English
Related papers

Related papers: Pretraining Frame Preservation for Lightweight Aut…

200 papers

We empirically study autoregressive pre-training from videos. To perform our study, we construct a series of autoregressive video models, called Toto. We treat videos as sequences of visual tokens and train transformer models to…

Computer Vision and Pattern Recognition · Computer Science 2025-01-10 Jathushan Rajasegaran , Ilija Radosavovic , Rahul Ravishankar , Yossi Gandelsman , Christoph Feichtenhofer , Jitendra Malik

Generating automatic dense captions for videos that accurately describe their contents remains a challenging area of research. Most current models require processing the entire video at once. Instead, we propose an efficient, online…

Computer Vision and Pattern Recognition · Computer Science 2024-11-25 AJ Piergiovanni , Dahun Kim , Michael S. Ryoo , Isaac Noble , Anelia Angelova

We present a novel perspective on learning video embedders for generative modeling: rather than requiring an exact reproduction of an input video, an effective embedder should focus on synthesizing visually plausible reconstructions. This…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Yitian Zhang , Long Mai , Aniruddha Mahapatra , David Bourgin , Yicong Hong , Jonah Casebeer , Feng Liu , Yun Fu

As generative technologies advance, visual content has evolved into a complex mix of natural and AI-generated images, driving the need for more efficient coding techniques that prioritize perceptual quality. Traditional codecs and learned…

Computer Vision and Pattern Recognition · Computer Science 2025-09-18 Jianhui Chang

Sequential video understanding, as an emerging video understanding task, has driven lots of researchers' attention because of its goal-oriented nature. This paper studies weakly supervised sequential video understanding where the accurate…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Sixun Dong , Huazhang Hu , Dongze Lian , Weixin Luo , Yicheng Qian , Shenghua Gao

This paper introduces a new lifelong learning solution where a single model is trained for a sequence of tasks. The main challenge that vision systems face in this context is catastrophic forgetting: as they tend to adapt to the most…

Computer Vision and Pattern Recognition · Computer Science 2018-07-19 Amal Rannen Triki , Rahaf Aljundi , Mathew B. Blaschko , Tinne Tuytelaars

Modern video codecs and learning-based approaches struggle for semantic reconstruction at extremely low bit-rates due to reliance on low-level spatiotemporal redundancies. Generative models, especially diffusion models, offer a new paradigm…

Image and Video Processing · Electrical Eng. & Systems 2026-02-06 Maojun Zhang , Haotian Wu , Richeng Jin , Deniz Gunduz , Krystian Mikolajczyk

Perceiving meaningful activities in a long video sequence is a challenging problem due to ambiguous definition of 'meaningfulness' as well as clutters in the scene. We approach this problem by learning a generative model for regular motion…

Computer Vision and Pattern Recognition · Computer Science 2016-04-18 Mahmudul Hasan , Jonghyun Choi , Jan Neumann , Amit K. Roy-Chowdhury , Larry S. Davis

Video prediction is an important yet challenging problem; burdened with the tasks of generating future frames and learning environment dynamics. Recently, autoregressive latent video models have proved to be a powerful video prediction…

Computer Vision and Pattern Recognition · Computer Science 2022-09-16 Younggyo Seo , Kimin Lee , Fangchen Liu , Stephen James , Pieter Abbeel

Recent advances in autoregressive video diffusion have enabled sequential and streaming video generation. However, long-horizon generation requires increasingly large KV caches, making efficient compression without sacrificing quality…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Peiliang Cai , Evelyn Zhang , Jiacheng Liu , Hao Lin , Ruiqi Zhang , Weile Mo , Yue Ma , Shikang Zheng , Jiehang Huang , Dongrui Liu , Linfeng 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

With recent advancements in video backbone architectures, combined with the remarkable achievements of large language models (LLMs), the analysis of long-form videos spanning tens of minutes has become both feasible and increasingly…

Computer Vision and Pattern Recognition · Computer Science 2026-02-23 Yuxiao Chen , Jue Wang , Zhikang Zhang , Jingru Yi , Xu Zhang , Yang Zou , Zhaowei Cai , Jianbo Yuan , Xinyu Li , Hao Yang , Davide Modolo

Point tracking is a challenging task in computer vision, aiming to establish point-wise correspondence across long video sequences. Recent advancements have primarily focused on temporal modeling techniques to improve local feature…

Computer Vision and Pattern Recognition · Computer Science 2024-07-31 Zikai Song , Ying Tang , Run Luo , Lintao Ma , Junqing Yu , Yi-Ping Phoebe Chen , Wei Yang

Recent approaches to real-time long video generation typically employ streaming tuning strategies, attempting to train a long-context student using a short-context (memoryless) teacher. In these frameworks, the student performs long…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Shuo Chen , Cong Wei , Sun Sun , Ping Nie , Kai Zhou , Ge Zhang , Ming-Hsuan Yang , Wenhu Chen

We present Recurrent Video Masked-Autoencoders (RVM): a novel approach to video representation learning that leverages recurrent computation to model the temporal structure of video data. RVM couples an asymmetric masking objective with a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Daniel Zoran , Nikhil Parthasarathy , Yi Yang , Drew A Hudson , Joao Carreira , Andrew Zisserman

Learning a robust video Variational Autoencoder (VAE) is essential for reducing video redundancy and facilitating efficient video generation. Directly applying image VAEs to individual frames in isolation can result in temporal…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Yazhou Xing , Yang Fei , Yingqing He , Jingye Chen , Jiaxin Xie , Xiaowei Chi , Qifeng Chen

This study explores the potential of open-source video conditional generation models as encoders for downstream tasks, focusing on instance segmentation using the BAIR Robot Pushing Dataset. The researchers propose using video prediction…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 James Maier , Nishanth Mohankumar

This paper presents a new self-supervised video representation learning framework, ARVideo, which autoregressively predicts the next video token in a tailored sequence order. Two key designs are included. First, we organize autoregressive…

Computer Vision and Pattern Recognition · Computer Science 2024-05-27 Sucheng Ren , Hongru Zhu , Chen Wei , Yijiang Li , Alan Yuille , Cihang Xie

We address the task of unsupervised retargeting of human actions from one video to another. We consider the challenging setting where only a few frames of the target is available. The core of our approach is a conditional generative model…

Computer Vision and Pattern Recognition · Computer Science 2020-03-26 Jessica Lee , Deva Ramanan , Rohit Girdhar

In this paper, we re-examine the task of cross-modal clip-sentence retrieval, where the clip is part of a longer untrimmed video. When the clip is short or visually ambiguous, knowledge of its local temporal context (i.e. surrounding video…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Adriano Fragomeni , Michael Wray , Dima Damen