Bin Ji

11

Papers

101

Total Citations

Papers (11)

Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style

FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization

FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases

SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering

POMP: Physics-constrainable Motion Generative Model through Phase Manifolds

TDN: Temporal Difference Networks for Efficient Action Recognition

EMMN: Emotional Motion Memory Network for Audio-driven Emotional Talking Face Generation

Towards Verifiable Text Generation with Generative Agent

Say Anything with Any Style

Chain-of-Thought Improves Text Generation with Citations in Large Language Models

TEA: Temporal Excitation and Aggregation for Action Recognition