3 papers
cs.CV2025
Style Quantization for Data-Efficient GAN Training
Jian Wang, Xin Lan, Jizhe Zhou +2
Under limited data setting, GANs often struggle to navigate and effectively exploit the input latent space. Consequently, images generated from adjacent variables in a sparse input…
cs.CV2024
Grounding is All You Need? Dual Temporal Grounding for Video Dialog
You Qin, Wei Ji, Xinze Lan +5
In the realm of video dialog response generation, the understanding of video content and the temporal nuances of conversation history are paramount. While a segment of current rese…
cs.LG2024
MSD: A RG Flow-Based Regularization for GAN Training with Limited Data
Jian Wang, Xin Lan, Yuxin Tian +1
Generative adversarial networks (GANs) have made impressive advances in image generation, but they often require large-scale training data to avoid degradation caused by discrimina…