We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
With the success of local features in object recognition, feature-set representations are widely used in computer vision and related domains. Pyramid match kernel (PMK) is an effi...
In this paper, we present an event parsing algorithm based on Stochastic Context Sensitive Grammar (SCSG) for understanding events, inferring the goal of agents, and predicting th...
Mingtao Pei, School of Computer Science, Yunde Jia...
Multi-label learning arises in many real-world tasks where an object is naturally associated with multiple concepts. It is well-accepted that, in order to achieve a good performan...
The innovations and improvements in digital imaging sensors and scanners, computer modeling, haptic equipments and e-learning technology, as well as the availability of many powerf...