English
Related papers

Related papers: Multiscale Video Pretraining for Long-Term Activit…

200 papers

Real-time rendering and animation of humans is a core function in games, movies, and telepresence applications. Existing methods have a number of drawbacks we aim to address with our work. Triangle meshes have difficulty modeling thin…

We have witnessed impressive advances in video action understanding. Increased dataset sizes, variability, and computation availability have enabled leaps in performance and task diversification. Current systems can provide coarse- and…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Alexandros Stergiou , Ronald Poppe

Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Jue Wang , Gedas Bertasius , Du Tran , Lorenzo Torresani

Video captioning which automatically translates video clips into natural language sentences is a very important task in computer vision. By virtue of recent deep learning technologies, e.g., convolutional neural networks (CNNs) and…

Computer Vision and Pattern Recognition · Computer Science 2016-11-18 Junbo Wang , Wei Wang , Yan Huang , Liang Wang , Tieniu Tan

We present a simplified, task-agnostic multi-modal pre-training approach that can accept either video or text input, or both for a variety of end tasks. Existing pre-training are task-specific by adopting either a single cross-modal encoder…

Computer Vision and Pattern Recognition · Computer Science 2021-10-04 Hu Xu , Gargi Ghosh , Po-Yao Huang , Prahal Arora , Masoumeh Aminzadeh , Christoph Feichtenhofer , Florian Metze , Luke Zettlemoyer

The objective of this paper is self-supervised learning from video, in particular for representations for action recognition. We make the following contributions: (i) We propose a new architecture and learning framework Memory-augmented…

Computer Vision and Pattern Recognition · Computer Science 2020-08-04 Tengda Han , Weidi Xie , Andrew Zisserman

Extracting physical dynamical system parameters from recorded observations is key in natural science. Current methods for automatic parameter estimation from video train supervised deep networks on large datasets. Such datasets require…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Alejandro Castañeda Garcia , Jan van Gemert , Daan Brinks , Nergis Tömen

Human behavior understanding in videos is a complex, still unsolved problem and requires to accurately model motion at both the local (pixel-wise dense prediction) and global (aggregation of motion cues) levels. Current approaches based on…

Computer Vision and Pattern Recognition · Computer Science 2019-09-19 C. Spampinato , S. Palazzo , P. D'Oro , D. Giordano , M. Shah

Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced video architectures. This paper presents an in-depth study of…

Computer Vision and Pattern Recognition · Computer Science 2019-05-03 Deepti Ghadiyaram , Matt Feiszli , Du Tran , Xueting Yan , Heng Wang , Dhruv Mahajan

While leveraging abundant human videos and simulated robot data poses a scalable solution to the scarcity of real-world robot data, the generalization capability of existing vision-language-action models (VLAs) remains limited by mismatches…

Learning robust and scalable visual representations from massive multi-view video data remains a challenge in computer vision and autonomous driving. Existing pre-training methods either rely on expensive supervised learning with 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-03-14 Jialv Zou , Bencheng Liao , Qian Zhang , Wenyu Liu , Xinggang Wang

Human activities are naturally structured as hierarchies unrolled over time. For action prediction, temporal relations in event sequences are widely exploited by current methods while their semantic coherence across different levels of…

Computer Vision and Pattern Recognition · Computer Science 2020-08-24 Romero Morais , Vuong Le , Truyen Tran , Svetha Venkatesh

We propose an end-to-end learned video compression scheme for low-latency scenarios. Previous methods are limited in using the previous one frame as reference. Our method introduces the usage of the previous multiple frames as references.…

Image and Video Processing · Electrical Eng. & Systems 2021-08-02 Jianping Lin , Dong Liu , Houqiang Li , Feng Wu

Long video understanding (LVU) is challenging because answering real-world queries often depends on sparse, temporally dispersed cues buried in hours of mostly redundant and irrelevant content. While agentic pipelines improve video…

Computer Vision and Pattern Recognition · Computer Science 2025-12-08 Ziyang Wang , Honglu Zhou , Shijie Wang , Junnan Li , Caiming Xiong , Silvio Savarese , Mohit Bansal , Michael S. Ryoo , Juan Carlos Niebles

Multimodal learning, which involves integrating information from various modalities such as text, images, audio, and video, is pivotal for numerous complex tasks like visual question answering, cross-modal retrieval, and caption generation.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 G. Thomas Hudson , Dean Slack , Thomas Winterbottom , Jamie Sterling , Chenghao Xiao , Junjie Shentu , Noura Al Moubayed

An agent that is capable of predicting what happens next can perform a variety of tasks through planning with no additional training. Furthermore, such an agent can internally represent the complex dynamics of the real-world and therefore…

Computer Vision and Pattern Recognition · Computer Science 2021-06-25 Mohammad Babaeizadeh , Mohammad Taghi Saffar , Suraj Nair , Sergey Levine , Chelsea Finn , Dumitru Erhan

We use multilayer Long Short Term Memory (LSTM) networks to learn representations of video sequences. Our model uses an encoder LSTM to map an input sequence into a fixed length representation. This representation is decoded using single or…

Machine Learning · Computer Science 2016-01-05 Nitish Srivastava , Elman Mansimov , Ruslan Salakhutdinov

Action anticipation, which aims to recognize the action with a partial observation, becomes increasingly popular due to a wide range of applications. In this paper, we investigate the problem of 3D action anticipation from streaming videos…

Computer Vision and Pattern Recognition · Computer Science 2023-06-16 Hongsong Wang , Jiashi Feng

A video prediction model that generalizes to diverse scenes would enable intelligent agents such as robots to perform a variety of tasks via planning with the model. However, while existing video prediction models have produced promising…

Computer Vision and Pattern Recognition · Computer Science 2021-06-22 Bohan Wu , Suraj Nair , Roberto Martin-Martin , Li Fei-Fei , Chelsea Finn

It is crucial to choose actions from an appropriate distribution while learning a sequential decision-making process in which a set of actions is expected given the states and previous reward. Yet, if there are more than two latent…

Computer Vision and Pattern Recognition · Computer Science 2022-11-24 Fatemeh Nouri , Robert Bergevin