songwang@tju.edu.cn
未公开
教授
面向公共安全的视频信息处理技术研究

---

基于多穿戴式相机的视频行为检测

Learning View-Invariant Features for Person Identification in Temporally Synchronized Videos Taken by Wearable Cameras

---

Co-Saliency Detection within a Single Image

---

SalSAC: A Video Saliency Prediction Model with Shuf？ed Attentions and Correlation-based ConvLSTM

---

Curve-Structure Segmentation from Depth Maps: A CNN-based Approach and Its Application to Exploring Cultural Heritage Objects

---

Dual-Branch Network with a Subtle Motion Detector for Microaction Recognition in Videos

---

Fast Learning of Spatially Regularized and Content Aware Correlation Filter for Visual Tracking

---

Local Pattern Collocations Using Regional Co-Occurrence Factorization

---

Visual-Attention Based Background Modeling for Detecting Infrequently Moving Objects,

---

Cross-Domain Recognition by Identifying Joint Subspaces of Source Domain and Target