English
Related papers

Related papers: LyTimeT: Towards Robust and Interpretable State-Va…

200 papers

We present a video generation model that accurately reproduces object motion, changes in camera viewpoint, and new content that arises over time. Existing video generation methods often fail to produce new content as a function of time…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Tim Brooks , Janne Hellsten , Miika Aittala , Ting-Chun Wang , Timo Aila , Jaakko Lehtinen , Ming-Yu Liu , Alexei A. Efros , Tero Karras

A core problem in machine learning is to learn expressive latent variables for model prediction on complex data that involves multiple sub-components in a flexible and interpretable fashion. Here, we develop an approach that improves…

Machine Learning · Computer Science 2024-02-13 Yi-Lin Tuan , Zih-Yun Chiu , William Yang Wang

We introduce latent intuitive physics, a transfer learning framework for physics simulation that can infer hidden properties of fluids from a single 3D video and simulate the observed fluid in novel scenes. Our key insight is to use latent…

Artificial Intelligence · Computer Science 2024-08-06 Xiangming Zhu , Huayu Deng , Haochen Yuan , Yunbo Wang , Xiaokang Yang

Real-world visual data rarely presents as isolated, static instances. Instead, it often evolves gradually over time through variations in pose, lighting, object state, or scene context. However, conventional classifiers are typically…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Xi Ding , Lei Wang , Piotr Koniusz , Yongsheng Gao

Visual understanding of the world goes beyond the semantics and flat structure of individual images. In this work, we aim to capture both the 3D structure and dynamics of real-world scenes from monocular real-world videos. Our Dynamic Scene…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Maximilian Seitzer , Sjoerd van Steenkiste , Thomas Kipf , Klaus Greff , Mehdi S. M. Sajjadi

Estimating scene lighting from a single image or video remains a longstanding challenge in computer vision and graphics. Learning-based approaches are constrained by the scarcity of ground-truth HDR environment maps, which are expensive to…

Graphics · Computer Science 2025-09-05 Ruofan Liang , Kai He , Zan Gojcic , Igor Gilitschenski , Sanja Fidler , Nandita Vijaykumar , Zian Wang

The task of video prediction and generation is known to be notoriously difficult, with the research in this area largely limited to short-term predictions. Though plagued with noise and stochasticity, videos consist of features that are…

Machine Learning · Computer Science 2023-01-10 Alexey Zakharov , Qinghai Guo , Zafeirios Fountas

Recently, dataset distillation has paved the way towards efficient machine learning, especially for image datasets. However, the distillation for videos, characterized by an exclusive temporal dimension, remains an underexplored domain. In…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Ziyu Wang , Yue Xu , Cewu Lu , Yong-Lu Li

This presentation introduces a self-supervised learning approach to the synthesis of new video clips from old ones, with several new key elements for improved spatial resolution and realism: It conditions the synthesis process on contextual…

Computer Vision and Pattern Recognition · Computer Science 2021-10-27 Guillaume Le Moing , Jean Ponce , Cordelia Schmid

Predicting the evolution of systems that exhibit spatio-temporal dynamics in response to external stimuli is a key enabling technology fostering scientific innovation. Traditional equations-based approaches leverage first principles to…

Machine Learning · Computer Science 2023-05-02 Francesco Regazzoni , Stefano Pagani , Matteo Salvador , Luca Dede' , Alfio Quarteroni

Extracting a stable and compact representation of the environment is crucial for efficient reinforcement learning in high-dimensional, noisy, and non-stationary environments. Different categories of information coexist in such environments…

Machine Learning · Computer Science 2023-06-28 Yu-Ren Liu , Biwei Huang , Zhengmao Zhu , Honglong Tian , Mingming Gong , Yang Yu , Kun Zhang

Analyzing signals arising from dynamical systems typically requires many modeling assumptions and parameter estimation. In high dimensions, this modeling is particularly difficult due to the "curse of dimensionality". In this paper, we…

Systems and Control · Computer Science 2016-12-21 Tal Shnitzer , Ronen Talmon , Jean-Jacques Slotine

Historically, feature-based approaches have been used extensively for camera-based robot perception tasks such as localization, mapping, tracking, and others. Several of these approaches also combine other sensors (inertial sensing, for…

Robotics · Computer Science 2023-10-11 Kartikeya Singh , Charuvaran Adhivarahan , Karthik Dantu

While Video Large Language Models (Video-LLMs) have shown significant potential in multimodal understanding and reasoning tasks, how to efficiently select the most informative frames from videos remains a critical challenge. Existing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Shihao Wang , Guo Chen , De-an Huang , Zhiqi Li , Minghan Li , Guilin Liu , Jose M. Alvarez , Lei Zhang , Zhiding Yu

Identifying underlying governing equations and physical relevant information from high-dimensional observable data has always been a challenge in physical sciences. With the recent advances in sensing technology and available datasets,…

Machine Learning · Computer Science 2021-04-27 Yayati Jadhav , Amir Barati Farimani

While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens.…

Computer Vision and Pattern Recognition · Computer Science 2022-11-23 Yuxuan Liang , Pan Zhou , Roger Zimmermann , Shuicheng Yan

Videos provide a rich source of information, but it is generally hard to extract dynamical parameters of interest. Inferring those parameters from a video stream would be beneficial for physical reasoning. Robots performing tasks in dynamic…

Video-based AI systems are increasingly adopted in safety-critical domains such as autonomous driving and healthcare. However, interpreting their decisions remains challenging due to the inherent spatiotemporal complexity of video data and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Payal Varshney , Adriano Lucieri , Christoph Balada , Sheraz Ahmed , Andreas Dengel

Previous methods for dynamic facial expression in the wild are mainly based on Convolutional Neural Networks (CNNs), whose local operations ignore the long-range dependencies in videos. To solve this problem, we propose the spatio-temporal…

Computer Vision and Pattern Recognition · Computer Science 2022-05-11 Fuyan Ma , Bin Sun , Shutao Li

Despite extensive research in robust visual-inertial navigation systems~(VINS) in dynamic environments, many approaches remain vulnerable to objects that suddenly start moving, which are referred to as \textit{abruptly dynamic objects}. In…

Robotics · Computer Science 2024-10-22 Seungwon Song , Hyungtae Lim , Alex Junho Lee , Hyun Myung