English
Related papers

Related papers: It Takes Two: Masked Appearance-Motion Modeling fo…

200 papers

In this work, we introduce long-video masked-embedding autoencoders (LV-MAE), a self-supervised learning framework for long video representation. Our approach treats short- and long-span dependencies as two separate tasks. Such decoupling…

Computer Vision and Pattern Recognition · Computer Science 2025-10-08 Ilan Naiman , Emanuel Ben-Baruch , Oron Anschel , Alon Shoshan , Igor Kviatkovsky , Manoj Aggarwal , Gerard Medioni

We present a new pre-training strategy called M$^{3}$3D ($\underline{M}$ulti-$\underline{M}$odal $\underline{M}$asked $\underline{3D}$) built based on Multi-modal masked autoencoders that can leverage 3D priors and learned cross-modal…

Computer Vision and Pattern Recognition · Computer Science 2023-09-28 Muhammad Abdullah Jamal , Omid Mohareri

We present Masked Feature Prediction (MaskFeat) for self-supervised pre-training of video models. Our approach first randomly masks out a portion of the input sequence and then predicts the feature of the masked regions. We study five…

Computer Vision and Pattern Recognition · Computer Science 2023-01-13 Chen Wei , Haoqi Fan , Saining Xie , Chao-Yuan Wu , Alan Yuille , Christoph Feichtenhofer

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

Pre-training video transformers generally requires a large amount of data, presenting significant challenges in terms of data collection costs and concerns related to privacy, licensing, and inherent biases. Synthesizing data is one of the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Yuchi Ishikawa , Masayoshi Kondo , Yoshimitsu Aoki

Masked Autoencoders is a simple yet powerful self-supervised learning method. However, it learns representations indirectly by reconstructing masked input patches. Several methods learn representations directly by predicting representations…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-03 Daisuke Niizumi , Daiki Takeuchi , Yasunori Ohishi , Noboru Harada , Kunio Kashino

In this paper, we present StrucTexTv2, an effective document image pre-training framework, by performing masked visual-textual prediction. It consists of two self-supervised pre-training tasks: masked image modeling and masked language…

Computer Vision and Pattern Recognition · Computer Science 2023-03-02 Yuechen Yu , Yulin Li , Chengquan Zhang , Xiaoqiang Zhang , Zengyuan Guo , Xiameng Qin , Kun Yao , Junyu Han , Errui Ding , Jingdong Wang

Videos captured from multiple viewpoints can help in perceiving the 3D structure of the world and benefit computer vision tasks such as action recognition, tracking, etc. In this paper, we present a method for self-supervised learning from…

Computer Vision and Pattern Recognition · Computer Science 2024-01-30 Ketul Shah , Robert Crandall , Jie Xu , Peng Zhou , Marian George , Mayank Bansal , Rama Chellappa

Masked video modeling (MVM) has emerged as a simple and scalable self-supervised pretraining paradigm, but only encodes motion information implicitly, limiting the encoding of temporal dynamics in the learned representations. As a result,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Renaud Vandeghen , Fida Mohammad Thoker , Marc Van Droogenbroeck , Bernard Ghanem

Video representation learning has seen tremendous progress in recent years. This has been driven by many factors, including the scale of training and the success of visual models trained contrastively with language. While these factors have…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Mantas Skackauskas , Xinyue Hao , Laura Sevilla-Lara

Learning representations from videos requires understanding continuous motion and visual correspondences between frames. In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Zhouqiang Jiang , Bowen Wang , Tong Xiang , Zhaofeng Niu , Hong Tang , Guangshun Li , Liangzhi Li

Masked Autoencoders (MAEs) learn generalizable representations for image, text, audio, video, etc., by reconstructing masked input data from tokens of the visible data. Current MAE approaches for videos rely on random patch, tube, or…

Computer Vision and Pattern Recognition · Computer Science 2022-11-17 Wele Gedara Chaminda Bandara , Naman Patel , Ali Gholami , Mehdi Nikkhah , Motilal Agrawal , Vishal M. Patel

Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to perceive the world from 2D images. However, to more effectively understand 3D structural priors in 2D backbones, we propose Mask3D to…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Ji Hou , Xiaoliang Dai , Zijian He , Angela Dai , Matthias Nießner

Masked Autoencoders (MAE) have been popular paradigms for large-scale vision representation pre-training. However, MAE solely reconstructs the low-level RGB signals after the decoder and lacks supervision upon high-level semantics for the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-10 Peng Gao , Renrui Zhang , Rongyao Fang , Ziyi Lin , Hongyang Li , Hongsheng Li , Qiao Yu

Video understanding has witnessed significant progress with recent video foundation models demonstrating strong performance owing to self-supervised pre-training objectives; Masked Autoencoders (MAE) being the design of choice.…

We present a mask-piloted Transformer which improves masked-attention in Mask2Former for image segmentation. The improvement is based on our observation that Mask2Former suffers from inconsistent mask predictions between consecutive decoder…

Computer Vision and Pattern Recognition · Computer Science 2023-03-16 Hao Zhang , Feng Li , Huaizhe Xu , Shijia Huang , Shilong Liu , Lionel M. Ni , Lei Zhang

Can we leverage the audiovisual information already present in video to improve self-supervised representation learning? To answer this question, we study various pretraining architectures and objectives within the masked autoencoding…

Computer Vision and Pattern Recognition · Computer Science 2024-01-05 Mariana-Iuliana Georgescu , Eduardo Fonseca , Radu Tudor Ionescu , Mario Lucic , Cordelia Schmid , Anurag Arnab

We propose an efficient approach to train large diffusion models with masked transformers. While masked transformers have been extensively explored for representation learning, their application to generative learning is less explored in…

Computer Vision and Pattern Recognition · Computer Science 2024-03-06 Hongkai Zheng , Weili Nie , Arash Vahdat , Anima Anandkumar

Vision transformer based models bring significant improvements for image segmentation tasks. Although these architectures offer powerful capabilities irrespective of specific segmentation tasks, their use of computational resources can be…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Manyi Yao , Abhishek Aich , Yumin Suh , Amit Roy-Chowdhury , Christian Shelton , Manmohan Chandraker

Video understanding relies on perceiving the global content and modeling its internal connections (e.g., causality, movement, and spatio-temporal correspondence). To learn these interactions, we apply a mask-then-predict pre-training task…

Computer Vision and Pattern Recognition · Computer Science 2021-06-22 Hao Tan , Jie Lei , Thomas Wolf , Mohit Bansal