Publications

SMC++: Masked Learning of Unsupervised Video Semantic Compression
Yuan Tian, Xiaoyue Ling, Cong Geng, Qiang Hu, Guo Lu, and Guangtao Zhai
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2025.

Exploring bidirectional bounds for minimax-training of Energy-based models
Cong Geng, Jia Wang, Li Chen, Zhiyong Gao, Jes Frellsen, and Søren Hauberg
International Journal of Computer Vision (IJCV) 2025.

EBM-WGF: Training energy-based models with Wasserstein gradient flow
Ben Wan*, Cong Geng*, Tianyi Zheng, and Jia Wang
Neural Networks 2025.

Non-uniform Timestep Sampling: Towards Faster Diffusion Model Training
Tianyi Zheng, Cong Geng, Peng-Tao Jiang, Ben Wan, Hao Zhang, Jinwei Chen,
Jia Wang, and Bo Li
ACM Multimedia 2024.

Improving Adversarial Energy-Based Model via Diffusion Process
Cong Geng, Tian Han, Peng-Tao Jiang, Hao Zhang, Jinwei Chen, Søren Hauberg, and Bo Li
International Conference on Machine Learning (ICML) 2024.

Solving the Reconstruction-Generation Trade-Off: Generative Model with Implicit Embedding Learning
Cong Geng, Jia Wang, Li Chen, and Zhiyong Gao
Neurocomputing 2023.

Bounds all Around: Training Energy-based Models with Bidirectional Bounds
Cong Geng, Jia Wang, Zhiyong Gao, Jes Frellsen, and Søren Hauberg
Advances in Neural Information Processing Systems (NeurIPS) 2021.

Omni-GAN: On the Secrets of cGANs and Beyond
Peng Zhou, Lingxi Xie, Bingbing Ni, Cong Geng, and Qi Tian
IEEE International Conference on Computer Vision (ICCV) 2021.

Adversarial Text Image Super-Resolution Using Sinkhorn Distance
Cong Geng, Li Chen, Xiaoyun Zhang, and Zhiyong Gao
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2020.

Wasserstein-Bounded Generative Adversarial Networks
Peng Zhou, Bingbing Ni, Lingxi Xie, Xiaopeng Zhang, Hang Wang, Cong Geng, and Qi Tian
Preprint 2020.

A Wavelet-based Learning for Face Hallucination with Loop Architecture
Cong Geng, Li Chen, Xiaoyun Zhang, Peng Zhou, and Zhiyong Gao
IEEE Visual Communications and Image Processing (VCIP) 2018.