132 citations · 146 across the 6 of their papers we have counts for
6 papers
Image-to-Video Generation via 3D Facial Dynamics
Xiaoguang Tu, Yingtian Zou, Jian Zhao +8
We present a versatile model, FaceAnime, for various video generation tasks from still images. Video generation from a single face image is an interesting problem and usually tackl…
PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment
Kaixin Wang, Jun Hao Liew, Yingtian Zou +2
Despite the great progress made by deep CNNs in image semantic segmentation, they typically require a large number of densely-annotated images for training and are difficult to gen…
Panoptic Edge Detection
Yuan Hu, Yingtian Zou, Jiashi Feng
Pursuing more complete and coherent scene understanding towards realistic vision applications drives edge detection from category-agnostic to category-aware semantic level. However…
Hierarchical Meta Learning
Yingtian Zou, Jiashi Feng
Meta learning is a promising solution to few-shot learning problems. However, existing meta learning methods are restricted to the scenarios where training and application tasks sh…
Better Guider Predicts Future Better: Difference Guided Generative Adversarial Networks
Guohao Ying, Yingtian Zou, Lin Wan +2
Predicting the future is a fantasy but practicality work. It is the key component to intelligent agents, such as self-driving vehicles, medical monitoring devices and robotics. In…
Spatial-Temporal Synergic Residual Learning for Video Person Re-Identification
Xinxing Su, Yingtian Zou, Yu Cheng +3
We tackle the problem of person re-identification in video setting in this paper, which has been viewed as a crucial task in many applications. Meanwhile, it is very challenging si…