English
Related papers

Related papers: Revisiting Feature Prediction for Learning Visual …

200 papers

Annotating videos is cumbersome, expensive and not scalable. Yet, many strong video models still rely on manually annotated data. With the recent introduction of the HowTo100M dataset, narrated videos now offer the possibility of learning…

Computer Vision and Pattern Recognition · Computer Science 2020-08-25 Antoine Miech , Jean-Baptiste Alayrac , Lucas Smaira , Ivan Laptev , Josef Sivic , Andrew Zisserman

Joint-Embedding Predictive Architectures (JEPAs) have recently emerged as a novel and powerful technique for self-supervised representation learning. They aim to learn an energy-based model by predicting the latent representation of a…

Machine Learning · Computer Science 2025-01-22 Geri Skenderi , Hang Li , Jiliang Tang , Marco Cristani

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

We introduce a simple yet effective algorithm that uses convolutional neural networks to directly estimate object poses from videos. Our approach leverages the temporal information from a video sequence, and is computationally efficient and…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Apoorva Beedu , Zhile Ren , Varun Agrawal , Irfan Essa

In this work, we explore the possibility of using synthetically generated data for video-based gesture recognition with large pre-trained models. We consider whether these models have sufficiently robust and expressive representation spaces…

Computer Vision and Pattern Recognition · Computer Science 2024-10-04 Arun Reddy , Ketul Shah , Corban Rivera , William Paul , Celso M. De Melo , Rama Chellappa

We study joint video and language (VL) pre-training to enable cross-modality learning and benefit plentiful downstream VL tasks. Existing works either extract low-quality video features or learn limited text embedding, while neglecting that…

Computer Vision and Pattern Recognition · Computer Science 2022-07-11 Hongwei Xue , Tiankai Hang , Yanhong Zeng , Yuchong Sun , Bei Liu , Huan Yang , Jianlong Fu , Baining Guo

Transfer learning has become an essential tool in modern computer vision, allowing practitioners to leverage backbones, pretrained on large datasets, to train successful models from limited annotated data. Choosing the right backbone is…

Computer Vision and Pattern Recognition · Computer Science 2025-08-20 Joris Guerin , Shray Bansal , Amirreza Shaban , Paulo Mann , Harshvardhan Gazula

Accurately predicting the 3D shape of any arbitrary object in any pose from a single image is a key goal of computer vision research. This is challenging as it requires a model to learn a representation that can infer both the visible and…

Computer Vision and Pattern Recognition · Computer Science 2021-09-03 Anh Thai , Stefan Stojanov , Vijay Upadhya , James M. Rehg

Current video generation models produce high-quality aesthetic videos but often struggle to learn representations of real-world physics dynamics, resulting in artifacts such as unnatural object collisions, inconsistent gravity, and temporal…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Siddarth Nilol Kundur Satish , Devesh Jaiswal , Hongyu Chen , Abhishek Bakshi

Self-supervised learning allows for better utilization of unlabelled data. The feature representation obtained by self-supervision can be used in downstream tasks such as classification, object detection, segmentation, and anomaly…

Computer Vision and Pattern Recognition · Computer Science 2020-06-18 Rabia Ali , Muhammad Umar Karim Khan , Chong Min Kyung

A key challenge in scaling up robot learning to many skills and environments is removing the need for human supervision, so that robots can collect their own data and improve their own performance without being limited by the cost of…

Machine Learning · Computer Science 2017-03-14 Chelsea Finn , Sergey Levine

Building on the Joint-Embedding Predictive Architecture (JEPA) paradigm, a recent self-supervised learning framework that predicts latent representations of masked regions in high-level feature spaces, we propose Audio-JEPA (Audio…

Sound · Computer Science 2025-07-08 Ludovic Tuncay , Etienne Labbé , Emmanouil Benetos , Thomas Pellegrini

Understanding vision and language representations of product content is vital for search and recommendation applications in e-commerce. As a backbone for online shopping platforms and inspired by the recent success in representation…

Machine Learning · Computer Science 2022-08-23 Wonyoung Shin , Jonghun Park , Taekang Woo , Yongwoo Cho , Kwangjin Oh , Hwanjun Song

Current video foundation models, including the strongest self-supervised models such as V-JEPA2, fail to capture how humans organize social information in dynamic scenes. For example, across a range of diverse vision models tested, none…

Neurons and Cognition · Quantitative Biology 2026-05-14 Kathy Garcia , Leyla Isik

Self-supervised learning has emerged as a powerful paradigm for label-free model pretraining, particularly in the video domain, where manual annotation is costly and time-intensive. However, existing self-supervised approaches employ…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Akash Kumar , Ashlesha Kumar , Vibhav Vineet , Yogesh S Rawat

Despite video forecasting has been a widely explored topic in recent years, the mainstream of the existing work still limits their models with a single prediction space but completely neglects the way to leverage their model with…

Computer Vision and Pattern Recognition · Computer Science 2021-07-22 Mengcheng Lan , Shuliang Ning , Yanran Li , Qian Chen , Xunlai Chen , Xiaoguang Han , Shuguang Cui

A core challenge for an agent learning to interact with the world is to predict how its actions affect objects in its environment. Many existing methods for learning the dynamics of physical interactions require labeled object information.…

Machine Learning · Computer Science 2016-10-19 Chelsea Finn , Ian Goodfellow , Sergey Levine

Self-supervised tasks have been utilized to build useful representations that can be used in downstream tasks when the annotation is unavailable. In this paper, we introduce a self-supervised video representation learning method based on…

Computer Vision and Pattern Recognition · Computer Science 2021-02-23 Duc Quang Vu , Ngan T. H. Le , Jia-Ching Wang

Self-supervised feature learning enables perception systems to benefit from the vast raw data recorded by vehicle fleets worldwide. While video-level self-supervised learning approaches have shown strong generalizability on classification…

Computer Vision and Pattern Recognition · Computer Science 2023-11-09 Christopher Lang , Alexander Braun , Lars Schillingmann , Karsten Haug , Abhinav Valada

Current state-of-the-art solutions for motion capture from a single camera are optimization driven: they optimize the parameters of a 3D human model so that its re-projection matches measurements in the video (e.g. person segmentation,…

Computer Vision and Pattern Recognition · Computer Science 2017-12-06 Hsiao-Yu Fish Tung , Hsiao-Wei Tung , Ersin Yumer , Katerina Fragkiadaki