Chenliang Xu

pic

I'm grateful to the following entities for their support of my research:

Current Projects:

Automated Video Description for Blind and Low Vision Users

Perceptually-enabled Task Guidance

Egocentric 3D Audio-Visual Scene Understanding

Identify Hidden Biases of AI Algorithms

Inferring Lattice Dynamics from Temporal X-ray Diffraction Data

Time-resolved Classification of X-ray Diffraction Data


Past Projects:

Audio-Visual Scene Understanding

Learning Dynamics and Evolution towards Cognitive Understanding of Videos

Scalable Deep Bayesian Tensor Decomposition

Applying Video Segmentation to CG Mapping Operators in Molecular Simulations

Cross-Modal Audio-Visual Generation

Video-To-Text Summarization

Actor-Action Video Understanding

Perceptual Analysis of Semantic Retention in Video Segmentation

Supervoxels: Toward an Efficient Hierarchical Video Representation