Výsledky vyhledávání - "Liang Longfei"

Report

Autor: Gao, Jianxiong, Qian, Xuelin, Liang, Longfei, Han, Junwei, Fu, Yanwei

Amodal object completion is a complex task that involves predicting the invisible parts of an object based on visible segments and background information. Learning shape priors is crucial for effective amodal completion, but traditional methods often

Externí odkaz: http://arxiv.org/abs/2405.19949

Zobrazit plný text záznamu

Report

Online Sequence Clustering Algorithm for Video Trajectory Analysis

Autor: Yuemaier, Aximu, Chen, Xiaogang, Qian, Xingyu, Liang, Longfei, Li, Shunfeng, Song, Zhitang

Target tracking and trajectory modeling have important applications in surveillance video analysis and have received great attention in the fields of road safety and community security. In this work, we propose a lightweight real-time video analysis

Externí odkaz: http://arxiv.org/abs/2305.08418

Zobrazit plný text záznamu

Report

Adaptive Multi-Agent Continuous Learning System

Autor: Qian, Xingyu, Yuemaier, Aximu, Liang, Longfei, Yang, Wen-Chi, Chen, Xiaogang, Li, Shunfen, Dai, Weibang, Song, Zhitang

We propose an adaptive multi-agent clustering recognition system that can be self-supervised driven, based on a temporal sequences continuous learning mechanism with adaptability. The system is designed to use some different functional agents to buil

Externí odkaz: http://arxiv.org/abs/2212.07646

Zobrazit plný text záznamu