output
19982026
most citedRecent Advances in Open Set Recognition: A Survey

1k citations

Showing 2021 · cs.CVShow all

13 papers · 2 filters

cs.CV2021★ 6 cited

Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images

Dong Liang, Qixiang Geng, Zongqi Wei +4

Object detection has made tremendous strides in computer vision. Small object detection with appearance degradation is a prominent challenge, especially for aerial observations. To…

cs.CV2021★ 5 cited

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…

cs.CV2021★ 39 cited

Patch-Based Deep Autoencoder for Point Cloud Geometry Compression

Kang You, Pan Gao

The ever-increasing 3D application makes the point cloud compression unprecedentedly important and needed. In this paper, we propose a patch-based compression process using deep le…

cs.CV2021★ 8 cited

Identity-aware Graph Memory Network for Action Detection

Jingcheng Ni, Jie Qin, Di Huang

Action detection plays an important role in high-level video understanding and media interpretation. Many existing studies fulfill this spatio-temporal localization by modeling the…

cs.CV2021★ 1 cited

Small Object Detection Based on Modified FSSD and Model Compression

Qingcai Wang, Hao Zhang, Xianggong Hong +1

Small objects have relatively low resolution, the unobvious visual features which are difficult to be extracted, so the existing object detection methods cannot effectively detect…

cs.CV2021★ 2 cited

MPI: Multi-receptive and Parallel Integration for Salient Object Detection

Han Sun, Jun Cen, Ningzhong Liu +2

The semantic representation of deep features is essential for image context understanding, and effective fusion of features with different semantic representations can significantl…

cs.CV2021★ 38 cited

Partial Domain Adaptation without Domain Alignment

Weikai Li, Songcan Chen

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a well-labeled source domain to a different but related unlabeled target domain with identical label space. Cur…

cs.CV2021★ 13 cited

Detecting Backdoor in Deep Neural Networks via Intentional Adversarial Perturbations

Mingfu Xue, Yinghao Wu, Zhiyu Wu +3

Recent researches show that deep learning model is susceptible to backdoor attacks. Many defenses against backdoor attacks have been proposed. However, existing defense works requi…

cs.CV2021★ 2 cited

Direction-aware Feature-level Frequency Decomposition for Single Image Deraining

Sen Deng, Yidan Feng, Mingqiang Wei +5

We present a novel direction-aware feature-level frequency decomposition network for single image deraining. Compared with existing solutions, the proposed network has three compel…

cs.CV2021★ 1 cited

You Never Cluster Alone

Yuming Shen, Ziyi Shen, Menghan Wang +3

Recent advances in self-supervised learning with instance-level contrastive objectives facilitate unsupervised clustering. However, a standalone datum is not perceiving the context…

cs.CV2021★ 58 cited

Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack

Mengting Xu, Tao Zhang, Zhongnian Li +2

Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images. Recent studies have shown d…

cs.CV2021★ 83 cited

A Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation

Shuren Qi, Yushu Zhang, Chao Wang +2

Image representation is an important topic in computer vision and pattern recognition. It plays a fundamental role in a range of applications towards understanding visual contents.…

cs.CV2021★ 5 cited

Multimodal Gait Recognition for Neurodegenerative Diseases

Aite Zhao, Jianbo Li, Junyu Dong +5

In recent years, single modality based gait recognition has been extensively explored in the analysis of medical images or other sensory data, and it is recognised that each of the…