{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:24:01Z","timestamp":1777890241629,"version":"3.51.4"},"reference-count":65,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01358","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14633-14643","source":"Crossref","is-referenced-by-count":0,"title":["DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understanding"],"prefix":"10.1109","author":[{"given":"Thomas","family":"Kreutz","sequence":"first","affiliation":[{"name":"Technical University Darmstadt,Telekooperation Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max","family":"M\u00fchlh\u00e4user","sequence":"additional","affiliation":[{"name":"Technical University Darmstadt,Telekooperation Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alejandro Sanchez","family":"Guinea","sequence":"additional","affiliation":[{"name":"Technical University Darmstadt,Telekooperation Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2974928"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SECON55815.2022.9918171"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.883"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00199"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/s20092576"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3529190.3534728"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01861"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681055"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01985"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3247088"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref13","author":"Dai","year":"2024","journal-title":"Advancing multi\u2013modal sensing through expandable modality alignment"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00158"},{"key":"ref16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref17","author":"Oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543273"},{"key":"ref20","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref21","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/wacv48630.2021.00381"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01514"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00123"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_24"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01520"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01694"},{"key":"ref29","article-title":"Cooperative learning of audio and video models from self\u2013supervised synchronization","volume":"31","author":"Korbar","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01246"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2024.3422844"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0822"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3402952"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275108"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.14"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3218373"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3161735"},{"key":"ref43","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref46","author":"Kingma","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"ref47","author":"Ruder","year":"2016","journal-title":"An overview of gradient descent optimization algorithms"},{"key":"ref48","article-title":"Pvnext: Rethinking network design and temporal motion for point cloud video recognition","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wang","year":"2025"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01642"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889324"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00934"},{"key":"ref52","article-title":"Pstnet: Point spatio\u2013temporal convolution on point cloud sequences","volume-title":"International Conference on Learning Representations","author":"Fan","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01398"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00832"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_2"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3135117"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00062"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref61","author":"Li","year":"2022","journal-title":"Uniformer: Unified transformer for efficient spatiotemporal representation learning"},{"issue":"11","key":"ref62","article-title":"Visualizing data using t\u2013sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00199"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445690.pdf?arnumber=11445690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:31Z","timestamp":1777613551000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445690\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01358","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}