Yuankai Qi

12

Papers

24

Total Citations

Papers (12)

EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing

Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing

Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning

Incomplete Multi-View Multi-Label Classification via Diffusion-Guided Redundancy Removal

Separation of Powers: On Segregating Knowledge from Observation in LLM-enabled Knowledge-based Visual Question Answering

Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding

Medusa: A Multi-Scale High-order Contrastive Dual-Diffusion Approach for Multi-View Clustering

Generating Synthetic Data for Unsupervised Federated Learning of Cross-Modal Retrieval

Augmented Commonsense Knowledge for Remote Object Grounding

Generating Content for HDR Deghosting from Frequency View

Weakly Supervised Video Individual Counting

Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework