Výsledky vyhledávání

Report

Recovering Complete Actions for Cross-dataset Skeleton Action Recognition

Autor: Liu, Hanchao, Li, Yujiang, Mu, Tai-Jiang, Hu, Shi-Min

Despite huge progress in skeleton-based action recognition, its generalizability to different domains remains a challenging issue. In this paper, to solve the skeleton action generalization problem, we present a recover-and-resample augmentation fram

Externí odkaz: http://arxiv.org/abs/2410.23641

Zobrazit plný text záznamu

Report

Programmable Motion Generation for Open-Set Motion Control Tasks

Autor: Liu, Hanchao, Zhan, Xiaohang, Huang, Shaoli, Mu, Tai-Jiang, Shan, Ying

Character animation in real-world scenarios necessitates a variety of constraints, such as trajectories, key-frames, interactions, etc. Existing methodologies typically treat single or a finite set of these constraint(s) as separate control tasks. Th

Externí odkaz: http://arxiv.org/abs/2405.19283

Zobrazit plný text záznamu

Report

Hilbert Space-Valued LQ Mean Field Games: An Infinite-Dimensional Analysis

Autor: Liu, Hanchao, Firoozi, Dena

This paper presents a comprehensive study of linear-quadratic (LQ) mean field games (MFGs) in Hilbert spaces, generalizing the classic LQ MFG theory to scenarios involving $N$ agents with dynamics governed by infinite-dimensional stochastic equations

Externí odkaz: http://arxiv.org/abs/2403.01012

Zobrazit plný text záznamu

Report

A Survey on Hallucination in Large Vision-Language Models

Autor: Liu, Hanchao, Xue, Wenyuan, Chen, Yifei, Chen, Dapeng, Zhao, Xiutian, Wang, Ke, Hou, Liping, Li, Rongjun, Peng, Wei

Recent development of Large Vision-Language Models (LVLMs) has attracted growing attention within the AI landscape for its practical implementation potential. However, ``hallucination'', or more specifically, the misalignment between factual visual c

Externí odkaz: http://arxiv.org/abs/2402.00253

Zobrazit plný text záznamu

Report

LQG Risk-Sensitive Single-Agent and Major-Minor Mean Field Game Systems: A Variational Framework

Autor: Liu, Hanchao, Firoozi, Dena, Breton, Michèle

We develop a variational approach to address risk-sensitive optimal control problems with an exponential-of-integral cost functional in a general linear-quadratic-Gaussian (LQG) single-agent setup, offering new insights into such problems. Our analys

Externí odkaz: http://arxiv.org/abs/2305.15364

Zobrazit plný text záznamu