1k citations · 3.9k across the 81 of their papers we have counts for
21 papers · 1 filter
Fully Context-Aware Image Inpainting with a Learned Semantic Pyramid
Wendong Zhang, Yunbo Wang, Bingbing Ni +1
Restoring reasonable and realistic content for arbitrary missing regions in images is an important yet challenging task. Although recent image inpainting models have made significa…
MovieNet-PS: A Large-Scale Person Search Dataset in the Wild
Jie Qin, Peng Zheng, Yichao Yan +3
Person search aims to jointly localize and identify a query person from natural, uncropped images, which has been actively studied over the past few years. In this paper, we delve…
TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification
Yichao Yan, Junjie Li, Shengcai Liao +3
Domain generalizable person re-identification aims to apply a trained model to unseen domains. Prior works either combine the data in all the training domains to capture domain-inv…
Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation
Shanyan Guan, Jingwei Xu, Michelle Z. He +3
We consider a new problem of adapting a human mesh reconstruction model to out-of-domain streaming videos, where performance of existing SMPL-based models are significantly affecte…
CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis
Peng Zhou, Lingxi Xie, Bingbing Ni +1
The style-based GAN (StyleGAN) architecture achieved state-of-the-art results for generating high-quality images, but it lacks explicit and precise control over camera poses. The r…
MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
Jiancheng Yang, Rui Shi, Donglai Wei +5
We introduce MedMNIST v2, a large-scale MNIST-like dataset collection of standardized biomedical images, including 12 datasets for 2D and 6 datasets for 3D. All images are pre-proc…
RibSeg Dataset and Strong Point Cloud Baselines for Rib Segmentation from CT Scans
Jiancheng Yang, Shixuan Gu, Donglai Wei +2
Manual rib inspections in computed tomography (CT) scans are clinically critical but labor-intensive, as 24 ribs are typically elongated and oblique in 3D volumes. Automatic rib se…
Asymmetric 3D Context Fusion for Universal Lesion Detection
Jiancheng Yang, Yi He, Kaiming Kuang +3
Modeling 3D context is essential for high-performance 3D medical image analysis. Although 2D networks benefit from large-scale 2D supervised pretraining, it is weak in capturing 3D…
Energy Attack: On Transferring Adversarial Examples
Ruoxi Shi, Borui Yang, Yangzhou Jiang +2
In this work we propose Energy Attack, a transfer-based black-box -adversarial attack. The attack is parameter-free and does not require gradient approximation. In partic…
Cross-category Video Highlight Detection via Set-based Learning
Minghao Xu, Hang Wang, Bingbing Ni +3
Autonomous highlight detection is crucial for enhancing the efficiency of video browsing on social media platforms. To attain this goal in a data-driven way, one may often face the…
Object Wake-up: 3D Object Rigging from a Single Image
Ji Yang, Xinxin Zuo, Sen Wang +5
Given a single image of a general object such as a chair, could we also restore its articulated 3D shape similar to human modeling, so as to animate its plausible articulations and…
Context-Aware Image Inpainting with Learned Semantic Priors
Wendong Zhang, Junwei Zhu, Ying Tai +5
Recent advances in image inpainting have shown impressive results for generating plausible visual details on rather simple backgrounds. However, for complex scenes, it is still cha…
SimSwap: An Efficient Framework For High Fidelity Face Swapping
Renwang Chen, Xuanhong Chen, Bingbing Ni +1
We propose an efficient framework, called Simple Swap (SimSwap), aiming for generalized and high fidelity face swapping. In contrast to previous approaches that either lack the abi…
Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement
Zefan Li, Chenxi Liu, Alan Yuille +3
Unsupervised learning methods have recently shown their competitiveness against supervised training. Typically, these methods use a single objective to train the entire network. Bu…
Self-supervised Graph-level Representation Learning with Local and Global Structure
Minghao Xu, Hang Wang, Bingbing Ni +2
This paper studies unsupervised/self-supervised whole-graph representation learning, which is critical in many tasks such as molecule properties prediction in drug and material dis…
X-volution: On the unification of convolution and self-attention
Xuanhong Chen, Hang Wang, Bingbing Ni
Convolution and self-attention are acting as two fundamental building blocks in deep neural networks, where the former extracts local image features in a linear way while the latte…
Exploring Visual Context for Weakly Supervised Person Search
Yichao Yan, Jinpeng Li, Shengcai Liao +4
Person search has recently emerged as a challenging task that jointly addresses pedestrian detection and person re-identification. Existing approaches follow a fully supervised set…
3D Human Action Representation Learning via Cross-View Consistency Pursuit
Linguo Li, Minsi Wang, Bingbing Ni +3
In this work, we propose a Cross-view Contrastive Learning framework for unsupervised 3D skeleton-based action Representation (CrosSCLR), by leveraging multi-view complementary sup…
Learning Multi-Attention Context Graph for Group-Based Re-Identification
Yichao Yan, Jie Qin, Bingbing Ni +6
Learning to re-identify or retrieve a group of people across non-overlapped camera systems has important applications in video surveillance. However, most existing methods focus on…
Graphical Modeling for Multi-Source Domain Adaptation
Minghao Xu, Hang Wang, Bingbing Ni
Multi-Source Domain Adaptation (MSDA) focuses on transferring the knowledge from multiple source domains to the target domain, which is a more practical and challenging problem com…
Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction
Shanyan Guan, Jingwei Xu, Yunbo Wang +2
This paper considers a new problem of adapting a pre-trained model of human mesh reconstruction to out-of-domain streaming videos. However, most previous methods based on the param…