Zhongfei Zhang
Binghamton University
284 Papers
2.3K Citations
Zhongfei Zhang is an academic researcher from Binghamton University. The author has contributed to research in topics: Computer science & Image retrieval. The author has an hindex of 47, co-authored 280 publications. Previous affiliations of Zhongfei Zhang include University of Warwick & University at Buffalo.
Chat about Author
Papers
A clustering based approach to efficient image retrieval
Ruofei Zhang,Zhongfei Zhang +1 more
- 04 Nov 2002
TL;DR: This paper addresses the issue of effective and efficient content based image retrieval by presenting a novel indexing and retrieval methodology that integrates color, texture, and shape information, and applies these features in regions obtained through unsupervised segmentation, as opposed to applying them to the whole image domain.
•Proceedings Article
Doubly convolutional neural networks
Shuangfei Zhai,Yu Cheng,Weining Lu,Zhongfei Zhang +3 more
- 05 Dec 2016
TL;DR: Doubly convolutional neural networks (DCNNs) as mentioned in this paper maintains groups of filters where filters within each group are translated versions of each other, which significantly improves the performance of CNNs by further exploring this idea.
User-Ranking Video Summarization With Multi-Stage Spatio–Temporal Representation
TL;DR: This paper presents a novel supervised video summarization scheme based on three-stage deep neural networks, and proposes a simple but effective user-ranking method to cope with the labeling subjectivity problem of user-created video summarizations, leading to the labeling quality refinement for robust supervised learning.
54
Celeb-500K: A Large Training Dataset for Face Recognition
Jiajiong Cao,Yingming Li,Zhongfei Zhang +2 more
- 01 Oct 2018
TL;DR: A large training dataset named Celeb-500K for face recognition, which contains 50M images from 500K persons is proposed and extensive experimental results show the superiority of Celeb- 500K and provide a strong support to the two observations.
51
Deep Learning Driven Visual Path Prediction From a Single Image
TL;DR: Wang et al. as discussed by the authors proposed a deep learning framework, which simultaneously performs deep feature learning for visual representation in conjunction with spatiotemporal context modeling, and a unified path-planning scheme is proposed to make accurate path prediction based on the analytic results returned by the deep context models.
47