☆ 4.7 Article

U-Turn: Crafting Adversarial Queries with Opposite-Direction Features

INTERNATIONAL JOURNAL OF COMPUTER VISION (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Information Systems

AP-GAN: Adversarial patch attack on content-based image retrieval systems

Guoping Zhao et al.

Summary: This paper discusses the vulnerability of DNN-based image retrieval systems in Smart City applications to adversarial attacks and proposes a novel adversarial patch generative adversarial network (AP-GAN) to generate adversarial patches. The study highlights the importance of considering the security and robustness of image retrieval systems when deploying them.

GEOINFORMATICA (2022)

Add to Collection

Article Automation & Control Systems

Adversarial CAPTCHAs

Chenghui Shi et al.

Summary: This article explores the design of adversarial CAPTCHA by proposing a framework based on state-of-the-art image generation techniques, designing and implementing the aCAPTCHA system, conducting extensive security and usability evaluations, and demonstrating that the generated adversarial CAPTCHAs can significantly enhance the security of normal CAPTCHAs.

IEEE TRANSACTIONS ON CYBERNETICS (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

DST: Dynamic Substitute Training for Data-free Black-box Attack

Wenxuan Wang et al.

Summary: With the increasing applications of deep neural network models in computer vision tasks, it becomes important to study the vulnerability of these models to adversarial examples. Existing methods are limited by the static network structure of the substitute model, whereas the proposed dynamic substitute training attack method allows better learning from the target model.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2022)

Add to Collection

Proceedings Paper Computer Science, Theory & Methods

Person Re-identification Method Based on Color Attack and Joint Defence

Yunpeng Gong et al.

Summary: The main challenges of ReID are the intra-class variations caused by color deviation under different camera conditions. This paper proposes a local transformation attack (LTA) based on color variation, and further proposes a joint adversarial defense (JAD) method including proactive defense and passive defense. Experimental results show that these methods outperform other advanced attack and defense methods.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022 (2022)

Add to Collection

Article Computer Science, Information Systems

Precise No-Reference Image Quality Evaluation Based on Distortion Identification

Chenggang Yan et al.

Summary: This article proposes a novel scheme for precise no-reference image quality assessment, involving distortion identification and targeted quality evaluation. Experimental results show that this method outperforms existing state-of-the-art methods in distortion classification and image quality assessment.

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS (2021)

Add to Collection

Article Computer Science, Information Systems

Depth Image Denoising Using Nuclear Norm and Learning Graph Model

Chenggang Yan et al.

Summary: In this research, a group-based nuclear norm and learning graph (GNNLG) model is proposed for depth image denoising, taking advantage of patch similarity and low-rank property to enhance performance. Experimental results demonstrate that the proposed method outperforms other current state-of-the-art denoising methods in both subjective and objective evaluation.

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Deep High-Resolution Representation Learning for Visual Recognition

Jingdong Wang et al.

Summary: The High-Resolution Network (HRNet) maintains high-resolution representations and exchanges information across resolutions, resulting in superior performance in various applications such as human pose estimation, semantic segmentation, and object detection.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Learning Part-based Convolutional Features for Person Re-Identification

Yifan Sun et al.

Summary: This article focuses on learning discriminative part-informed features for person re-identification, introducing a part-based Convolutional Baseline (PCB) method and refined part pooling (RPP) for more accurate part localization. Experimental results show that RPP boosts the performance of PCB significantly, achieving competitive results on the Market-1501 dataset.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Add to Collection

Article Computer Science, Information Systems

Multiple knowledge representation for big data artificial intelligence: framework, applications, and case studies

Yi Yang et al.

Summary: The paper introduces a multiple knowledge representation (MKR) framework and discusses its potential in developing big data artificial intelligence (AI) techniques. MKR makes current AI techniques more explainable and generalizable, while also expanding current AI techniques to facilitate the mutual benefits of different representations.

FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Deep Multi-View Enhancement Hashing for Image Retrieval

Chenggang Yan et al.

Summary: This paper proposes a novel multi-view hashing learning method, integrating neural networks to enhance retrieval performance significantly. By effectively evaluating view stability and fusing multiple data, relationships between views are explored and advantages are preserved.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Adversarial Metric Attack and Defense for Person Re-Identification

Song Bai et al.

Summary: Recent research has shown that current distance metrics are highly vulnerable to adversarial examples, which may increase security risks in commercial re-identification systems used in video surveillance. Adversarial examples have been rarely studied in metric analysis, possibly due to the natural gap between training and testing. The proposed Adversarial Metric Attack method demonstrates adversarial effects in re-ID systems and presents an early attempt at training a metric-preserving network.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistency

Xueping Wang et al.

Summary: This study proposes a MultiExpert Adversarial Attack Detection (MEAAD) approach to detect adversarial attacks by checking context inconsistency, which is suitable for any DNN-based ReID systems. Extensive experiments show that MEAAD effectively detects various adversarial attacks and achieves high ROC-AUC (over 97.5%).

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Practical Relative Order Attack in Deep Ranking

Mo Zhou et al.

Summary: Recent studies have revealed vulnerabilities in deep ranking systems, leading to a new adversarial attack called the Order Attack. This attack covertly alters the relative order among selected candidates based on an attacker-specified permutation, introducing limited interference to other candidates. A surrogate objective called Short-range Ranking Correlation metric is proposed to approximate the white-box method in a black-box attack scenario.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval

Xiaodan Li et al.

Summary: The paper studies query-based attack against image retrieval and proposes a new relevance-based loss to quantify attack effects, as well as a recursive model stealing method to enhance attack efficiency. Experiments show that the attack achieves a high success rate against image retrieval systems under the black-box setting.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Article Computer Science, Information Systems

VehicleNet: Learning Robust Visual Representation for Vehicle Re-Identification

Zhedong Zheng et al.

Summary: In the context of vehicle re-identification (re-id), learning robust and discriminative visual representation is a fundamental challenge due to significant intra-class variations across different camera views. A new large-scale vehicle dataset called VehicleNet is introduced to address the limitations of existing datasets, with a two-stage progressive approach proposed to improve visual representation learning. Extensive experiments demonstrate the effectiveness of the proposed approach, achieving state-of-the-art accuracy on the AICity Challenge test set and competitive results on other public vehicle re-id datasets.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Deep-Person: Learning discriminative deep features for person Re-Identification

Xiang Bai et al.

PATTERN RECOGNITION (2020)

Add to Collection

Article Computer Science, Information Systems

Deep Metric Learning With Density Adaptivity

Yehao Li et al.

IEEE TRANSACTIONS ON MULTIMEDIA (2020)

Add to Collection

Article Computer Science, Information Systems

Saliency Detection via a Multiple Self-Weighted Graph-Based Manifold Ranking

Cheng Deng et al.

IEEE TRANSACTIONS ON MULTIMEDIA (2020)

Add to Collection

Article Automation & Control Systems

Adversarial Examples for Hamming Space Search

Erkun Yang et al.

IEEE TRANSACTIONS ON CYBERNETICS (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Unsupervised Deep Learning of Compact Binary Descriptors

Kevin Lin et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Fine-Tuning CNN Image Retrieval with No Human Annotation

Filip Radenovic et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Deep Semantic-Preserving Ordinal Hashing for Cross-Modal Similarity Search

Lu Jin et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Face Sketch Synthesis by Multidomain Adversarial Learning

Shengchuan Zhang et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Person Reidentification via Structural Deep Metric Learning

Xun Yang et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Targeted Mismatch Adversarial Attack: Query with a Flower to Retrieve the Tower

Giorgos Tolias et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

Who's Afraid of Adversarial Queries? The Impact of Image Modifications on Content-based Image Retrieval

Zhuoran Liu et al.

ICMR'19: PROCEEDINGS OF THE 2019 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL (2019)

Add to Collection

Article Computer Science, Information Systems

PROVID: Progressive and Multimodal Vehicle Reidentification for Large-Scale Urban Surveillance

Xinchen Liu et al.

IEEE TRANSACTIONS ON MULTIMEDIA (2018)

Add to Collection

Article Computer Science, Artificial Intelligence

Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks

Huei-Fang Yang et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2018)

Add to Collection

Article Computer Science, Artificial Intelligence

Shared Predictive Cross-Modal Deep Quantization

Erkun Yang et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2018)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Features for Multi-Target Multi-Camera Tracking and Re-Identification

Ergys Ristani et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Add to Collection

Article Computer Science, Information Systems

A Discriminatively Learned CNN Embedding for Person Reidentification

Zhedong Zheng et al.

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS (2018)

Add to Collection

Article Computer Science, Artificial Intelligence

Effective Multi-Query Expansions: Collaborative Deep Networks for Robust Landmark Retrieval

Yang Wang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Scalable Person Re-identification on Supervised Smoothed Manifold

Song Bai et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Multi-scale Deep Learning Architectures for Person Re-identification

Xuelin Qian et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Densely Connected Convolutional Networks

Gao Huang et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Person Re-Identification by Deep Learning Multi-Scale Representations

Yanbei Chen et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Neural Codes for Image Retrieval

Artem Babenko et al.

COMPUTER VISION - ECCV 2014, PT I (2014)

Add to Collection

© Peeref 2019-2024. All rights reserved.