检索结果-内蒙古大学图书馆

Motion-appearance interactive encoding for object segmentation in unconstrained videos

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Guo, Chunchao Lai, Jianhuang Xie, Xiaohua School of Data and Computer Science Sun Yat-sen University Guangdong Key Laboratory of Information Security Technology Guangzhou510006 China

We present a novel method of integrating motion and appearance cues for foreground object segmentation in unconstrained videos. Unlike conventional methods encoding motion and appearance patterns individually, our method puts particular emphasis on their mutual assistance. Specifically, we propose using an interactively constrained encoding (ICE) scheme to incorporate motion and appearance patterns into a graph that leads to a spatiotemporal energy optimization. The reason of utilizing ICE is that both motion and appearance cues for the same target share underlying correlative structure, thus can be exploited in a deeply collab.rative manner. We perform ICE not only in the initialization but also in the refinement stage of a two-layer framework for object segmentation. This scheme allows our method to consistently capture structural patterns about object perceptions throughout the whole framework. Our method can be operated on superpixels instead of raw pixels to reduce the number of graph nodes by two orders of magnitude. Moreover, we propose to partially explore the multiobject localization problem with inter-occlusion by weighted bipartite graph matching. Comprehensive experiments on three benchmark datasets (i.e., SegTrack, MOViCS, and GaTech) demonstrate the effectiveness of our approach compared with extensive state-of-the-art methods. Copyright © 2017, The Authors. All rights reserved.

关键词： Signal encoding

Twisted-pair superposition transmission

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cai, Suihua Ma, Xiao School of Data and Computer Science Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510006 China

We propose in this paper a new coding scheme called twisted-pair superposition transmission (TPST). The encoding is to "mix together" a pair of basic codes by superposition, while the decoding can be implemented as a successive cancellation list decoding algorithm. The most significant features of the TPST code are its predictable performance that can be estimated numerically from the basic codes and its flexible construction in the sense that it can be easily adapted to different coding rates. To construct good TPST codes in the finite length regime, we propose two design approaches – rate allocation and partial superposition. By taking tail-biting convolutional codes (TBCC) as basic codes, we show by numerical results that the TPST codes can have near-capacity performance in the short length regime. Copyright © 2021, The Authors. All rights reserved.

关键词： Decoding

Systematic convolutional low density generator matrix code

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Cai, Suihua Lin, Wenchao Yao, Xinyuanmeng Wei, Baodian Ma, Xiao School of Data and Computer Science Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510006 China

In this paper, we propose a systematic low density generator matrix (LDGM) code ensemble, which is defined by the Bernoulli process. We prove that, under maximum likelihood (ML) decoding, the proposed ensemble can achieve the capacity of binary-input output symmetric (BIOS) memoryless channels in terms of bit error rate (BER). The proof technique reveals a new mechanism, different from lowering down frame error rate (FER), that the BER can be lowered down by assigning light codeword vectors to light information vectors. The finite length performance is analyzed by deriving an upper bound and a lower bound, both of which are shown to be tight in the high signal-to-noise ratio (SNR) region. To improve the waterfall performance, we construct the systematic convolutional LDGM (SC-LDGM) codes by a random splitting process. The SC-LDGM codes are easily configurable in the sense that any rational code rate can be realized without complex optimization. As a universal construction, the main advantage of the SC-LDGM codes is their near-capacity performance in the waterfall region and predictable performance in the error-floor region that can be lowered down to any target as required by increasing the density of the uncoupled LDGM codes. Numerical results are also provided to verify our analysis. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

The Power of Bamboo: On the Post-Compromise security for Searchable Symmetric Encryption 30

学校读者我要写书评

暂无评论

The Power of Bamboo: On the Post-Compromise Security for Sea...

30th Annual Network and Distributed System security Symposium, NDSS 2023

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

ISBN: (纸本)1891562835

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. © 2023 30th Annual Network and Distributed System security Symposium, NDSS 2023. All Rights Reserved.

关键词：

Statistical learning aided list decoding of semi-random block oriented convolutional codes

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Lin, Wenchao Ma, Xiao Cai, Suihua Wei, Baodian School of Data and Computer Science Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510006 China School of Electronics and Information Technology Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510006 China

In this paper, we propose a statistical learning aided list decoding algorithm, which integrates a serial list Viterbi algorithm (SLVA) with a soft check instead of the conventional cyclic redundancy check (CRC), for semi-random block oriented convolutional codes (SRBO-CCs). The basic idea is that, compared with an erroneous candidate codeword, the correct candidate codeword for the first sub-frame has less effect on the output of Viterbi algorithm (VA) for the second sub-frame. The threshold for testing the correctness of the candidate codeword is then determined by learning the statistical behavior of the introduced empirical divergence function (EDF). With statistical learning aided list decoding, the performance-complexity tradeoff and the performance-delay tradeoff can be achieved by adjusting the statistical threshold and extending the decoding window, respectively. To analyze the performance, a closed-form upper bound and a simulated lower bound are derived. Simulation results verify our analysis and show that: 1) The statistical learning aided list decoding outperforms the sequential decoding in high signal-to-noise ratio (SNR) region;2) under the constraint of equivalent decoding delay, the SRBO-CCs have comparable performance with the polar codes. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolutional codes

Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models 38

学校读者我要写书评

暂无评论

Frozen-DETR: Enhancing DETR with Image Understanding from Fr...

38th Conference on Neural information Processing Systems, NeurIPS 2024

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. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques 38

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-th...

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is availab.e at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features 38

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as D...

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is availab.e at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

A Novel Meta-Hierarchical Active Inference Reinforcement Learning Approach for QoS-Driven Resource Allocation in Dynamic Clouds

学校读者我要写书评

暂无评论

A Novel Meta-Hierarchical Active Inference Reinforcement Lea...

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Xian, Peijie He, Ying Yu, F. Richard Du, Jianbo Shenzhen Univ. College of Computer Science and Software Engineering Shenzhen China Xi'an Univ. of Posts & Telecomm. Shaanxi Key Lab. of Information Comm. Network and Security Shaanxi Xi'an China Carleton Univ. School of Information Technology OttawaON Canada

ISBN: (纸本)9798350351255

The cloud computing environment is highly dynamic due to a variety of external factors such as seasonal changes, market trends, and social events. In this case, tenant behavior patterns exhibit significant variability. Therefore, the cloud computing resource allocation model must continuously adapt to these changes. To this end, we propose an adaptive algorithm for dynamic cloud resource allocation based on meta-hierarchical active inference reinforcement learning (MHAIRL). The algorithm combines active inference with meta-hierarchical reinforcement learning. It improves the overall performance of the algorithm, as well as quickly adapts to environmental changes, and improves the generalization performance. In addition, we design a novel polling scheduling framework combined with long short-term memory (LSTM) network. The framework ensures scheduling fairness and flexibility while greatly reducing the state and action space dimensions of the agent. Extensive simulation results show that our method outperforms baseline algorithms in quality of service (QoS) metrics and significantly improves system performance in highly dynamic cloud resource allocation. © 2024 IEEE.

关键词： Active learning