{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:06:08Z","timestamp":1772906768607,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10826081","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"1909-1918","source":"Crossref","is-referenced-by-count":3,"title":["Animal-JEPA: Advancing Animal Behavior Studies Through Joint Embedding Predictive Architecture in Video Analysis"],"prefix":"10.1109","author":[{"given":"Chengjie","family":"Zheng","sequence":"first","affiliation":[{"name":"University of Massachusetts Boston,Department of Computer Science,Boston,United States"}]},{"given":"Tewodros Mulugeta","family":"Dagnew","sequence":"additional","affiliation":[{"name":"Havard Medical School,Massachusetts General Hospital,Department of Radiology,Boston,United States"}]},{"given":"Liuyue","family":"Yang","sequence":"additional","affiliation":[{"name":"Havard Medical School,Anesthesia, Critical Care and Pain Medicine Massachusetts General Hospital,Boston,United States"}]},{"given":"Wei","family":"Ding","sequence":"additional","affiliation":[{"name":"University of Massachusetts Boston,Department of Computer Science,Boston,United States"}]},{"given":"Shiqian","family":"Shen","sequence":"additional","affiliation":[{"name":"Havard Medical School,Anesthesia, Critical Care and Pain Medicine Massachusetts General Hospital,Boston,United States"}]},{"given":"Changning","family":"Wang","sequence":"additional","affiliation":[{"name":"Havard Medical School,Massachusetts General Hospital,Department of Radiology,Boston,United States"}]},{"given":"Ping","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Massachusetts Boston,Department of Computer Science,Boston,United States"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9781420010749"},{"key":"ref2","first-page":"24261","article-title":"MLP-Mixer: An all-MLP Architecture for Vision","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems (NeurIPS)","author":"Tolstikhin"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref4","first-page":"6816","article-title":"ViViT: A Video Vision Transformer","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Arnab"},{"key":"ref5","first-page":"4219","article-title":"Joint Learning of Salient Object Detection, Depth Estimation, and Image Reconstruction","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhang"},{"key":"ref6","first-page":"1234","article-title":"V-JEPA: Video Joint Embedding Predictive Architecture","volume-title":"*Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Bohnslav"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-022-01443-0"},{"key":"ref8","article-title":"The Kinetics Human Action Video Dataset","author":"Kay","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref10","article-title":"Attention is All You Need","author":"Vaswani","year":"2017"},{"issue":"6","key":"ref11","first-page":"2938","article-title":"Self-Supervised Learning: Generative or Contrastive","volume":"34","author":"He","year":"2022","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1101\/2020.07.26.222299","article-title":"The Mouse Action Recognition System (MARS): a software pipeline for automated analysis of social behaviors in mice","volume-title":"bioRxiv","author":"Segalin","year":"2020"},{"key":"ref13","first-page":"1329","article-title":"Social behavior recognition in continuous video","volume-title":"Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Burgos-Artizzu"},{"key":"ref14","first-page":"108774","article-title":"RatSI: The Rat Social Interaction Dataset for Multi-animal 3D pose estimation and behavior classification","volume":"341","author":"von Ziegler","year":"2020","journal-title":"Journal of Neuroscience Methods"},{"issue":"1","key":"ref15","first-page":"354","article-title":"MouseAcademy: A large-scale dataset for animal behavior and neuroscience research","volume":"7","author":"Geuther","year":"2020","journal-title":"Scientific Data"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-36819-6_22"},{"key":"ref17","first-page":"1","article-title":"Designing animal-friendly behavioral tests for neuroscience research: The importance of an ethological approach","volume":"15","author":"Gerlai","year":"2021","journal-title":"Frontiers in Behavioral Neuroscience"},{"issue":"10","key":"ref18","first-page":"778","article-title":"Advancements in automated classification and analysis in human behavioral studies: Applications and implications for animal behavior research","volume":"69","author":"Willems","year":"2019","journal-title":"Bioscience"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/ani11103003"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00530"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/act10010002"},{"key":"ref22","article-title":"Using the Compresstome\u00ae in Immunotherapy Research","volume-title":"Proceedings of the 2022 Precisionary Instruments Webinar","author":"Wong"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/jzbg2040038"},{"key":"ref24","article-title":"Rethinking the pros and cons of randomized controlled trials and observational studies in the era of big data and advanced methods: a panel discussion","volume-title":"BMC Proceedings","author":"Murray","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.4103\/0974-1208.82352"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1001885"},{"key":"ref27","article-title":"Foundation Models for Video Understanding: A Survey","author":"Qing","year":"2023"},{"key":"ref28","article-title":"FILS: Self-Supervised Video Feature Prediction In Semantic Language Space","author":"Ahmadian","year":"2024"},{"key":"ref29","article-title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","author":"Zhang","year":"2023"},{"key":"ref30","article-title":"Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos","volume-title":"Proceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/electronics7110302"},{"issue":"2","key":"ref32","first-page":"e0263134","article-title":"Instance segmentation convolutional neural network based on multi-scale attention mechanism","volume-title":"PLOS ONE","volume":"16","author":"Zhang","year":"2021"},{"key":"ref33","first-page":"203","article-title":"Siamese Network with Spatio-Temporal Awareness for Object Tracking","volume":"117","author":"He","year":"2021","journal-title":"ScienceDirect"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/electronics7110302"},{"issue":"1","key":"ref35","first-page":"20","article-title":"An improved object detection algorithm based on multi-scaled and deformable convolutional neural networks","volume-title":"Human-centric Computing and Information Sciences","volume":"11","author":"Liu","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00298"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","location":"Washington, DC, USA","start":{"date-parts":[[2024,12,15]]},"end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10826081.pdf?arnumber=10826081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:44:31Z","timestamp":1737099871000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10826081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10826081","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}