59 citations · 446 across the 85 of their papers we have counts for
9 papers · 1 filter
Identity-guided Face Generation with Multi-modal Contour Conditions
Qingyan Bai, Weihao Xia, Fei Yin +1
Recent face generation methods have tried to synthesize faces based on the given contour condition, like a low-resolution image or sketch. However, the problem of identity ambiguit…
Guiding Topic Flows in the Generative Chatbot by Enhancing the ConceptNet with the Conversation Corpora
Pengda Si, Yao Qiu, Jinchao Zhang +1
Human conversations consist of reasonable and natural topic flows, which are observed as the shifts of the mentioned concepts across utterances. Previous chatbots that incorporate…
Real-time Human-Centric Segmentation for Complex Video Scenes
Ran Yu, Chenyu Tian, Weihao Xia +3
Most existing video tasks related to "human" focus on the segmentation of salient humans, ignoring the unspecified others in the video. Few studies have focused on segmenting and t…
PoseDet: Fast Multi-Person Pose Estimation Using Pose Embedding
Chenyu Tian, Ran Yu, Xinyuan Zhao +3
Current methods of multi-person pose estimation typically treat the localization and the association of body joints separately. It is convenient but inefficient, leading to additio…
Coarse-to-Fine Searching for Efficient Generative Adversarial Networks
Jiahao Wang, Han Shu, Weihao Xia +2
This paper studies the neural architecture search (NAS) problem for developing efficient generator networks. Compared with deep models for visual recognition tasks, generative adve…
Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation
Gengcong Yang, Jingyi Zhang, Yong Zhang +2
To generate "accurate" scene graphs, almost all existing methods predict pairwise relationships in a deterministic manner. However, we argue that visual relationships are often sem…
AACP: Model Compression by Accurate and Automatic Channel Pruning
Lanbo Lin, Yujiu Yang, Zhenhua Guo
Channel pruning is formulated as a neural architecture search (NAS) problem recently. However, existing NAS-based methods are challenged by huge computational cost and inflexibilit…
Augmenting Proposals by the Detector Itself
Xiaopei Wan, Zhenhua Guo, Chao He +2
Lacking enough high quality proposals for RoI box head has impeded two-stage and multi-stage object detectors for a long time, and many previous works try to solve it via improving…
GAN Inversion: A Survey
Weihao Xia, Yulun Zhang, Yujiu Yang +3
GAN inversion aims to invert a given image back into the latent space of a pretrained GAN model, for the image to be faithfully reconstructed from the inverted code by the generato…