English
Related papers

Related papers: Olaf-World: Orienting Latent Actions for Video Wor…

200 papers

Open-set Unsupervised Video Domain Adaptation (OUVDA) deals with the task of adapting an action recognition model from a labelled source domain to an unlabelled target domain that contains "target-private" categories, which are present in…

Computer Vision and Pattern Recognition · Computer Science 2023-04-05 Giacomo Zara , Subhankar Roy , Paolo Rota , Elisa Ricci

Vision-Language-Action (VLA) models have advanced rapidly with stronger backbones, broader pre-training, and larger demonstration datasets, yet their action heads remain largely homogeneous: most directly predict action commands in a fixed…

Artificial Intelligence · Computer Science 2026-05-13 Huoren Yang , Jianchao Zhao , Hu Yusong , Qiguan Ou , Yuyang Gao , Wei Ke , Yuhang He , SongLin Dong , Zhiheng Ma , Yihong Gong

Video is a scalable observation of physical dynamics: it captures how objects move, how contact unfolds, and how scenes evolve under interaction -- all without requiring robot action labels. Yet translating this temporal structure into…

Robotics · Computer Science 2026-04-08 Linfang Zheng , Zikai Ouyang , Chen Wang , Jia Pan , Wei Zhang

Traditional video captioning requests a holistic description of the video, yet the detailed descriptions of the specific objects may not be available. Without associating the moving trajectories, these image-based data-driven methods cannot…

Computer Vision and Pattern Recognition · Computer Science 2020-07-15 Fangyi Zhu , Jenq-Neng Hwang , Zhanyu Ma , Guang Chen , Jun Guo

We focus on the task of future frame prediction in video governed by underlying physical dynamics. We work with models which are object-centric, i.e., explicitly work with object representations, and propagate a loss in the latent space.…

Machine Learning · Computer Science 2021-07-19 Rushil Gupta , Vishal Sharma , Yash Jain , Yitao Liang , Guy Van den Broeck , Parag Singla

Real-world videos contain many complex actions with inherent relationships between action classes. In this work, we propose an attention-based architecture that models these action relationships for the task of temporal action localization…

Computer Vision and Pattern Recognition · Computer Science 2021-06-01 Praveen Tirupattur , Kevin Duarte , Yogesh Rawat , Mubarak Shah

Exploring open-vocabulary video action recognition is a promising venture, which aims to recognize previously unseen actions within any arbitrary set of categories. Existing methods typically adapt pretrained image-text models to the video…

Computer Vision and Pattern Recognition · Computer Science 2023-12-06 Chengyou Jia , Minnan Luo , Xiaojun Chang , Zhuohang Dang , Mingfei Han , Mengmeng Wang , Guang Dai , Sizhe Dang , Jingdong Wang

Vision-language-action (VLA) models remain constrained by the scarcity of action-labeled robot data, whereas action-free videos provide abundant evidence of how the physical world changes. Latent action models offer a promising way to…

Learning a latent dynamics model provides a task-agnostic representation of an agent's understanding of its environment. Leveraging this knowledge for model-based reinforcement learning (RL) holds the potential to improve sample efficiency…

Machine Learning · Computer Science 2025-02-10 Malte Mosbach , Jan Niklas Ewertz , Angel Villar-Corrales , Sven Behnke

Humans perceive actions through key transitions that structure actions across multiple abstraction levels, whereas machines, relying on visual features, tend to over-segment. This highlights the difficulty of enabling hierarchical reasoning…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Junxian Huang , Ruichu Cai , Hao Zhu , Juntao Fang , Boyan Xu , Weilin Chen , Zijian Li , Shenghua Gao

Latent action models (LAMs) aim to learn action-like representations from unlabeled videos by compressing frame-to-frame changes. The frames of in-the-wild videos, however, contain not only the agent's own state but exogenous state such as…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Jung Min Lee , Taehyun Cho , Li Zhao , Jungwoo Lee

The goal of this paper is to recognize actions in video without the need for examples. Different from traditional zero-shot approaches we do not demand the design and specification of attribute classifiers and class-to-attribute mappings to…

Computer Vision and Pattern Recognition · Computer Science 2015-10-26 Mihir Jain , Jan C. van Gemert , Thomas Mensink , Cees G. M. Snoek

We present OCRA, an Object-Centric framework for video-based human-to-Robot Action transfer that learns directly from human demonstration videos to enable robust manipulation. Object-centric learning emphasizes task-relevant objects and…

Robotics · Computer Science 2026-03-17 Kuanning Wang , Ke Fan , Yuqian Fu , Siyu Lin , Hu Luo , Daniel Seita , Yanwei Fu , Yu-Gang Jiang , Xiangyang Xue

Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The execution of complex multi-step behaviors in VLA models can be improved by robust instruction grounding, a critical component…

A World Model is a compressed spatial and temporal representation of a real world environment that allows one to train an agent or execute planning methods. However, world models are typically trained on observations from the real world…

Machine Learning · Computer Science 2024-10-28 Fabio Ferreira , Moreno Schlageter , Raghu Rajan , Andre Biedenkapp , Frank Hutter

World models, which predict future transitions from past observation and action sequences, have shown great promise for improving data efficiency in sequential decision-making. However, existing world models often require extensive…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Siqiao Huang , Jialong Wu , Qixing Zhou , Shangchen Miao , Mingsheng Long

A plausible scene evolution depends on the maneuver being considered, while a good maneuver depends on how the scene may evolve. Existing World Action Models (WAMs) largely miss this reciprocity, treating world prediction and action…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Hongbo Lu , Liang Yao , Chenghao He , Haoyu Wang , Xiang Gu , Xianfei Li , Wenlong Liao , Tao He , Pai Peng

Open-world continual learning (OWCL) adapts to sequential tasks with open samples, learning knowledge incrementally while preventing forgetting. However, existing OWCL still requires a large amount of labeled data for training, which is…

Machine Learning · Computer Science 2025-07-29 Yujie Li , Xiangkun Wang , Xin Yang , Marcello Bonsangue , Junbo Zhang , Tianrui Li

Motion forecasting aims to predict the future trajectories of dynamic agents in the scene, enabling autonomous vehicles to effectively reason about scene evolution. Existing approaches operate under the closed-world regime and assume fixed…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Nicolas Schischka , Nikhil Gosala , B Ravi Kiran , Senthil Yogamani , Abhinav Valada

Action recognition models have achieved promising results in understanding instructional videos. However, they often rely on dominant, dataset-specific action sequences rather than true video comprehension, a problem that we define as…

Computer Vision and Pattern Recognition · Computer Science 2025-12-08 Joochan Kim , Minjoon Jung , Byoung-Tak Zhang