541 citations
- Nanyang Technological UniversitySG56 papers
- National University of SingaporeSG46 papers
- Zhejiang UniversityCN43 papers
- Monash UniversityAU29 papers
- Singapore University of Technology and DesignSG21 papers
- Chinese University of Hong KongHK19 papers
- Hong Kong University of Science and TechnologyHK18 papers
- Institute for Infocomm ResearchSG18 papers
- Humboldt-Universität zu BerlinDE15 papers
- Agency for Science, Technology and ResearchSG13 papers
- Alibaba Group (China)CN13 papers
- Carnegie Mellon UniversityUS13 papers
5 papers · 2 filters
FoodAI: Food Image Recognition via Deep Learning for Smart Food Logging
Doyen Sahoo, Wang Hao, Shu Ke +5
An important aspect of health monitoring is effective logging of food consumption. This can help management of diet-related diseases like obesity, diabetes, and even cardiovascular…
Recent Advances in Deep Learning for Object Detection
Xiongwei Wu, Doyen Sahoo, Steven C. H. Hoi
Object detection is a fundamental visual recognition problem in computer vision and has been widely studied in the past decades. Visual object detection aims to find objects of cer…
Prior Activation Distribution (PAD): A Versatile Representation to Utilize DNN Hidden Units
Lakmal Meegahapola, Vengateswaran Subramaniam, Lance Kaplan +1
In this paper, we introduce the concept of Prior Activation Distribution (PAD) as a versatile and general technique to capture the typical activation patterns of hidden layer units…
Distilled Siamese Networks for Visual Tracking
Jianbing Shen, Yuanpei Liu, Xingping Dong +3
In recent years, Siamese network based trackers have significantly advanced the state-of-the-art in real-time tracking. Despite their success, Siamese trackers tend to suffer from…
An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
Yaoyao Liu, Bernt Schiele, Qianru Sun
Few-shot learning aims to train efficient predictive models with a few examples. The lack of training data leads to poor models that perform high-variance or low-confidence predict…