AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis
Dongze Li, Kang Zhao, Wei Wang, Bo Peng, Yingya Zhang, Jing Dong, Tieniu Tan.
Association for the Advancement of Artificial Intelligence (AAAI), 2024
About Me
I am currently a member in Computer Vision team of Machine Intelligence Technology division, a branch of Alibaba DAMO Academy. Before that, I got my Master degree from the Computer Science and Engineering Department of Shanghai Jiao Tong University in 2015. My supervisor is Hongtao Lu in the BCMI Lab. And I received the Bachelor degree from the Computer Science and Technology Department of Zhejiang University in 2012, under the supervisor Ruofeng Tong in the GIVE Lab.
My research interests include large-scale visual search, computer vision and machine learning. I particularly focus on AIGC (e.g., Talking Head, Video/Image Generation, 2D/3D Portrait Generation), Large-Scale Model Training (e.g., Extreme Classification, Quantization Training and Communication Optimization), and Large-Scale ANN Search Algorithms (e.g., Quantization, Hashing, Binary Index, GPU Index and Graph-based Search).
News
Selected Publications [full list in Google Scholar]
(* indicates equal contribution)
AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis
Dongze Li, Kang Zhao, Wei Wang, Bo Peng, Yingya Zhang, Jing Dong, Tieniu Tan.
Association for the Advancement of Artificial Intelligence (AAAI), 2024
FaceComposer: A Unified Model for Versatile Facial Content Creation
Jiayu Wang*, Kang Zhao*, Yifeng Ma*, Shiwei Zhang, Yingya Zhang, Yujun Shen, Deli Zhao, Jingren Zhou.
Conference on Neural Information Processing Systems (NeurIPS), 2023.
LipFormer: Talking Face Generation with A Pre-learned Facial Codebook [pdf]
Jiayu Wang, Kang Zhao, Shiwei Zhang, Yingya Zhang, Yujun Shen, Deli Zhao, Jingren Zhou.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
ANN Softmax: Acceleration of Extreme Classification Training [pdf]
Kang Zhao, Liuyihan Song, Yingya Zhang, Pan Pan, Yinghui Xu, Rong Jin.
International Conference on Very Large Data Bases (VLDB), 2022.
Communication Efficient SGD via Gradient Sampling with Bayes Prior [pdf]
Liuyihan Song*, Kang Zhao*, Pan Pan, Yu Liu, Yingya Zhang, Yinghui Xu, Rong Jin.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
Distribution Adaptive INT8 Quantization for Training CNNs [pdf]
Kang Zhao, Sida Huang, Pan Pan, Yinghan Li, Yingya Zhang, Zhenyu Gu, Yinghui Xu.
Association for the Advancement of Artificial Intelligence (AAAI), 2021.
Large-Scale Training System for 100-Million Classification at Alibaba [pdf]
Liuyihan Song, Pan Pan, Kang Zhao, Hao Yang, Yiming Chen, Yingya Zhang, Yinghui Xu, Rong Jin.
International Conference on Knowledge Discovery & Data Mining (SIGKDD), 2020.
Large-Scale Visual Search with Binary Distributed Graph at Alibaba [pdf]
Kang Zhao, Pan Pan, Yun Zheng, Yanhao Zhang, Changxu Wang, Rong Jin.
ACM International Conference on Information and Knowledge Management (CIKM), 2019.
Virtual ID Discovery from E-commerce Media At Alibaba [pdf]
Yanhao Zhang, Pan Pan, Yun Zheng, Kang Zhao, Jianmin Wu, Rong Jin.
ACM International Conference on Information and Knowledge Management (CIKM), 2019.
Visual Search at Alibaba [pdf]
Yanhao Zhang, Pan Pan, Yun Zheng, Kang Zhao, Yingya Zhang, Xiaofeng Ren, Rong Jin.
International Conference on Knowledge Discovery & Data Mining (SIGKDD), 2018.
Unconstrained Quasi-Submodular Function Optimization [pdf]
Jincheng Mei, Kang Zhao, Bao-Liang Lu.
Association for the Advancement of Artificial Intelligence (AAAI), 2015.
Distance preserving marginal hashing for image retrieval [pdf]
Li Wu, Kang Zhao, Hongtao Lu, Zhen Wei, Baoliang Lu.
IEEE International Conference on Multimedia and Expo (ICME), 2015.
Locality Preserving Discriminative Hashing [pdf]
Kang Zhao, Hongtao Lu, Yangcheng He, Shaokun Feng.
ACM International Conference on Multimedia (ACM MM), 2014.
Locality Preserving Hashing [pdf]
Kang Zhao, Hongtao Lu, Jincheng Mei.
Association for the Advancement of Artificial Intelligence (AAAI), 2014.
Honors & Awards