RESEARCH PROJECTS
Saliency prediction on natural images [code]
A saliency detection method using a novel feature on sparse representation of learnt texture atoms (SR-LTA), which are encoded in salient and non-salient dictionaries. A online salient dictionary learning (OSDL) algorithm is provided to solve the proposed formulation.
Compressed domain method for video saliency prediction [code]
We argue that the state-of-the-art high efficiency video coding (HEVC) standard can be used to generate the useful features in compressed domain. Several features in HEVC domain are proposed on the basis of splitting depth, bit allocation, and MV. Next, a kind of support vector machine (SVM) is learned to integrate those HEVC features together, for video saliency detection.
OM-CNN and 2C-LSTM for video saliency prediction [code]
A novel DNN-based video saliency prediction method. Specifically, we propose an object-to-motion convolutional neural network (OM-CNN) to learn spatio-temporal features for predicting the intra-frame saliency via exploring the information of both objectness and object motion. Also, we develop a two-layer convolutional long short-term memory (2C-LSTM) network for predicting the inter-frame saliency, considering the transition of attention across video frames.