4 papers
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…
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…
HM-Talker: Hybrid Motion Modeling for High-Fidelity Talking Head Synthesis
Shiyu Liu, Kui Jiang, Junjun Jiang +4
Audio-driven talking head generation faces a fundamental trade-off between personalization and generalization, limiting its practical application. Implicit models often achieve gen…
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…