Multi-modal Video Chapter Generation.

Real-time water level monitoring using live cameras and computer vision techniques.

Continual Local Replacement for Few-shot Image Recognition.

JigsawNet: Shredded Image Reassembly Using Convolutional Neural Network and Loop-Based Composition.

Learning Continually from Low-shot Data Stream.

Sparse3D: A new global model for matching sparse RGB-D dataset with small inter-frame overlap.