317 citations · 1.3k across the 37 of their papers we have counts for
37 papers · 1 filter
Variational Relational Point Completion Network for Robust 3D Classification
Liang Pan, Xinyi Chen, Zhongang Cai +4
Real-scanned point clouds are often incomplete due to viewpoint, occlusion, and noise, which hampers 3D geometric modeling and perception. Existing point cloud completion methods t…
Federated Unsupervised Domain Adaptation for Face Recognition
Weiming Zhuang, Xin Gan, Yonggang Wen +3
Given labeled data in a source domain, unsupervised domain adaptation has been widely adopted to generalize models for unlabeled data in a target domain, whose data distributions a…
Pyramid Fusion Transformer for Semantic Segmentation
Zipeng Qin, Jianbo Liu, Xiaolin Zhang +4
The recently proposed MaskFormer gives a refreshed perspective on the task of semantic segmentation: it shifts from the popular pixel-level classification paradigm to a mask-level…
Playing for 3D Human Recovery
Zhongang Cai, Mingyuan Zhang, Jiawei Ren +7
Image- and video-based 3D human recovery (i.e., pose and shape estimation) have achieved substantial progress. However, due to the prohibitive cost of motion capture, existing data…
Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation
Ziniu Wan, Zhengjia Li, Maoqing Tian +3
3D human shape and pose estimation is the essential task for human motion analysis, which is widely used in many 3D applications. However, existing methods cannot simultaneously ca…
GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer
Shuaicheng Li, Qianggang Cao, Lingbo Liu +4
Group activity recognition is a crucial yet challenging problem, whose core lies in fully exploring spatial-temporal interactions among individuals and generating reasonable group…
CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing
Daxuan Ren, Jianmin Zheng, Jianfei Cai +8
Generating an interpretable and compact representation of 3D shapes from point clouds is an important and challenging problem. This paper presents CSG-Stump Net, an unsupervised en…
Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency
Zhipeng Luo, Zhongang Cai, Changqing Zhou +7
Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets. However, drastic performance degradation rema…
Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection
Yinmin Zhang, Xinzhu Ma, Shuai Yi +4
As a crucial task of autonomous driving, 3D object detection has made great progress in recent years. However, monocular 3D object detection remains a challenging problem due to th…
Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification
Zhipeng Luo, Xiaobing Zhang, Shijian Lu +1
Deep learning-based multi-source unsupervised domain adaptation (MUDA) has been actively studied in recent years. Compared with single-source unsupervised domain adaptation (SUDA),…
Delving Deep into the Generalization of Vision Transformers under Distribution Shifts
Chongzhi Zhang, Mingyuan Zhang, Shanghang Zhang +6
Vision Transformers (ViTs) have achieved impressive performance on various vision tasks, yet their generalization under distribution shifts (DS) is rarely understood. In this work,…
Towards Unsupervised Domain Adaptation for Deep Face Recognition under Privacy Constraints via Federated Learning
Weiming Zhuang, Xin Gan, Yonggang Wen +3
Unsupervised domain adaptation has been widely adopted to generalize models for unlabeled data in a target domain, given labeled data in a source domain, whose data distributions d…
Unsupervised 3D Shape Completion through GAN Inversion
Junzhe Zhang, Xinyi Chen, Zhongang Cai +6
Most 3D shape completion approaches rely heavily on partial-complete shape pairs and learn in a fully supervised manner. Despite their impressive performances on in-domain data, wh…
Variational Relational Point Completion Network
Liang Pan, Xinyi Chen, Zhongang Cai +4
Real-scanned point clouds are often incomplete due to viewpoint, occlusion, and noise. Existing point cloud completion methods tend to generate global shape skeletons and hence lac…
Delving into Localization Errors for Monocular 3D Object Detection
Xinzhu Ma, Yinmin Zhang, Dan Xu +4
Estimating 3D bounding boxes from monocular images is an essential component in autonomous driving, while accurate 3D object detection from this kind of data is very challenging. I…
HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identification
Jiawei Ren, Xiao Ma, Chen Xu +2
Person Re-Identification (Re-ID) is of great importance to the many video surveillance systems. Learning discriminative features for Re-ID remains a challenge due to the large vari…
Towards Overcoming False Positives in Visual Relationship Detection
Daisheng Jin, Xiao Ma, Chongzhi Zhang +8
In this paper, we investigate the cause of the high false positive rate in Visual Relationship Detection (VRD). We observe that during training, the relationship proposal distribut…
BiPointNet: Binary Neural Network for Point Clouds
Haotong Qin, Zhongang Cai, Mingyuan Zhang +5
To alleviate the resource constraint for real-time point cloud applications that run on edge devices, in this paper we present BiPointNet, the first model binarization approach for…
BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentation
Xianghui Yang, Bairun Wang, Kaige Chen +4
Few-shot segmentation focuses on the generalization of models to segment unseen object instances with limited training samples. Although tremendous improvements have been achieved,…
Performance Optimization for Federated Person Re-identification via Benchmark Analysis
Weiming Zhuang, Yonggang Wen, Xuesen Zhang +5
Federated learning is a privacy-preserving machine learning technique that learns a shared model across decentralized clients. It can alleviate privacy concerns of personal re-iden…
MessyTable: Instance Association in Multiple Camera Views
Zhongang Cai, Junzhe Zhang, Daxuan Ren +5
We present an interesting and challenging dataset that features a large number of scenes with messy tables captured from multiple camera views. Each scene in this dataset is highly…
Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
Cunjun Yu, Xiao Ma, Jiawei Ren +2
Understanding crowd motion dynamics is critical to real-world applications, e.g., surveillance systems and autonomous driving. This is challenging because it requires effectively m…
Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection
Dongzhan Zhou, Xinchi Zhou, Hongwen Zhang +2
In this paper, we propose a general and efficient pre-training paradigm, Montage pre-training, for object detection. Montage pre-training needs only the target detection dataset wh…
EcoNAS: Finding Proxies for Economical Neural Architecture Search
Dongzhan Zhou, Xinchi Zhou, Wenwei Zhang +4
Neural Architecture Search (NAS) achieves significant progress in many computer vision tasks. While many methods have been proposed to improve the efficiency of NAS, the search pro…