27 citations · 127 across the 18 of their papers we have counts for
18 papers
NPF-200: A Multi-Modal Eye Fixation Dataset and Method for Non-Photorealistic Videos
Ziyu Yang, Sucheng Ren, Zongwei Wu +4
Non-photorealistic videos are in demand with the wave of the metaverse, but lack of sufficient research studies. This work aims to take a step forward to understand how humans perc…
RIGID: Recurrent GAN Inversion and Editing of Real Face Videos
Yangyang Xu, Shengfeng He, Kwan-Yee K. Wong +1
GAN inversion is indispensable for applying the powerful editability of GAN to real images. However, existing methods invert video frames individually often leading to undesired in…
DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting
Huilin Zhu, Jingling Yuan, Xian Zhong +3
Domain adaptation is commonly employed in crowd counting to bridge the domain gaps between different datasets. However, existing domain adaptation methods tend to focus on inter-da…
Disentangling Multi-view Representations Beyond Inductive Bias
Guanzhou Ke, Yang Yu, Guoqing Chao +3
Multi-view (or -modality) representation learning aims to understand the relationships between different view representations. Existing methods disentangle multi-view representatio…
Single-View View Synthesis with Self-Rectified Pseudo-Stereo
Yang Zhou, Hanjie Wu, Wenxi Liu +3
Synthesizing novel views from a single view image is a highly ill-posed problem. We discover an effective solution to reduce the learning ambiguity by expanding the single-view vie…
SCANet: Self-Paced Semi-Curricular Attention Network for Non-Homogeneous Image Dehazing
Yu Guo, Yuan Gao, Ryan Wen Liu +4
The presence of non-homogeneous haze can cause scene blurring, color distortion, low contrast, and other degradations that obscure texture details. Existing homogeneous dehazing me…
Curricular Contrastive Regularization for Physics-aware Single Image Dehazing
Yu Zheng, Jiahui Zhan, Shengfeng He +2
Considering the ill-posed nature, contrastive regularization has been developed for single image dehazing, introducing the information from negative images as a lower bound. Howeve…
Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval
Yi Xie, Huaidong Zhang, Xuemiao Xu +2
Previous Knowledge Distillation based efficient image retrieval methods employs a lightweight network as the student model for fast inference. However, the lightweight student mode…
Editing Out-of-domain GAN Inversion via Differential Activations
Haorui Song, Yong Du, Tianyi Xiang +3
Despite the demonstrated editing capacity in the latent space of a pretrained GAN model, inverting real-world images is stuck in a dilemma that the reconstruction cannot be faithfu…
A Simple Data Mixing Prior for Improving Self-Supervised Learning
Sucheng Ren, Huiyu Wang, Zhengqi Gao +4
Data mixing (e.g., Mixup, Cutmix, ResizeMix) is an essential component for advancing recognition models. In this paper, we focus on studying its effectiveness in the self-supervise…
Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting
Zheng Xiong, Liangyu Chai, Wenxi Liu +3
Crowd image is arguably one of the most laborious data to annotate. In this paper, we devote to reduce the massive demand of densely labeled crowd data, and propose a novel weakly-…
High-resolution Face Swapping via Latent Semantics Disentanglement
Yangyang Xu, Bailin Deng, Junle Wang +3
We present a novel high-resolution face swapping method using the inherent prior knowledge of a pre-trained GAN model. Although previous research can leverage generative priors to…
Shunted Self-Attention via Multi-Scale Token Aggregation
Sucheng Ren, Daquan Zhou, Shengfeng He +2
Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of…
From Continuity to Editability: Inverting GANs with Consecutive Images
Yangyang Xu, Yong Du, Wenpeng Xiao +2
Existing GAN inversion methods are stuck in a paradox that the inverted codes can either achieve high-fidelity reconstruction, or retain the editing capability. Having only one of…
Reducing Spatial Labeling Redundancy for Semi-supervised Crowd Counting
Yongtuo Liu, Sucheng Ren, Liangyu Chai +4
Labeling is onerous for crowd counting as it should annotate each individual in crowd images. Recently, several methods have been proposed for semi-supervised crowd counting to red…
Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation
Yongtuo Liu, Dan Xu, Sucheng Ren +3
Due to domain shift, a large performance drop is usually observed when a trained crowd counting model is deployed in the wild. While existing domain-adaptive crowd counting methods…
Unifying Global-Local Representations in Salient Object Detection with Transformer
Sucheng Ren, Qiang Wen, Nanxuan Zhao +2
The fully convolutional network (FCN) has dominated salient object detection for a long period. However, the locality of CNN requires the model deep enough to have a global recepti…
Co-advise: Cross Inductive Bias Distillation
Sucheng Ren, Zhengqi Gao, Tianyu Hua +4
Transformers recently are adapted from the community of natural language processing as a promising substitute of convolution-based neural networks for visual learning tasks. Howeve…