English
Related papers

Related papers: SIGMA: Sinkhorn-Guided Masked Video Modeling

200 papers

Time series analysis is widely used in extensive areas. Recently, to reduce labeling expenses and benefit various tasks, self-supervised pre-training has attracted immense interest. One mainstream paradigm is masked modeling, which…

Machine Learning · Computer Science 2023-10-24 Jiaxiang Dong , Haixu Wu , Haoran Zhang , Li Zhang , Jianmin Wang , Mingsheng Long

Training visual embeddings with labeled data supervision has been the de facto setup for representation learning in computer vision. Inspired by recent success of adopting masked image modeling (MIM) in self-supervised representation…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Kaifeng Chen , Daniel Salz , Huiwen Chang , Kihyuk Sohn , Dilip Krishnan , Mojtaba Seyedhosseini

Training models to apply linguistic knowledge and visual concepts from 2D images to 3D world understanding is a promising direction that researchers have only recently started to explore. In this work, we design a novel 3D pre-training…

Computer Vision and Pattern Recognition · Computer Science 2023-04-14 Maria Parelli , Alexandros Delitzas , Nikolas Hars , Georgios Vlassis , Sotirios Anagnostidis , Gregor Bachmann , Thomas Hofmann

Traditional human vision-centric image compression methods are suboptimal for machine vision centric compression due to different visual properties and feature characteristics. To address this problem, we propose a Channel Importance-driven…

Image and Video Processing · Electrical Eng. & Systems 2026-04-08 Yun Zhang , Junle Liu , Huan Zhang , Zhaoqing Pan , Gangyi Jiang , Weisi Lin

Pre-training has become a standard paradigm in many computer vision tasks. However, most of the methods are generally designed on the RGB image domain. Due to the discrepancy between the two-dimensional image plane and the three-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2022-01-19 Zhenyu Li , Zehui Chen , Ang Li , Liangji Fang , Qinhong Jiang , Xianming Liu , Junjun Jiang , Bolei Zhou , Hang Zhao

Instruction following is crucial in contemporary LLM. However, when extended to multimodal setting, it often suffers from misalignment between specific textual instruction and targeted local region of an image. To achieve more accurate and…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Jinliang Zheng , Jianxiong Li , Sijie Cheng , Yinan Zheng , Jiaming Li , Jihao Liu , Yu Liu , Jingjing Liu , Xianyuan Zhan

This paper tries to address a fundamental question in point cloud self-supervised learning: what is a good signal we should leverage to learn features from point clouds without annotations? To answer that, we introduce a point cloud…

Computer Vision and Pattern Recognition · Computer Science 2023-05-16 Xiaoyu Tian , Haoxi Ran , Yue Wang , Hang Zhao

Vehicle-centric perception plays a crucial role in many intelligent systems, including large-scale surveillance systems, intelligent transportation, and autonomous driving. Existing approaches lack effective learning of vehicle-related…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Wentao Wu , Xiao Wang , Chenglong Li , Jin Tang , Bin Luo

Video prediction is a challenging task. The quality of video frames from current state-of-the-art (SOTA) generative models tends to be poor and generalization beyond the training data is difficult. Furthermore, existing prediction…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Vikram Voleti , Alexia Jolicoeur-Martineau , Christopher Pal

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…

Computer Vision and Pattern Recognition · Computer Science 2024-05-14 Zuan Gao , Yuxin Wang , Yadong Qu , Boqiang Zhang , Zixiao Wang , Jianjun Xu , Hongtao Xie

Pre-training video transformers on extra large-scale datasets is generally required to achieve premier performance on relatively small datasets. In this paper, we show that video masked autoencoders (VideoMAE) are data-efficient learners…

Computer Vision and Pattern Recognition · Computer Science 2022-10-19 Zhan Tong , Yibing Song , Jue Wang , Limin Wang

Learning meaningful visual representations in an embedding space can facilitate generalization in downstream tasks such as action segmentation and imitation. In this paper, we learn a motion-centric representation of surgical video…

Robotics · Computer Science 2020-06-02 Ajay Kumar Tanwani , Pierre Sermanet , Andy Yan , Raghav Anand , Mariano Phielipp , Ken Goldberg

Vision Foundation Models (VFMs) have demonstrated impressive representational capabilities. However, adapting them to downstream tasks via full fine-tuning incurs prohibitive computational and storage overhead. Parameter-Efficient…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Lingyu Xiong , Jinjin Shi , Xuran Xu , Cong Luo , Runyu Shi , Ying Huang

Video recognition models have progressed significantly over the past few years, evolving from shallow classifiers trained on hand-crafted features to deep spatiotemporal networks. However, labeled video data required to train such models…

Computer Vision and Pattern Recognition · Computer Science 2019-08-21 Rohit Girdhar , Du Tran , Lorenzo Torresani , Deva Ramanan

In contrast to single-skill tasks, long-horizon tasks play a crucial role in our daily life, e.g., a pouring task requires a proper concatenation of reaching, grasping and pouring subtasks. As an efficient solution for transferring human…

Robotics · Computer Science 2024-10-03 Shaokang Wu , Yijin Wang , Yanlong Huang

We propose a self-supervised learning method to jointly reason about spatial and temporal context for video recognition. Recent self-supervised approaches have used spatial context [9, 34] as well as temporal coherency [32] but a…

Computer Vision and Pattern Recognition · Computer Science 2018-08-24 Unaiza Ahsan , Rishi Madhok , Irfan Essa

Purpose: To systematically investigate the influence of various data consistency layers, (semi-)supervised learning and ensembling strategies, defined in a $\Sigma$-net, for accelerated parallel MR image reconstruction using deep learning.…

Image and Video Processing · Electrical Eng. & Systems 2019-12-20 Kerstin Hammernik , Jo Schlemper , Chen Qin , Jinming Duan , Ronald M. Summers , Daniel Rueckert

An increasing variety of AI accelerators is being considered for large-scale training. However, enabling large-scale training on early-life AI accelerators faces three core challenges: frequent system disruptions and undefined failure modes…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-16 Lei Qu , Lianhai Ren , Peng Cheng , Rui Gao , Ruizhe Wang , Tianyu Chen , Xiao Liu , Xingjian Zhang , Yeyun Gong , Yifan Xiong , Yucheng Ding , Yuting Jiang , Zhenghao Lin , Zhongxin Guo , Ziyue Yang

Multi-Modal Self-Supervised Learning from videos has been shown to improve model's performance on various downstream tasks. However, such Self-Supervised pre-training requires large batch sizes and a large amount of computation resources…

Computer Vision and Pattern Recognition · Computer Science 2021-12-24 Duo Wang , Salah Karout

Data-driven approaches to assist operating room (OR) workflow analysis depend on large curated datasets that are time consuming and expensive to collect. On the other hand, we see a recent paradigm shift from supervised learning to…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Muhammad Abdullah Jamal , Omid Mohareri