Stochastic Backpropagation: A Memory Efficient Strategy for Training
Video Models

Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models

Computer Vision and Pattern Recognition (CVPR), 2022

31 March 2022

ArXiv (abs)PDF HTML

Papers citing "Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models"

16 / 16 papers shown

Title
SUS backprop: linear backpropagation algorithm for long inputs in transformers Sergey Pankov Georges Harik 238 0 0 21 May 2025
Beyond the Horizon: Decoupling Multi-View UAV Action Recognition via Partial Order Transfer Wenxuan Liu Zhuo Zhou Zhuo Zhou Shangshang Yang Wenxin Huang Alex Chichung Kot Chia-Wen Lin 167 0 0 29 Apr 2025
SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding Mingze Xu Mingfei Gao Shiyu Li Jiasen Lu Zhe Gan Zhengfeng Lai Meng Cao Kai Kang Yue Yang Afshin Dehghan 346 13 0 24 Mar 2025
SnAG: Scalable and Accurate Video GroundingComputer Vision and Pattern Recognition (CVPR), 2024 Fangzhou Mu Sicheng Mo Yin Li 221 24 0 02 Apr 2024
LoSA: Long-Short-range Adapter for Scaling End-to-End Temporal Action Localization Akshita Gupta Gaurav Mittal Ahmed Magooda Ye Yu Graham W. Taylor Mei Chen 287 3 0 01 Apr 2024
End-to-End Temporal Action Detection with 1B Parameters Across 1000 FramesComputer Vision and Pattern Recognition (CVPR), 2023 Shuming Liu Chen-Da Liu-Zhang Chen Zhao Guohao Li 300 45 0 28 Nov 2023
Training a Large Video Model on a Single Machine in a Day Yue Zhao Philipp Krahenbuhl VLM 209 22 0 28 Sep 2023
End-to-End Streaming Video Temporal Action Segmentation with Reinforce LearningIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023 Jinrong Zhang Wu Wen Sheng-lan Liu Yunheng Li Qifeng Li Lin Feng 286 0 0 27 Sep 2023
Uncovering the Unseen: Discover Hidden Intentions by Micro-Behavior Graph ReasoningACM Multimedia (ACM MM), 2023 Zhuo Zhou Wenxuan Liu Danni Xu Zheng Wang Jian Zhao 169 9 0 29 Aug 2023
To Adapt or Not to Adapt? Real-Time Adaptation for Semantic SegmentationIEEE International Conference on Computer Vision (ICCV), 2023 Marc Botet Colomer Pier Luigi Dovesi Theodoros Panagiotakopoulos J. Carvalho Linus Harenstam-Nielsen Hossein Azizpour Hedvig Kjellström Zorah Lähner Matteo Poggi TTA 165 17 0 27 Jul 2023
E2E-LOAD: End-to-End Long-form Online Action DetectionIEEE International Conference on Computer Vision (ICCV), 2023 Shuyuan Cao Weihua Luo Bairui Wang Wei Emma Zhang Lin Ma 155 12 0 13 Jun 2023
An In-depth Study of Stochastic BackpropagationNeural Information Processing Systems (NeurIPS), 2022 J. Fang Ming Xu Hao Chen Bing Shuai Zhuowen Tu Joseph Tighe BDL 129 2 0 30 Sep 2022
MS-RNN: A Flexible Multi-Scale Framework for Spatiotemporal Predictive Learning Zhifeng Ma Hao Zhang Jie Liu HAI AI4CE 474 13 0 07 Jun 2022
ETAD: Training Action Detection End to End on a Laptop Shuming Liu Mengmeng Xu Chen Zhao Xu Zhao Guohao Li 156 9 0 14 May 2022
TALLFormer: Temporal Action Localization with a Long-memory TransformerEuropean Conference on Computer Vision (ECCV), 2022 Feng Cheng Gedas Bertasius ViT 225 115 0 04 Apr 2022
DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN TrainingInternational Conference on Learning Representations (ICLR), 2022 Joya Chen Kai Xu Yuhui Wang Yifei Cheng Angela Yao 209 8 0 28 Feb 2022