English
Related papers

Related papers: REJEPA: A Novel Joint-Embedding Predictive Archite…

200 papers

Many common methods for learning a world model for pixel-based environments use generative architectures trained with pixel-level reconstruction objectives. Recently proposed Joint Embedding Predictive Architectures (JEPA) offer a…

Machine Learning · Computer Science 2022-11-22 Vlad Sobal , Jyothir S , Siddhartha Jalagam , Nicolas Carion , Kyunghyun Cho , Yann LeCun

Vision-based pose estimation of articulated robots with unknown joint angles has applications in collaborative robotics and human-robot interaction tasks. Current frameworks use neural network encoders to extract image features and…

Robotics · Computer Science 2025-05-05 Raktim Gautam Goswami , Prashanth Krishnamurthy , Yann LeCun , Farshad Khorrami

Remote sensing text--image retrieval (RSTIR) aims to retrieve the matched remote sensing (RS) images from the database according to the descriptive text. Recently, the rapid development of large visual-language pre-training models provides…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Weihang Zhang , Jihao Li , Shuoke Li , Ziqing Niu , Jialiang Chen , Wenkai Zhang

We present EB-JEPA, an open-source library for learning representations and world models using Joint-Embedding Predictive Architectures (JEPAs). JEPAs learn to predict in representation space rather than pixel space, avoiding the pitfalls…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Basile Terver , Randall Balestriero , Megi Dervishi , David Fan , Quentin Garrido , Tushar Nagarajan , Koustuv Sinha , Wancong Zhang , Mike Rabbat , Yann LeCun , Amir Bar

Joint-Embedding Predictive Architectures (JEPA) learn view-invariant representations and admit projection-based distribution matching for collapse prevention. Existing approaches regularize representations towards isotropic Gaussian…

Machine Learning · Computer Science 2026-05-29 Yilun Kuang , Yash Dagade , Tim G. J. Rudner , Randall Balestriero , Yann LeCun

The joint-embedding predictive architecture (JEPA) recently has shown impressive results in extracting visual representations from unlabeled imagery under a masking strategy. However, we reveal its disadvantages, notably its insufficient…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Shentong Mo , Sukmin Yun

Image-based Joint-Embedding Predictive Architecture (IJEPA) offers an attractive alternative to Masked Autoencoder (MAE) for representation learning using the Masked Image Modeling framework. IJEPA drives representations to capture useful…

Machine Learning · Computer Science 2024-10-15 Etai Littwin , Vimal Thilak , Anand Gopalakrishnan

Recent advancements in self-supervised learning in the point cloud domain have demonstrated significant potential. However, these methods often suffer from drawbacks, including lengthy pre-training time, the necessity of reconstruction in…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Ayumu Saito , Prachi Kudeshia , Jiju Poovvancheri

Image-to-point cross-modal learning has emerged to address the scarcity of large-scale 3D datasets in 3D representation learning. However, current methods that leverage 2D data often result in large, slow-to-train models, making them…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Avishka Perera , Kumal Hewagamage , Saeedha Nazar , Kavishka Abeywardana , Hasitha Gallella , Ranga Rodrigo , Mohamed Afham

Visual Speech Recognition (VSR) tasks are generally recognized to have a lower theoretical performance ceiling than Automatic Speech Recognition (ASR), owing to the inherent limitations of conveying semantic information visually. To…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Chang Sun , Hong Yang , Bo Qin

Trajectory similarity computation is an essential technique for analyzing moving patterns of spatial data across various applications such as traffic management, wildlife tracking, and location-based services. Modern methods often apply…

Machine Learning · Computer Science 2024-06-21 Lihuan Li , Hao Xue , Yang Song , Flora Salim

Content-based image retrieval (CBIR) systems on pixel domain use low-level features, such as colour, texture and shape, to retrieve images. In this context, two types of image representations i.e. local and global image features have been…

Image and Video Processing · Electrical Eng. & Systems 2021-07-09 Shrikant Temburwar , Bulla Rajesh , Mohammed Javed

This work introduces composed image retrieval to remote sensing. It allows to query a large image archive by image examples alternated by a textual description, enriching the descriptive power over unimodal queries, either visual or…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Bill Psomas , Ioannis Kakogeorgiou , Nikos Efthymiadis , Giorgos Tolias , Ondrej Chum , Yannis Avrithis , Konstantinos Karantzalos

Self-supervised learning of visual representations has been focusing on learning content features, which do not capture object motion or location, and focus on identifying and differentiating objects in images and videos. On the other hand,…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Adrien Bardes , Jean Ponce , Yann LeCun

Semi-supervised learning has emerged as a powerful paradigm for leveraging large amounts of unlabeled data to improve the performance of machine learning models when labeled data are scarce. Among existing approaches, methods derived from…

Machine Learning · Computer Science 2026-04-29 Ali Aghababaei-Harandi , Aude Sportisse , Massih-Reza Amini

Content Based Image Retrieval(CBIR) is one of the important subfield in the field of Information Retrieval. The goal of a CBIR algorithm is to retrieve semantically similar images in response to a query image submitted by the end user. CBIR…

Information Retrieval · Computer Science 2014-09-03 Vikas Verma

We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene understanding. The approach combines four key components. First,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Lorenzo Mur-Labadia , Matthew Muckley , Amir Bar , Mido Assran , Koustuv Sinha , Mike Rabbat , Yann LeCun , Nicolas Ballas , Adrien Bardes

Modern Text-to-Image (T2I) generation increasingly relies on token-centric architectures that are trained with self-supervision, yet effectively fusing text with visual tokens remains a challenge. We propose \textbf{JEPA-T}, a unified…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Siheng Wan , Zhengtao Yao , Zhengdao Li , Junhao Dong , Yanshu Li , Yikai Li , Linshan Li , Haoyan Xu , Yijiang Li , Zhikang Dong , Huacan Wang , Jifeng Shen

The objective of Content-Based Image Retrieval (CBIR) methods is essentially to extract, from large (image) databases, a specified number of images similar in visual and semantic content to a so-called query image. To bridge the semantic…

Information Retrieval · Computer Science 2015-02-12 Smarajit Bose , Amita Pal , Jhimli Mallick , Sunil Kumar , Pratyaydipta Rudra

Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing methods remain fragile, relying on complex multi-term losses, exponential moving averages,…

Machine Learning · Computer Science 2026-03-26 Lucas Maes , Quentin Le Lidec , Damien Scieur , Yann LeCun , Randall Balestriero