M
Ming Sun
Researcher at SenseTime
Publications - 46
Citations - 1559
Ming Sun is an academic researcher from SenseTime. The author has contributed to research in topics: Object detection & Convolutional neural network. The author has an hindex of 14, co-authored 46 publications receiving 1009 citations. Previous affiliations of Ming Sun include Nankai University & Baidu.
Papers
More filters
Book ChapterDOI
Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition
TL;DR: A novel attention-based convolutional neural network (CNN) which regulates multiple object parts among different input images, which can be easily trained end-to-end, and is highly efficient which requires only one training stage.
Posted Content
Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition
TL;DR: Zhang et al. as mentioned in this paper proposed an attention-based convolutional neural network (CNN) which regulates multiple object parts among different input images, and applied the multi-attention multi-class constraint (MAMC) in a metric learning framework.
Proceedings ArticleDOI
Joint image emotion classification and distribution learning via deep convolutional neural network
Jufeng Yang,Dongyu She,Ming Sun +2 more
TL;DR: This work addresses the problem via label distribution learning and develops a multi-task deep framework by jointly optimizing classification and distribution prediction by exploiting two weak forms of prior knowledge, which are expressed as similarity information between labels, to generate emotional distribution for each category.
Journal ArticleDOI
Visual Sentiment Prediction Based on Automatic Discovery of Affective Regions
TL;DR: This paper investigates the problem of visual sentiment analysis, which involves a high-level abstraction in the recognition process, and proposes a framework to leverage affective regions, which outperforms the state-of-the-art approaches on eight popular benchmark datasets.
Proceedings Article
Compact Generalized Non-local Network
TL;DR: This extension utilizes the compact representation for multiple kernel functions with Taylor expansion that makes the generalized non-local module in a fast and low-complexity computation flow and implements the generalizednon-local method within channel groups to ease the optimization.