Learning to Recognize the Unseen Visual Predicates

no code implementations • 25 Sep 2019 • Defa Zhu, Si Liu, Wentao Jiang, Guanbin Li, Tianyi Wu, Guodong Guo

Visual relationship recognition models are limited in the ability to generalize from finite seen predicates to unseen ones.

Question Answering Visual Question Answering +1

UGAN: Untraceable GAN for Multi-Domain Face Translation

no code implementations • 26 Jul 2019 • Defa Zhu, Si Liu, Wentao Jiang, Chen Gao, Tianyi Wu, Qaingchang Wang, Guodong Guo

To address this issue, we propose a method called Untraceable GAN, which has a novel source classifier to differentiate which domain an image is translated from, and determines whether the translated image still retains the characteristics of the source domain.

Image-to-Image Translation Translation

Face Aging with Contextual Generative Adversarial Nets

no code implementations • 1 Feb 2018 • Si Liu, Yao Sun, Defa Zhu, Renda Bao, Wei Wang, Xiangbo Shu, Shuicheng Yan

The age discriminative network guides the synthesized face to fit the real conditional distribution.

Face Verification

Cross-domain Human Parsing via Adversarial Feature and Label Adaptation

no code implementations • 4 Jan 2018 • Si Liu, Yao Sun, Defa Zhu, Guanghui Ren, Yu Chen, Jiashi Feng, Jizhong Han

Our proposed model explicitly learns a feature compensation network, which is specialized for mitigating the cross-domain differences.

Human Parsing