311 citations · 1.1k across the 79 of their papers we have counts for
18 papers · 1 filter
TCOVIS: Temporally Consistent Online Video Instance Segmentation
Junlong Li, Bingyao Yu, Yongming Rao +2
In recent years, significant progress has been made in video instance segmentation (VIS), with many offline and online methods achieving state-of-the-art performance. While offline…
Demystify Transformers & Convolutions in Modern Image Deep Networks
Xiaowei Hu, Min Shi, Weiyun Wang +9
Vision transformers have gained popularity recently, leading to the development of new vision backbones with improved features and consistent performance gains. However, these adva…
Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defense
Bowen Peng, Bo Peng, Jie Zhou +2
Deep Neural Networks (DNNs) based Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) systems have shown to be highly vulnerable to adversarial perturbations that are…
Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-Resolution
Bin Xia, Yapeng Tian, Yucheng Hang +3
Reference-based super-resolution (RefSR) has made significant progress in producing realistic textures using an external reference (Ref) image. However, existing RefSR methods obta…
Efficient Non-Local Contrastive Attention for Image Super-Resolution
Bin Xia, Yucheng Hang, Yapeng Tian +3
Non-Local Attention (NLA) brings significant improvement for Single Image Super-Resolution (SISR) by leveraging intrinsic feature correlation in natural images. However, NLA gives…
Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical
Wanhua Li, Jiwen Lu, Abudukelimu Wuerkaixi +2
In this paper, we investigate the problem of facial kinship verification by learning hierarchical reasoning graph networks. Conventional methods usually focus on learning discrimin…
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
Yongming Rao, Wenliang Zhao, Benlin Liu +3
Attention is sparse in vision transformers. We observe the final prediction in vision transformers is only based on a subset of most informative tokens, which is sufficient for acc…
FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection
Yi Wei, Shang Su, Jiwen Lu +1
In this paper, we investigate the problem of weakly supervised 3D vehicle detection. Conventional methods for 3D object detection need vast amounts of manually labelled 3D data as…
SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation
Jiabin Zhang, Zheng Zhu, Jiwen Lu +3
The practical application requests both accuracy and efficiency on multi-person pose estimation algorithms. But the high accuracy and fast inference speed are dominated by top-down…
Objects are Different: Flexible Monocular 3D Object Detection
Yunpeng Zhang, Jiwen Lu, Jie Zhou
The precise localization of 3D objects from a single image without depth information is a highly challenging problem. Most existing methods adopt the same approach for all objects…
Meta-Mining Discriminative Samples for Kinship Verification
Wanhua Li, Shiwei Wang, Jiwen Lu +2
Kinship verification aims to find out whether there is a kin relation for a given pair of facial images. Kinship verification databases are born with unbalanced data. For a databas…
Structure-Aware Face Clustering on a Large-Scale Graph with Nodes
Shuai Shen, Wanhua Li, Zheng Zhu +4
Face clustering is a promising method for annotating unlabeled face images. Recent supervised approaches have boosted the face clustering accuracy greatly, however their performanc…
Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression
Wanhua Li, Xiaoke Huang, Jiwen Lu +2
Uncertainty is the only certainty there is. Modeling data uncertainty is essential for regression, especially in unconstrained settings. Traditionally the direct regression formula…
Robust Facial Landmark Detection by Cross-order Cross-semantic Deep Network
Jun Wan, Zhihui Lai, Linlin Shen +4
Recently, convolutional neural networks (CNNs)-based facial landmark detection methods have achieved great success. However, most of existing CNN-based facial landmark detection me…
Graph-Based Social Relation Reasoning
Wanhua Li, Yueqi Duan, Jiwen Lu +2
Human beings are fundamentally sociable -- that we generally organize our social lives in terms of relations with other people. Understanding social relations from an image has gre…
Uncertainty-aware Score Distribution Learning for Action Quality Assessment
Yansong Tang, Zanlin Ni, Jiahuan Zhou +4
Assessing action quality from videos has attracted growing attention in recent years. Most existing approaches usually tackle this problem based on regression algorithms, which ign…
Dense Registration and Mosaicking of Fingerprints by Training an End-to-End Network
Zhe Cui, Jianjiang Feng, Jie Zhou
Dense registration of fingerprints is a challenging task due to elastic skin distortion, low image quality, and self-similarity of ridge pattern. To overcome the limitation of hand…
Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification
Yunlong Bian, Chuang Gan, Xiao Liu +7
This paper describes our solution for the video recognition task of ActivityNet Kinetics challenge that ranked the 1st place. Most of existing state-of-the-art video recognition ap…