Match!
Wenhui Li
Tianjin University
Machine learningPattern recognitionInformation systemComputer visionComputer science
23Publications
4H-index
57Citations
What is this?
Publications 23
Newest
#1Wenhui Li (TJU: Tianjin University)H-Index: 4
#2Shu Xiang (TJU: Tianjin University)H-Index: 3
Last. Tong Hao (Tianjin Normal University)H-Index: 9
view all 7 authors...
Abstract With the widespread application of 3D capture devices, diverse 3D object datasets from different domains have emerged recently. Consequently, how to obtain the 3D objects from different domains is becoming a significant and challenging task. The existing approaches mainly focus on the task of retrieval from the identical dataset, which significantly constrains their implementation in real-world applications. This paper addresses the cross-domain object retrieval in an unsupervised manne...
Source
Jul 11, 2020 in IJCAI (International Joint Conference on Artificial Intelligence)
#1Yuting Su (TJU: Tianjin University)H-Index: 19
#2Yuqian LiH-Index: 1
Last. Anan Liu (TJU: Tianjin University)H-Index: 17
view all 6 authors...
Jul 11, 2020 in IJCAI (International Joint Conference on Artificial Intelligence)
#1Heyu Zhou (TJU: Tianjin University)H-Index: 2
#2Weizhi Nie (TJU: Tianjin University)H-Index: 16
Last. Anan Liu (TJU: Tianjin University)H-Index: 17
view all 5 authors...
#1Wenhui Li (TJU: Tianjin University)H-Index: 4
#2Yuting Su (TJU: Tianjin University)H-Index: 19
view all 5 authors...
Recently, with the rapid development of digital technologies and its wide application, 3D model retrieval is becoming more and more important in graphic communities. In this task, how to effectively represent the 3D model and how to robustly measure similarity between pair-wise models are two crucial problems. In previous work, most papers dedicated to researching how to effectively using the visualize features to represent 3D model and using the visual information to measure the similarity. How...
Source
Source
Source
#1Jing Zhang (TJU: Tianjin University)H-Index: 3
#2Fuwu Li (TJU: Tianjin University)H-Index: 1
Last. Yuting Su (TJU: Tianjin University)H-Index: 19
view all 5 authors...
Attributes are expected to narrow down the semantic gap between low-level visual features and high-level semantic meanings. Such superiority motivates us to explore pedestrian attributes which has became a critical problem to boost image understanding and improve the performance of pedestrian detection, retrieval, re-identification, etc. Based on the PETA dateset, we manually relabel two subset VIPeR and PRID as our experimental dataset. Moreover, we proposed an evaluation protocol for researche...
1 CitationsSource
#1Yuting Su (TJU: Tianjin University)H-Index: 19
#2Wenhui Li (TJU: Tianjin University)H-Index: 4
Last. Anan Liu (TJU: Tianjin University)H-Index: 17
view all 5 authors...
3D model retrieval is becoming a hot research topic due to its wide applications such as computer-aided design, digital entertainment, and virtual reality. For this challenging task, feature learning and similarity measure are two critical problems. However, existing approaches usually learn discriminative visual features and develop a complex graph matching strategy to measure the similarity independently. In this paper, we propose an unsupervised method which can embed similarity measure into ...
Source
#1Wenhui LiH-Index: 4
#2Anan LiuH-Index: 17
Last. Sicheng ZhaoH-Index: 1
view all 40 authors...
1 CitationsSource
Jul 13, 2018 in IJCAI (International Joint Conference on Artificial Intelligence)
#1Anan Liu (TJU: Tianjin University)H-Index: 17
#2Shu Xiang (TJU: Tianjin University)H-Index: 3
Last. Yuting Su (TJU: Tianjin University)H-Index: 19
view all 5 authors...
2 CitationsSource
123