检索结果-内蒙古大学图书馆

Ultra-scalab.e spectral clustering and ensemble clustering

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Huang, Dong Wang, Chang-Dong Wu, Jian-Sheng Lai, Jian-Huang Kwoh, Chee-Keong College of Mathematics and Informatics South China Agricultural University Guangzhou China School of Computer Science and Engineering Nanyang Technological University Singapore Singapore School of Data and Computer Science Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China School of Information Engineering Nanchang University Nanchang China School of Computer Science and Engineering Nanyang Technological University Singapore Singapore

This paper focuses on scalab.lity and robustness of spectral clustering for extremely large-scale datasets with limited resources. Two novel algorithms are proposed, namely, ultra-scalab.e spectral clustering (U-SPEC) and ultra-scalab.e ensemble clustering (U-SENC). In U-SPEC, a hybrid representative selection strategy and a fast approximation method for K-nearest representatives are proposed for the construction of a sparse affinity sub-matrix. By interpreting the sparse sub-matrix as a bipartite graph, the transfer cut is then utilized to efficiently partition the graph and obtain the clustering result. In U-SENC, multiple U-SPEC clusterers are further integrated into an ensemble clustering framework to enhance the robustness of U-SPEC while maintaining high efficiency. Based on the ensemble generation via multiple U-SEPC's, a new bipartite graph is constructed between objects and base clusters and then efficiently partitioned to achieve the consensus clustering result. It is noteworthy that both U-SPEC and U-SENC have nearly linear time and space complexity, and are capable of robustly and efficiently partitioning ten-million-level nonlinearly-separable datasets on a PC with 64GB memory. Experiments on various large-scale datasets have demonstrated the scalab.lity and robustness of our algorithms. The MATlab.code and experimental data are availab.e at https://***/publication/330760669. Copyright © 2019, The Authors. All rights reserved.

关键词： Clustering algorithms

Semantics-Guided Contrastive Network for Zero-Shot Object Detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yan, Caixia Chang, Xiaojun Luo, Minnan Liu, Huan Zhang, Xiaoqin Zheng, Qinghua The Ministry of Education Key Lab of Intelligent Networks and Network Security National Engineering Lab for Big Data Analytics School of Electronic and Information Engineering Xi'an Jiaotong University Shaanxi710049 China The ReLER Lab AAAI Faculty of Engineering and Information Technology University of Technology Sydney Australia The College of Computer Science and Artificial Intelligence Wenzhou University China

Zero-shot object detection (ZSD), the task that extends conventional detection models to detecting objects from unseen categories, has emerged as a new challenge in computer vision. Most existing approaches tackle the ZSD task with a strict mapping-transfer strategy that may lead to suboptimal ZSD results: 1) the learning process of these models neglects the availab.e semantic information on unseen classes, which can easily bias towards the seen categories;2) the original visual feature space is not well-structured for the ZSD task due to the lack of discriminative information. To address these issues, we develop a novel Semantics-Guided Contrastive Network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection. Particularly, ContrastZSD incorporates two semantics-guided contrastive learning subnets that contrast between region-category and region-region pairs respectively. The pairwise contrastive tasks take advantage of supervision signals derived from both the ground truth lab.l and class similarity information. By performing supervised contrastive learning over those explicit semantic supervision, the model can learn more knowledge about unseen categories to avoid the bias problem to seen concepts, while optimizing the visual data structure to be more discriminative for better visual-semantic alignment. Extensive experiments are conducted on two popular benchmarks for ZSD, i.e., PASCAL VOC and MS COCO. Results show that our method outperforms the previous state-of-the-art on both ZSD and generalized ZSD tasks. © 2021, CC BY.

关键词： Object detection

NTIRE 2023 Challenge on Light Field Image Super-Resolution: dataset, Methods and Results

学校读者我要写书评

暂无评论

NTIRE 2023 Challenge on Light Field Image Super-Resolution: ...

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Wang, Yingqian Wang, Longguang Liang, Zhengyu Yang, Jungang Timofte, Radu Guo, Yulan Jin, Kai Wei, Zeqiang Yang, Angulia Guo, Sha Gao, Mingzhi Zhou, Xiuzhuang Van Duong, Vinh Huu, Thuc Nguyen Yim, Jonghoon Jeon, Byeungwoo Liu, Yutong Cheng, Zhen Xiao, Zeyu Xu, Ruikang Xiong, Zhiwei Liu, Gaosheng Jin, Manchang Yue, Huanjing Yang, Jingyu Gao, Chen Zhang, Shuo Chang, Song Lin, Youfang Chao, Wentao Wang, Xuechun Wang, Guanghui Duan, Fuqing Xia, Wang Wang, Yan Xia, Peiqi Wang, Shunzhou Lu, Yao Cong, Ruixuan Sheng, Hao Yang, Da Chen, Rongshan Wang, Sizhe Cui, Zhenglong Chen, Yilei Lu, Yongjie Cai, Dongjun An, Ping Salem, Ahmed Ibrahem, Hatem Yagoub, Bilel Kang, Hyun-Soo Zeng, Zekai Wu, Heng National University of Defense Technology China Aviation University of Air Force China University of Würzburg Germany Eth Zürich Switzerland Sun Yat-sen University The Shenzhen Campus of Sun Yat-sen University China Bigo Technology Pte. Ltd. Singapore Smart Medical Innovation Lab Beijing University of Posts and Telecommunications China Global Explorer Ltd. Suzhou China National Engineering Research Center of Visual Technology School of Computer Science Peking University China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of University of Science and Technology of China China School of Electrical and Information Engineering Tianjin University China Beijing Key Lab of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University China Beijing Normal University China Toronto Metropolitan University Canada Beijing Institute of Technology China Shenzhen MSU-BIT University China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China Beihang Hangzhou Innovation Institute Yuhang China Faculty of Applied Sciences Macao Polytechnic University China School of Communication and Information Engineering Shanghai University China School of Information and Communication Engineering Chungbuk National University Korea Republic of Guangdong University of Technology China

ISBN: (纸本)9798350302493

In this report, we summarize the first NTIRE challenge on light field (LF) image super-resolution (SR), which aims at super-resolving LF images under the standard bicubic degradation with a magnification factor of 4. This challenge develops a new LF dataset called NTIRE-2023 for validation and test, and provides a toolbox called BasicLFSR to facilitate model development. Compared with single image SR, the major challenge of LF image SR lies in how to exploit complementary angular information from plenty of views with varying disparities. In total, 148 participants have registered the challenge, and 11 teams have successfully submitted results with PSNR scores higher than the baseline method LF-InterNet [1]. These newly developed methods have set new state-of-the-art in LF image SR, e.g., the winning method achieves around 1 dB PSNR improvement over the existing state-of-the-art method DistgSSR [2]. We report the solutions proposed by the participants, and summarize their common trends and useful tricks. We hope this challenge can stimulate future research and inspire new ideas in LF image SR. © 2023 IEEE.

关键词： Image enhancement

GM-DF: Generalized Multi-Scenario Deepfake Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lai, Yingxin Yu, Zitong Yang, Jing Li, Bin Kang, Xiangui Shen, Linlin The School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Information Security The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510080 China Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Existing face forgery detection usually follows the paradigm of training models in a single domain, which leads to limited generalization capacity when unseen scenarios and unknown attacks occur. In this paper, we elab.rately investigate the generalization capacity of deepfake detection models when jointly trained on multiple face forgery detection datasets. We first find a rapid degradation of detection accuracy when models are directly trained on combined datasets due to the discrepancy across collection scenarios and generation methods. To address the above issue, a Generalized Multi-Scenario Deepfake Detection framework (GM-DF) is proposed to serve multiple real-world scenarios by a unified model. First, we propose a hybrid expert modeling approach for domain-specific real/forgery feature extraction. Besides, as for the commonality representation, we use CLIP to extract the common features for better aligning visual and textual features across domains. Meanwhile, we introduce a masked image reconstruction mechanism to force models to capture rich forged details. Finally, we supervise the models via a domain-aware meta-learning strategy to further enhance their generalization capacities. Specifically, we design a novel domain alignment loss to strongly align the distributions of the meta-test domains and meta-train domains. Thus, the updated models are able to represent both specific and common real/forgery features across multiple datasets. In consideration of the lack of study of multi-dataset training, we establish a new benchmark leveraging multi-source data to fairly evaluate the models' generalization capacity on unseen scenarios. Both qualitative and quantitative experiments on five datasets conducted on traditional protocols as well as the proposed benchmark demonstrate the effectiveness of our approach. The codes will be availab.e on https://***/laiyingxin2/GM-DF. Copyright © 2024, The Authors. All rights reserved.

关键词： Image reconstruction

Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Dong, Jianfeng Wang, Yabing Chen, Xianke Qu, Xiaoye Li, Xirong He, Yuan Wang, Xun The College of Computer and Information Engineering Zhejiang Gongshang University Hangzhou310035 China The State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China The School of Electronic Information and Communications Huazhong University of Science and Technology Hubei430074 China The Key Lab of Data Engineering and Knowledge Engineering Renmin University of China The AIMC Lab. School of Information Renmin University of China Beijing100872 China The Alibaba Group Beijing100102 China

This paper aims for the task of text-to-video retrieval, where given a query in the form of a natural-language sentence, it is asked to retrieve videos which are semantically relevant to the given query, from a great number of unlab.led videos. The success of this task depends on cross-modal representation learning that projects both videos and sentences into common spaces for semantic similarity computation. In this work, we concentrate on video representation learning, an essential component for text-to-video retrieval. Inspired by the reading strategy of humans, we propose a Reading-strategy Inspired Visual Representation Learning (RIVRL) to represent videos, which consists of two branches: a previewing branch and an intensive-reading branch. The previewing branch is designed to briefly capture the overview information of videos, while the intensive-reading branch is designed to obtain more in-depth information. Moreover, the intensive-reading branch is aware of the video overview captured by the previewing branch. Such holistic information is found to be useful for the intensive-reading branch to extract more fine-grained features. Extensive experiments on three datasets are conducted, where our model RIVRL achieves a new state-of-the-art on TGIF and VATEX. Moreover, on MSR-VTT, our model using two video features shows comparable performance to the state-of-the-art using seven video features and even outperforms models pre-trained on the large-scale HowTo100M dataset. Code is availab.e at https://***/LiJiaBei-7/rivrl. © 2022, CC BY.

关键词： Video recording

Online Attentive Kernel-Based Temporal Difference Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Guang Chen, Xingguo Yang, Shangdong Wang, Huihui Dong, Shaokang Gao, Yang The the Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications National Engineering Laboratory for Agri-Product Quality Traceability Beijing Technology and Business University China The State Key Laboratory for Novel Software Technology Nanjing University China The PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers from complex Value Function Approximation (VFA) and catastrophic interference, creating difficulty for the deep neural network to be applied to an online RL algorithm in a fully online setting. Therefore, a simpler and more adaptive approach is introduced to evaluate value function with the kernel-based model. Sparse representations are superior at handling interference, indicating that competitive sparse representations should be learnable, non-prior, non-truncated and explicit when compared with current sparse representation methods. Moreover, in learning sparse representations, attention mechanisms are utilized to represent the degree of sparsification, and a smooth attentive function is introduced into the kernel-based VFA. In this paper, we propose an Online Attentive Kernel-Based Temporal Difference (OAKTD) algorithm using two-timescale optimization and provide convergence analysis of our proposed algorithm. Experimental evaluations showed that OAKTD outperformed several Online Kernel-based Temporal Difference (OKTD) learning algorithms in addition to the Temporal Difference (TD) learning algorithm with Tile Coding on public Mountain Car, Acrobot, CartPole and Puddle World tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

The Power of Bamboo: On the Post-Compromise security for Searchable Symmetric Encryption

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Tianyang Xu, Peng Picek, Stjepan Luo, Bo Susilo, Willy Jin, Hai Liang, Kaitai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering China Cluster and Grid Computing Lab School of Computer Science and Technology China Huazhong University of Science and Technology Wuhan430074 China Digital Security Group Radboud University Nijmegen Netherlands Department of EECS Institute of Information Sciences The University of Kansas LawrenceKS United States Institute of Cybersecurity and Cryptology School of Computing and Information Technology University of Wollongong WollongongNSW2522 Australia Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft2628 CD Netherlands

Dynamic searchable symmetric encryption (DSSE) enables users to delegate the keyword search over dynamically updated encrypted databases to an honest-but-curious server without losing keyword privacy. This paper studies a new and practical security risk to DSSE, namely, secret key compromise (e.g., a user’s secret key is leaked or stolen), which threatens all the security guarantees offered by existing DSSE schemes. To address this open problem, we introduce the notion of searchable encryption with key-update (SEKU) that provides users with the option of non-interactive key updates. We further define the notion of post-compromise secure with respect to leakage functions to study whether DSSE schemes can still provide data security after the client’s secret key is compromised. We demonstrate that post-compromise security is achievable with a proposed protocol called "Bamboo". Interestingly, the leakage functions of Bamboo satisfy the requirements for both forward and backward security. We conduct a performance evaluation of Bamboo using a real-world dataset and compare its runtime efficiency with the existing forward-and-backward secure DSSE schemes. The result shows that Bamboo provides strong security with better or comparable performance. © 2024, CC BY.

关键词： Bamboo

Rsh-Bu: Revocable Secret Handshakes with Backward Unlinkability from Vlr Group Signatures

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Wen, Yamin Wan, Min Zhao, Junying Gong, Zheng Deng, Yuqiao School of Statistics and Mathematics Guangdong University of Finance and Economics Guangzhou510320 China Guangdong Provincial Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510006 China Big Data and Education Statistics Application Laboratory Guangdong University of Finance and Economics Guangzhou510320 China School of Information Guangdong University of Finance and Economics Guangzhou510320 China School of Computer Science South China Normal University Guangzhou510631 China

Secret handshake scheme is a bi-directional authentication method that enables two participants from the same organization to identify both sides in private. A new generic construction of secret handshakes is proposed in this paper, which is basically derived from verifier-local revocation group signature (VLR-GS). Accordingly, a secret handshake scheme instance is illustrated from a short VLR-GS with backward unlinkability. Our scheme implements an efficient revocation mechanism that also ensures traceability and unlinkability. In addition, the past behaviors of revoked users still keep confidential because of the mechanism of backward unlinkability. We also strengthen the communication protection between Group Authority (GA) and members, such that group members will not be forged by malicious GA. Compared with the previous secret handshake schemes, our scheme greatly reduces the communication and computation overhead, so it is especially suitable for mobile environments. Due to the difficulty of Decision Linear (DLIN) and q-Strong Diffie-Hellman (q-SDH) problems, our proposal can be proved to be secure under the random oracle model. © 2023, The Authors. All rights reserved.

关键词： Authentication

Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fu, Shenghao Yan, Junkai Yang, Qize Wei, Xihan Xie, Xiaohua Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Peng Cheng Laboratory Shenzhen518055 China Tongyi Lab Alibaba Group China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Information Security Technology China Guangdong Guangzhou510555 China

Recent vision foundation models can extract universal representations and show impressive abilities in various tasks. However, their application on object detection is largely overlooked, especially without fine-tuning them. In this work, we show that frozen foundation models can be a versatile feature enhancer, even though they are not pre-trained for object detection. Specifically, we explore directly transferring the high-level image understanding of foundation models to detectors in the following two ways. First, the class token in foundation models provides an in-depth understanding of the complex scene, which facilitates decoding object queries in the detector’s decoder by providing a compact context. Additionally, the patch tokens in foundation models can enrich the features in the detector’s encoder by providing semantic details. Utilizing frozen foundation models as plug-and-play modules rather than the commonly used backbone can significantly enhance the detector’s performance while preventing the problems caused by the architecture discrepancy between the detector’s backbone and the foundation model. With such a novel paradigm, we boost the SOTA query-based detector DINO from 49.0% AP to 51.9% AP (+2.9% AP) and further to 53.8% AP (+4.8% AP) by integrating one or two foundation models respectively, on the COCO validation set after training for 12 epochs with R50 as the detector’s backbone. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding