{"id":"https://openalex.org/W4405785455","doi":"https://doi.org/10.1109/iros58592.2024.10802583","title":"How Physics and Background Attributes Impact Video Transformers in Robotic Manipulation: A Case Study on Planar Pushing","display_name":"How Physics and Background Attributes Impact Video Transformers in Robotic Manipulation: A Case Study on Planar Pushing","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785455","doi":"https://doi.org/10.1109/iros58592.2024.10802583"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5023878608","display_name":"Shutong Jin","orcid":"https://orcid.org/0000-0003-0611-4239"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Shutong Jin","raw_affiliation_strings":["KTH Royal Institute of Technology,School of Electrical Engineering and Computer Science"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,School of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100730180","display_name":"Ruiyu Wang","orcid":"https://orcid.org/0000-0002-0242-1488"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ruiyu Wang","raw_affiliation_strings":["KTH Royal Institute of Technology,School of Electrical Engineering and Computer Science"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,School of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012726923","display_name":"Muhammad Zahid","orcid":"https://orcid.org/0000-0003-4143-4692"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Muhammad Zahid","raw_affiliation_strings":["KTH Royal Institute of Technology,School of Electrical Engineering and Computer Science"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,School of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018027629","display_name":"Florian T. Pokorny","orcid":"https://orcid.org/0000-0003-1114-6040"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Florian T. Pokorny","raw_affiliation_strings":["KTH Royal Institute of Technology,School of Electrical Engineering and Computer Science"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,School of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023878608"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.3488,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63459644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7391","last_page":"7398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11301","display_name":"Advanced Surface Polishing Techniques","score":0.9609000086784363,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.9581000208854675,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/planar","display_name":"Planar","score":0.6780074238777161},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.575171172618866},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.5505580306053162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46180716156959534},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3508176803588867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34272557497024536},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32035040855407715},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09144312143325806}],"concepts":[{"id":"https://openalex.org/C134786449","wikidata":"https://www.wikidata.org/wiki/Q3391255","display_name":"Planar","level":2,"score":0.6780074238777161},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.575171172618866},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.5505580306053162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46180716156959534},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3508176803588867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34272557497024536},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32035040855407715},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09144312143325806},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W2898200825","https://openalex.org/W2962711930","https://openalex.org/W2963341956","https://openalex.org/W3007769740","https://openalex.org/W3131500599","https://openalex.org/W3133428285","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3152331843","https://openalex.org/W3167536469","https://openalex.org/W3199332348","https://openalex.org/W3207758636","https://openalex.org/W3210279979","https://openalex.org/W4206706211","https://openalex.org/W4214612132","https://openalex.org/W4312478760","https://openalex.org/W4312560592","https://openalex.org/W4312847199","https://openalex.org/W4312876407","https://openalex.org/W4383108856","https://openalex.org/W4385430679","https://openalex.org/W4386083067","https://openalex.org/W4389666747","https://openalex.org/W4390872546","https://openalex.org/W4401415336","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6750355821","https://openalex.org/W6755243447","https://openalex.org/W6759534164","https://openalex.org/W6771750343","https://openalex.org/W6772383348","https://openalex.org/W6776048684","https://openalex.org/W6776601253","https://openalex.org/W6780340834","https://openalex.org/W6784333009","https://openalex.org/W6784556858","https://openalex.org/W6788811087","https://openalex.org/W6796289742","https://openalex.org/W6797263693","https://openalex.org/W6799150178","https://openalex.org/W6801395018","https://openalex.org/W6801810553","https://openalex.org/W6802366246","https://openalex.org/W6803464670","https://openalex.org/W6805147364","https://openalex.org/W6810264703","https://openalex.org/W6810265253","https://openalex.org/W6810745647","https://openalex.org/W6838638105","https://openalex.org/W6838931476","https://openalex.org/W6840873177","https://openalex.org/W6843759960","https://openalex.org/W6850343319","https://openalex.org/W6854077547","https://openalex.org/W6854738657","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"As":[0],"model":[1,24,35,90,102],"and":[2,18,34,50,58,85,134,146,179],"dataset":[3,22,130,178],"sizes":[4],"continue":[5],"to":[6,13,29,101,111,114],"scale":[7],"in":[8,71,96],"robot":[9,128],"learning,":[10],"the":[11,16,56,66,171],"need":[12],"understand":[14],"how":[15,43],"composition":[17],"properties":[19],"of":[20,60,68,94,106,137,167,173],"a":[21,124,156],"affect":[23],"performance":[25,67],"becomes":[26],"increasingly":[27],"urgent":[28],"ensure":[30],"cost-effective":[31],"data":[32,108],"collection":[33],"performance.":[36],"In":[37],"this":[38,119],"work,":[39],"we":[40,121],"empirically":[41],"investigate":[42,77],"physics":[44,83,145],"attributes":[45,84,97],"(color,":[46],"friction":[47],"coefficient,":[48],"shape)":[49],"scene":[51,87],"background":[52,63,86,147],"characteristics,":[53],"such":[54],"as":[55,170],"complexity":[57],"dynamics":[59],"interactions":[61,140],"with":[62,141,143],"objects,":[64],"influence":[65,89],"Video":[69,152],"Transformers":[70],"predicting":[72],"planar":[73,138],"pushing":[74,129,139],"trajectories.":[75],"We":[76,149],"three":[78],"primary":[79],"questions:":[80],"How":[81],"do":[82],"characteristics":[88],"performance?":[91],"What":[92,104],"kind":[93],"changes":[95],"are":[98,182],"most":[99],"detrimental":[100],"generalization?":[103],"proportion":[105],"fine-tuning":[107],"is":[109],"required":[110],"adapt":[112],"models":[113],"novel":[115],"scenarios?":[116],"To":[117],"facilitate":[118],"research,":[120],"present":[122],"CloudGripper-Push-1K,":[123],"large":[125],"real-world":[126],"vision-based":[127],"comprising":[131],"1278":[132],"hours":[133],"460,000":[135],"videos":[136],"objects":[142],"different":[144],"attributes.":[148],"also":[150],"propose":[151],"Occlusion":[153],"Transformer":[154],"(VOT),":[155],"generic":[157],"modular":[158],"video-transformer-based":[159],"trajectory":[160],"prediction":[161],"framework":[162],"which":[163],"features":[164],"3":[165],"choices":[166],"2D-spatial":[168],"encoders":[169],"subject":[172],"our":[174],"case":[175],"study.":[176],"The":[177],"source":[180],"code":[181],"available":[183],"at":[184],"https://cloudgripper.org.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}