VideoWorld: Exploring Knowledge Learning from Unlabeled Videos

• URL: http://arxiv.org/abs/2501.09781v1
• Date: Thu, 16 Jan 2025 18:59:10 GMT
• Title: VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
• Authors: Zhongwei Ren, Yunchao Wei, Xun Guo, Yao Zhao, Bingyi Kang, Jiashi Feng, Xiaojie Jin,
• Abstract summary: This work explores whether a deep generative model can learn complex knowledge solely from visual input. We develop VideoWorld, an auto-regressive video generation model trained on unlabeled video data, and test its knowledge acquisition abilities in video-based Go and robotic control tasks.
• Score: 119.35107657321902
• License:
• Abstract: This work explores whether a deep generative model can learn complex knowledge solely from visual input, in contrast to the prevalent focus on text-based models like large language models (LLMs). We develop VideoWorld, an auto-regressive video generation model trained on unlabeled video data, and test its knowledge acquisition abilities in video-based Go and robotic control tasks. Our experiments reveal two key findings: (1) video-only training provides sufficient information for learning knowledge, including rules, reasoning and planning capabilities, and (2) the representation of visual change is crucial for knowledge acquisition. To improve both the efficiency and efficacy of this process, we introduce the Latent Dynamics Model (LDM) as a key component of VideoWorld. Remarkably, VideoWorld reaches a 5-dan professional level in the Video-GoBench with just a 300-million-parameter model, without relying on search algorithms or reward mechanisms typical in reinforcement learning. In robotic tasks, VideoWorld effectively learns diverse control operations and generalizes across environments, approaching the performance of oracle models in CALVIN and RLBench. This study opens new avenues for knowledge acquisition from visual data, with all code, data, and models open-sourced for further research.

Related papers

• Learning by Watching: A Review of Video-based Learning Approaches for Robot Manipulation [0.0]
  Recent works have explored learning manipulation skills by passively watching abundant videos sourced online. This survey reviews foundations such as video feature representation learning techniques, object affordance understanding, 3D hand/body modeling, and large-scale robot resources. We discuss how learning only from observing large-scale human videos can enhance generalization and sample efficiency for robotic manipulation.
  arXiv  Detail & Related papers  (2024-02-11T08:41:42Z)
• Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning [54.67880602409801]
  In this paper, we study the problem of pre-training world models with abundant in-the-wild videos for efficient learning of visual control tasks. We introduce Contextualized World Models (ContextWM) that explicitly separate context and dynamics modeling. Our experiments show that in-the-wild video pre-training equipped with ContextWM can significantly improve the sample efficiency of model-based reinforcement learning.
  arXiv  Detail & Related papers  (2023-05-29T14:29:12Z)
• Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models [149.1331903899298]
  We propose a novel framework called BIKE, which utilizes the cross-modal bridge to explore bidirectional knowledge. We present a Temporal Concept Spotting mechanism that uses the Text-to-Video expertise to capture temporal saliency in a parameter-free manner. Our best model achieves a state-of-the-art accuracy of 88.6% on the challenging Kinetics-400 using the released CLIP model.
  arXiv  Detail & Related papers  (2022-12-31T11:36:53Z)
• InternVideo: General Video Foundation Models via Generative and Discriminative Learning [52.69422763715118]
  We present general video foundation models, InternVideo, for dynamic and complex video-level understanding tasks. InternVideo efficiently explores masked video modeling and video-language contrastive learning as the pretraining objectives. InternVideo achieves state-of-the-art performance on 39 video datasets from extensive tasks including video action recognition/detection, video-language alignment, and open-world video applications.
  arXiv  Detail & Related papers  (2022-12-06T18:09:49Z)
• Revisiting Classifier: Transferring Vision-Language Models for Video Recognition [102.93524173258487]
  Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. In this study, we focus on transferring knowledge for video classification tasks. We utilize the well-pretrained language model to generate good semantic target for efficient transferring learning.
  arXiv  Detail & Related papers  (2022-07-04T10:00:47Z)
• Masked World Models for Visual Control [90.13638482124567]
  We introduce a visual model-based RL framework that decouples visual representation learning and dynamics learning. We demonstrate that our approach achieves state-of-the-art performance on a variety of visual robotic tasks.
  arXiv  Detail & Related papers  (2022-06-28T18:42:27Z)
• A Comprehensive Study of Deep Video Action Recognition [35.7068977497202]
  Video action recognition is one of the representative tasks for video understanding. We provide a comprehensive survey of over 200 existing papers on deep learning for video action recognition.
  arXiv  Detail & Related papers  (2020-12-11T18:54:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.