D
Donglin Cao
Researcher at Xiamen University
Publications - 55
Citations - 2210
Donglin Cao is an academic researcher from Xiamen University. The author has contributed to research in topics: Sentiment analysis & Image retrieval. The author has an hindex of 14, co-authored 51 publications receiving 1617 citations. Previous affiliations of Donglin Cao include Wuyi University & Minjiang University.
Papers
More filters
Proceedings ArticleDOI
Re-ranking Person Re-identification with k-Reciprocal Encoding
TL;DR: This paper proposes a k-reciprocal encoding method to re-rank the re-ID results, and hypothesis is that if a gallery image is similar to the probe in the k- Reciprocal nearest neighbors, it is more likely to be a true match.
Posted Content
Re-ranking Person Re-identification with k-reciprocal Encoding
TL;DR: Zhang et al. as mentioned in this paper proposed a k-reciprocal encoding method to re-rank the re-ID results under the Jaccard distance, which is based on the assumption that if a gallery image is similar to the probe in the k-receiver nearest neighbors, it is more likely to be a true match.
Journal ArticleDOI
Multi-label learning with label-specific features by resolving label correlations
TL;DR: A new method for the joint learning of label-specific features and label correlations is presented, which involves the design of an optimization framework to learn the weight assignment scheme of features, and the correlations among labels are taken into account by constructing additional features at the same time.
Proceedings ArticleDOI
Microblog Sentiment Analysis Based on Cross-media Bag-of-words Model
TL;DR: A novel Cross-media Bag-of-words Model (CBM) for Microblog sentiment analysis is proposed that represents the text and image of a Weibo tweet as a unified Bag- of-words representation and performs well in the sentiment classification task since it doesn't require the conditional dependence assumption.
Journal ArticleDOI
Predicting Microblog Sentiments via Weakly Supervised Multimodal Deep Learning
TL;DR: A weakly supervised multimodal deep learning scheme toward robust and scalable sentiment prediction that learns convolutional neural networks iteratively and selectively from “weak” emoticon labels, which are cheaply available and noise containing.