Time Is MattEr: Temporal Self-supervision for Video Transformers

Time Is MattEr: Temporal Self-supervision for Video Transformers

International Conference on Machine Learning (ICML), 2022

19 July 2022

ArXiv (abs)PDF HTML

Papers citing "Time Is MattEr: Temporal Self-supervision for Video Transformers"

6 / 6 papers shown

Title
Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening Piyush Bagad Andrew Zisserman AI4TS 200 2 0 10 Sep 2025
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy Xiang Li Cristina Mata J. Park Kumara Kahatapitiya Yoo Sung Jang ... Kanchana Ranasinghe R. Burgert Mu Cai Yong Jae Lee Michael S. Ryoo LM&Ro 519 54 0 28 Jun 2024
Learning to Exploit Temporal Structure for Biomedical Vision-Language ProcessingComputer Vision and Pattern Recognition (CVPR), 2023 Shruthi Bannur Stephanie L. Hyland Qianchu Liu Fernando Pérez-García Maximilian Ilse ... Maria T. A. Wetscherek M. Lungren A. Nori Javier Alvarez-Valle Ozan Oktay 293 194 0 11 Jan 2023
Mitigating and Evaluating Static Bias of Action Representations in the Background and the ForegroundIEEE International Conference on Computer Vision (ICCV), 2022 Haoxin Li Yuan Liu Hanwang Zhang Boyang Li 217 22 0 23 Nov 2022
Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization TasksComputer Vision and Pattern Recognition (CVPR), 2022 Hyolim Kang Hanjung Kim Joungbin An Minsu Cho Seon Joo Kim 236 7 0 11 Nov 2022
Video Transformers: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 Javier Selva A. S. Johansen Sergio Escalera Kamal Nasrollahi T. Moeslund Albert Clapés ViT 382 134 0 16 Jan 2022