Exposure Trajectory Recovery From Motion Blur

Motion blur in dynamic scenes is an important yet challenging research topic. Recently, deep learning methods have achieved impressive performance for dynamic scene deblurring. However, the motion …

Interaction-Aware Spatio-Temporal Pyramid Attention Networks for Action Class…

For CNN-based visual action recognition, the accuracy may be increased if local key action regions are focused on. The task of self-attention is to focus on key features and ignore irrelevant infor…

Tracking-by-Fusion via Gaussian Process Regression Extended to Transfer Learning

Dual Sticky Hierarchical Dirichlet Process Hidden Markov Model and Its Applic…

Salient Object Detection via Structured Matrix Decomposition

Semi-Supervised Tensor-Based Graph Embedding Learning and Application to Visu…

Single and multiple object tracking using a multi-feature joint sparse repres…

Learning Human Actions by Combining Global Dynamics and Local Appearance

Bin Ratio-Based Histogram Distances and Their Application to Image Classifica…

An Incremental DPMM-Based Method for Trajectory Clustering, Modeling, and Ret…