Kai Hu

7

Papers

52

Total Citations

Papers (7)

M-LLM Based Video Frame Selection for Efficient Video Understanding

Learning Graph Invariance by Harnessing Spuriosity

Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation

Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution

Explicit Relational Reasoning Network for Scene Text Detection

Completing Visual Objects via Bridging Generation and Segmentation

Empowering Graph Invariance Learning with Deep Spurious Infomax