中文
相关论文

相关论文: Out of Sight, Out of Mind? Evaluating State Evolut…

200 篇论文

Recent generative video world models aim to simulate visual environment evolution, allowing an observer to interactively explore the scene via camera control. However, they implicitly assume that the world only evolves within the observer's…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Zicheng Duan , Jiatong Xia , Zeyu Zhang , Wenbo Zhang , Gengze Zhou , Chenhui Gou , Yefei He , Feng Chen , Xinyu Zhang , Lingqiao Liu

Video world models should maintain evolving states when evidence is unobserved, yet current generators often freeze hidden states upon interruption. This is not simply a capacity problem: pretrained video diffusion transformers already…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Tianshuo Xu , Yichen Xie , Depu Meng , Chensheng Peng , Quentin Herau , Bo Jiang , Yihan Hu , Wei Zhan

When humans observe a physical system, they can easily locate objects, understand their interactions, and anticipate future behavior, even in settings with complicated and previously unseen interactions. For computers, however, learning…

机器学习 · 计算机科学 2020-02-13 Jannik Kossen , Karl Stelzner , Marcel Hussing , Claas Voelcker , Kristian Kersting

Learning from visual observation (LfVO), aiming at recovering policies from only visual observation data, is promising yet a challenging problem. Existing LfVO approaches either only adopt inefficient online learning schemes or require…

机器学习 · 计算机科学 2023-06-23 Bohan Zhou , Ke Li , Jiechuan Jiang , Zongqing Lu

Humans can easily segment moving objects without knowing what they are. That objectness could emerge from continuous visual observations motivates us to model grouping and movement concurrently from unlabeled videos. Our premise is that a…

计算机视觉与模式识别 · 计算机科学 2021-11-12 Runtao Liu , Zhirong Wu , Stella X. Yu , Stephen Lin

A natural approach to generative modeling of videos is to represent them as a composition of moving objects. Recent works model a set of 2D sprites over a slowly-varying background, but without considering the underlying 3D scene that gives…

计算机视觉与模式识别 · 计算机科学 2021-03-26 Paul Henderson , Christoph H. Lampert

Recent single image unsupervised representation learning techniques show remarkable success on a variety of tasks. The basic principle in these works is instance discrimination: learning to differentiate between two augmented versions of…

计算机视觉与模式识别 · 计算机科学 2020-05-08 Daniel Gordon , Kiana Ehsani , Dieter Fox , Ali Farhadi

Video generation models (VGMs) have received extensive attention recently and serve as promising candidates for general-purpose large vision models. While they can only generate short videos each time, existing methods achieve long video…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Yuanhui Huang , Wenzhao Zheng , Yuan Gao , Xin Tao , Pengfei Wan , Di Zhang , Jie Zhou , Jiwen Lu

Recent video diffusion models generate photorealistic, temporally coherent videos, yet they fall short as reliable world models for autonomous driving, where structured motion and physically consistent interactions are essential. Adapting…

计算机视觉与模式识别 · 计算机科学 2026-01-15 Ahmad Rahimi , Valentin Gerard , Eloi Zablocki , Matthieu Cord , Alexandre Alahi

Unsupervised object-centric learning aims to represent the modular, compositional, and causal structure of a scene as a set of object representations and thereby promises to resolve many critical limitations of traditional single-vector…

计算机视觉与模式识别 · 计算机科学 2022-05-30 Gautam Singh , Yi-Fu Wu , Sungjin Ahn

State-of-the-art text-to-video models often look realistic frame-by-frame yet fail on simple interactions: motion starts before contact, actions are not realized, objects drift after placement, and support relations break. We argue this…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Chika Maduabuchi

Text-to-video (T2V) generation models have made rapid progress in producing visually high-quality and temporally coherent videos. However, existing benchmarks primarily focus on perceptual quality, text-video alignment, or physical…

计算机视觉与模式识别 · 计算机科学 2026-04-20 Xianjing Han , Bin Zhu , Shiqi Hu , Franklin Mingzhe Li , Patrick Carrington , Roger Zimmermann , Jingjing Chen

Video understanding requires models to continuously track and update world state during playback. While existing benchmarks have advanced video understanding evaluation across multiple dimensions, the observation of how models maintain…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Pengyiang Liu , Zhongyue Shi , Hongye Hao , Qi Fu , Xueting Bi , Siwei Zhang , Xiaoyang Hu , Zitian Wang , Linjiang Huang , Si Liu

World models learn to predict future states of an environment, enabling planning and mental simulation. Current approaches default to Transformer-based predictors operating in learned latent spaces. This comes at a cost: O(N^2) computation…

机器学习 · 计算机科学 2026-03-24 Fabien Polly

Following major advances in text and image generation, the video domain has surged, producing highly realistic and controllable sequences. Along with this progress, these models also raise serious concerns about misinformation, making…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Omer Ben Hayun , Roy Betser , Meir Yossef Levi , Levi Kassel , Guy Gilboa

Ophthalmic decision-making depends on subtle lesion-scale cues interpreted across multimodal imaging and over time, yet most medical foundation models remain static and degrade under modality and acquisition shifts. Here we introduce…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Ziyu Gao , Xinyuan Wu , Xiaolan Chen , Zhuoran Liu , Ruoyu Chen , Bowen Liu , Bingjie Yan , Zhenhan Wang , Kai Jin , Jiancheng Yang , Yih Chung Tham , Mingguang He , Danli Shi

We propose a method which can detect events in videos by modeling the change in appearance of the event participants over time. This method makes it possible to detect events which are characterized not by motion, but by the changing state…

计算机视觉与模式识别 · 计算机科学 2013-06-21 Daniel Paul Barrett , Jeffrey Mark Siskind

We explore a novel video creation experience, namely Video Creation by Demonstration. Given a demonstration video and a context image from a different scene, we generate a physically plausible video that continues naturally from the context…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Yihong Sun , Hao Zhou , Liangzhe Yuan , Jennifer J. Sun , Yandong Li , Xuhui Jia , Hartwig Adam , Bharath Hariharan , Long Zhao , Ting Liu

The problem of determining whether an object is in motion, irrespective of camera motion, is far from being solved. We address this challenging task by learning motion patterns in videos. The core of our approach is a fully convolutional…

计算机视觉与模式识别 · 计算机科学 2017-04-11 Pavel Tokmakov , Karteek Alahari , Cordelia Schmid

Much of model-based reinforcement learning involves learning a model of an agent's world, and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every…

神经与进化计算 · 计算机科学 2019-11-01 C. Daniel Freeman , Luke Metz , David Ha
‹ 上一页 1 2 3 10 下一页 ›