中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共9条，第1-9条 帮助

限定条件                    
已选(0)清除 条数/页：   排序方式：
交互场景下多模态抑郁程度评估与可解释性研究 学位论文
, 2023
作者:  蔡聪
Adobe PDF(5243Kb)  |  收藏  |  浏览/下载：9/0  |  提交时间：2024/06/25
抑郁程度评估  多模态  交互场景  机器学习  可解释性  
Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Search 会议论文
, 法国巴黎, 2023 年 10 月 2 日 – 2023 年 10 月 6 日
作者:  Benzhi Wang;  Yang Yang;  Jinlin Wu;  Guo-jun Qi;  Zhen Lei
Adobe PDF(6488Kb)  |  收藏  |  浏览/下载：38/12  |  提交时间：2024/06/04
行人搜索，行人再识别，弱监督学习，度量学习，伪标签预测  
TwinTex: Geometry-aware Texture Generation for Abstracted 3D Architectural Models 期刊论文
ACM TRANSACTIONS ON GRAPHICS, 2023, 卷号: 42, 期号: 6, 页码: 14
作者:  Xiong, Weidan;  Zhang, Hongqian;  Peng, Botao;  Hu, Ziyu;  Wu, Yongli;  Guo, Jianwei;  Huang, Hui
Adobe PDF(5835Kb)  |  收藏  |  浏览/下载：50/3  |  提交时间：2024/03/26
Texture Mapping  3D Architectural Proxy  View Selection  Image Stitching  Texture Optimization  Diffusion Model  
Unsupervised Graph Representation Learning with Cluster-aware Self-training and Refining 期刊论文
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2023, 卷号: 14, 期号: 5, 页码: 21
作者:  Zhu, Yanqiao;  Xu, Yichen;  Yu, Feng;  Liu, Qiang;  Wu, Shu
Adobe PDF(1686Kb)  |  收藏  |  浏览/下载：98/5  |  提交时间：2023/12/21
Cluster-aware self-training and refining  unsupervised learning  graph representation learning  
SignParser: An End-to-End Framework for Traffic Sign Understanding 期刊论文
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2023, 卷号: 132, 期号: 2, 页码: 805-821
作者:  Guo, Yunfei;  Feng, Wei;  Yin, Fei;  Liu, Cheng-Lin
Adobe PDF(7011Kb)  |  收藏  |  浏览/下载：121/5  |  提交时间：2023/12/21
Traffic sign understanding  Content reasoning  Semantic description generation  
An unsupervised STDP-based spiking neural network inspired by biologically plausible learning rules and connections 期刊论文
Neural Networks, 2023, 卷号: 165, 页码: 799-808
作者:  Dong, Yiting;  Zhao, Dongcheng;  Li, Yang;  Zeng, Yi
Adobe PDF(2202Kb)  |  收藏  |  浏览/下载：111/11  |  提交时间：2023/11/17
Spiking neural network  Unsupervised  Plasticity learning rule  Brain inspired connection  
Reducing Vision-Answer Biases for Multiple-Choice VQA 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 4621-4634
作者:  Zhang, Xi;  Zhang, Feifei;  Xu, Changsheng
Adobe PDF(2684Kb)  |  收藏  |  浏览/下载：85/2  |  提交时间：2023/11/17
Multiple-choice VQA  vision-answer bias  causal intervention  counterfactual interaction learning  
Self-Supervised Monocular Depth Estimation With Geometric Prior and Pixel-Level Sensitivity 期刊论文
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2023, 卷号: 8, 期号: 3, 页码: 2244-2256
作者:  Liu, Jierui;  Cao, Zhiqiang;  Liu, Xilong;  Wang, Shuo;  Yu, Junzhi
Adobe PDF(8291Kb)  |  收藏  |  浏览/下载：156/10  |  提交时间：2023/11/17
Estimation  Costs  Training  Sensitivity  Cameras  Optical flow  Semantics  Monocular depth estimation  self-supervised learning  prior feature consistency  sensitivity adaptation  
Learning to Adapt Across Dual Discrepancy for Cross-Domain Person Re-Identification 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 2, 页码: 1963-1980
作者:  Luo, Chuanchen;  Song, Chunfeng;  Zhang, Zhaoxiang
Adobe PDF(2539Kb)  |  收藏  |  浏览/下载：258/76  |  提交时间：2023/03/20
Person re-identification  domain adaptation  cross-domain mixup  camera-aware learning  self-paced learning