3 papers
cs.CV2025
M2DAO-Talker: Harmonizing Multi-granular Motion Decoupling and Alternating Optimization for Talking-head Generation
Kui Jiang, Shiyu Liu, Junjun Jiang +2
Audio-driven talking head generation holds significant potential for film production. While existing 3D methods have advanced motion modeling and content synthesis, they often prod…
cs.CV2025
AHDMIL: Asymmetric Hierarchical Distillation Multi-Instance Learning for Fast and Accurate Whole-Slide Image Classification
Jiuyang Dong, Jiahan Li, Junjun Jiang +2
Although multi-instance learning (MIL) has succeeded in pathological image classification, it faces the challenge of high inference costs due to the need to process thousands of pa…
cs.CV2025
Fast and Accurate Gigapixel Pathological Image Classification with Hierarchical Distillation Multi-Instance Learning
Jiuyang Dong, Junjun Jiang, Kui Jiang +2
Although multi-instance learning (MIL) has succeeded in pathological image classification, it faces the challenge of high inference costs due to processing numerous patches from gi…