name":"Discriminative model","score":0.8510000109672546},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6223999857902527},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5073999762535095},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5062000155448914},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4991999864578247},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4950000047683716},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4894999861717224},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.44679999351501465},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.44110000133514404}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8510000109672546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8069000244140625},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6223999857902527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5698999762535095},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5073999762535095},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4991999864578247},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4950000047683716},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4894999861717224},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.44110000133514404},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4293999969959259},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.412200003862381},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.3003000020980835},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29170000553131104},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2547000050544739},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.12160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.12160","pdf_url":"https://arxiv.org/pdf/2510.12160","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.12160","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.12160","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.12160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.12160","pdf_url":"https://arxiv.org/pdf/2510.12160","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4415269727.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"pre-trained":[1,37],"state":[2,98],"space":[3],"models":[4,38],"have":[5],"shown":[6],"great":[7],"potential":[8],"for":[9,120],"video":[10,28,89,121,199],"classification,":[11],"which":[12,123],"sequentially":[13,62],"compresses":[14],"visual":[15,64],"tokens":[16,66],"in":[17,76,96,136,189,191],"videos":[18,190],"with":[19,52],"linear":[20],"complexity,":[21],"thereby":[22],"improving":[23],"the":[24,61,70,77,81,97,102,109,137,217],"processing":[25],"efficiency":[26],"of":[27,57,84,104,219],"data":[29],"while":[30,215],"maintaining":[31],"high":[32],"performance.":[33],"To":[34,107],"apply":[35],"powerful":[36],"to":[39,46,68,129,147,163],"downstream":[40,49],"tasks,":[41],"prompt":[42,65],"learning":[43],"is":[44,145,161],"proposed":[45,113],"achieve":[47],"efficient":[48],"task":[50],"adaptation":[51],"only":[53],"a":[54,88,114,192],"small":[55],"number":[56],"fine-tuned":[58],"parameters.":[59,221],"However,":[60],"compressed":[63],"fail":[67],"capture":[69],"spatial":[71,85,149],"and":[72,91,101,126,131,174,180],"temporal":[73,92],"contextual":[74],"information":[75,86,93,135,151,167,178,188],"video,":[78],"thus":[79],"limiting":[80],"effective":[82],"propagation":[83],"within":[87,152,179],"frame":[90],"between":[94,181],"frames":[95],"compression":[99],"model":[100],"extraction":[103],"discriminative":[105,165,187],"information.":[106],"tackle":[108],"above":[110],"issue,":[111],"we":[112],"State":[115],"Space":[116],"Prompting":[117],"(SSP)":[118],"method":[119],"understanding,":[122],"combines":[124],"intra-frame":[125],"inter-frame":[127],"prompts":[128],"aggregate":[130,148],"propagate":[132],"key":[133,150,176],"spatiotemporal":[134],"video.":[138],"Specifically,":[139],"an":[140,156],"Intra-Frame":[141],"Gathering":[142],"(IFG)":[143],"module":[144,160],"designed":[146,162],"each":[153],"frame.":[154],"Besides,":[155],"Inter-Frame":[157],"Spreading":[158],"(IFS)":[159],"spread":[164],"spatio-temporal":[166,177],"across":[168],"different":[169],"frames.":[170],"By":[171],"adaptively":[172],"balancing":[173],"compressing":[175],"frames,":[182],"our":[183,204],"SSP":[184,205],"effectively":[185],"propagates":[186],"complementary":[193],"manner.":[194],"Extensive":[195],"experiments":[196],"on":[197,213],"four":[198],"benchmark":[200],"datasets":[201],"verify":[202],"that":[203],"significantly":[206],"outperforms":[207],"existing":[208],"SOTA":[209],"methods":[210],"by":[211],"2.76%":[212],"average":[214],"reducing":[216],"overhead":[218],"fine-tuning":[220]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-17T00:00:00"}