Chu-Song Chen

10

Papers

59

Total Citations

Papers (10)

SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation

Safety Depth in Large Language Models: A Markov Chain Perspective

Relation-Rich Visual Document Generator for Visual Information Extraction

Aesthetic Critiques Generation for Photos

STR-GQN: Scene Representation and Rendering for Unknown Cameras Based on Spatial Transformation Routing

Class-incremental Continual Learning for Instance Segmentation with Image-level Weak Supervision

Continual Learning for Visual Search With Backward Consistent Feature Embedding

Learning Compact Binary Descriptors With Unsupervised Deep Neural Networks

3D Video Stabilization With Depth Estimation by CNN-Based Optimization

Compacting, Picking and Growing for Unforgetting Continual Learning