Search

Multi-modality magnetic resonance imaging data with various sequences facilitate the early diagnosis, tumor segmentation, and disease staging in the management of nasopharyngeal carcinoma (NPC). The lack of publicly available, comprehensive datasets limits advancements in diagnosis, treatment planning, and the development of machine learning algorithms for NPC. Addressing this critical need, we introduce the first comprehensive NPC MRI dataset, encompassing MR axial imaging of 277 primary NPC patients. This dataset includes T1-weighted, T2-weighted, and contrast-enhanced T1-weighted sequences, totaling 831 scans. In addition to the corresponding clinical data, manually annotated and labeled segmentations by experienced radiologists offer high-quality data resources from untreated primary NPC.

In this paper, we present and study a new instance-level retrieval task: PointCloud-Text Matching~(PTM), which aims to find the exact cross-modal instance that matches a given point-cloud query or text query. PTM could be applied to various scenarios, such as indoor/urban-canyon localization and scene retrieval. However, there exists no suitable and targeted dataset for PTM in practice. Therefore, we construct three new PTM benchmark datasets, namely 3D2T-SR, 3D2T-NR, and 3D2T-QA. We observe that the data is challenging and with noisy correspondence due to the sparsity, noise, or disorder of point clouds and the ambiguity, vagueness, or incompleteness of texts, which make existing cross-modal matching methods ineffective for PTM. To tackle these challenges, we propose a PTM baseline, named Robust PointCloud-Text Matching method (RoMa). RoMa consists of two modules: a Dual Attention Perception module (DAP) and a Robust Negative Contrastive Learning module (RNCL). Specifically, DAP leverages token-level and feature-level attention to adaptively focus on useful local and global features, and aggregate them into common representations, thereby reducing the adverse impact of noise and ambiguity. To handle noisy correspondence, RNCL divides negative pairs, which are much less error-prone than positive pairs, into clean and noisy subsets, and assigns them forward and reverse optimization directions respectively, thus enhancing robustness against noisy correspondence. We conduct extensive experiments on our benchmarks and demonstrate the superiority of our RoMa., Comment: Upon further consideration, we have concluded that the current version requires significant revision and may not yet be ready for publication. We plan to conduct additional experiments and make the necessary improvements to ensure the paper meets the standards for future submission

Recently, image-text matching has attracted more and more attention from academia and industry, which is fundamental to understanding the latent correspondence across visual and textual modalities. However, most existing methods implicitly assume the training pairs are well-aligned while ignoring the ubiquitous annotation noise, a.k.a noisy correspondence (NC), thereby inevitably leading to a performance drop. Although some methods attempt to address such noise, they still face two challenging problems: excessive memorizing/overfitting and unreliable correction for NC, especially under high noise. To address the two problems, we propose a generalized Cross-modal Robust Complementary Learning framework (CRCL), which benefits from a novel Active Complementary Loss (ACL) and an efficient Self-refining Correspondence Correction (SCC) to improve the robustness of existing methods. Specifically, ACL exploits active and complementary learning losses to reduce the risk of providing erroneous supervision, leading to theoretically and experimentally demonstrated robustness against NC. SCC utilizes multiple self-refining processes with momentum correction to enlarge the receptive field for correcting correspondences, thereby alleviating error accumulation and achieving accurate and stable corrections. We carry out extensive experiments on three image-text benchmarks, i.e., Flickr30K, MS-COCO, and CC152K, to verify the superior robustness of our CRCL against synthetic and real-world noisy correspondences., Comment: This paper is accepted by NeurIPS 2023

Text-to-image person re-identification (TIReID) is a compelling topic in the cross-modal community, which aims to retrieve the target person based on a textual query. Although numerous TIReID methods have been proposed and achieved promising performance, they implicitly assume the training image-text pairs are correctly aligned, which is not always the case in real-world scenarios. In practice, the image-text pairs inevitably exist under-correlated or even false-correlated, a.k.a noisy correspondence (NC), due to the low quality of the images and annotation errors. To address this problem, we propose a novel Robust Dual Embedding method (RDE) that can learn robust visual-semantic associations even with NC. Specifically, RDE consists of two main components: 1) A Confident Consensus Division (CCD) module that leverages the dual-grained decisions of dual embedding modules to obtain a consensus set of clean training data, which enables the model to learn correct and reliable visual-semantic associations. 2) A Triplet Alignment Loss (TAL) relaxes the conventional Triplet Ranking loss with the hardest negative samples to a log-exponential upper bound over all negative ones, thus preventing the model collapse under NC and can also focus on hard-negative samples for promising performance. We conduct extensive experiments on three public benchmarks, namely CUHK-PEDES, ICFG-PEDES, and RSTPReID, to evaluate the performance and robustness of our RDE. Our method achieves state-of-the-art results both with and without synthetic noisy correspondences on all three datasets. Code is available at https://github.com/QinYang79/RDE.

Recently, uncertainty-aware methods have attracted increasing attention in semi-supervised medical image segmentation. However, current methods usually suffer from the drawback that it is difficult to balance the computational cost, estimation accuracy, and theoretical support in a unified framework. To alleviate this problem, we introduce the Dempster-Shafer Theory of Evidence (DST) into semi-supervised medical image segmentation, dubbed Evidential Inference Learning (EVIL). EVIL provides a theoretically guaranteed solution to infer accurate uncertainty quantification in a single forward pass. Trustworthy pseudo labels on unlabeled data are generated after uncertainty estimation. The recently proposed consistency regularization-based training paradigm is adopted in our framework, which enforces the consistency on the perturbed predictions to enhance the generalization with few labeled data. Experimental results show that EVIL achieves competitive performance in comparison with several state-of-the-art methods on the public dataset.

Information overload is a prevalent challenge in many high-value domains. A prominent case in point is the explosion of the biomedical literature on COVID-19, which swelled to hundreds of thousands of papers in a matter of months. In general, biomedical literature expands by two papers every minute, totalling over a million new papers every year. Search in the biomedical realm, and many other vertical domains is challenging due to the scarcity of direct supervision from click logs. Self-supervised learning has emerged as a promising direction to overcome the annotation bottleneck. We propose a general approach for vertical search based on domain-specific pretraining and present a case study for the biomedical domain. Despite being substantially simpler and not using any relevance labels for training or development, our method performs comparably or better than the best systems in the official TREC-COVID evaluation, a COVID-related biomedical search competition. Using distributed computing in modern cloud infrastructure, our system can scale to tens of millions of articles on PubMed and has been deployed as Microsoft Biomedical Search, a new search experience for biomedical literature: https://aka.ms/biomedsearch., Comment: ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2021 Applied Data Science Track

We consider the problem of intelligent and efficient task allocation mechanism in large-scale mobile edge computing (MEC), which can reduce delay and energy consumption in a parallel and distributed optimization. In this paper, we study the joint optimization model to consider cooperative task management mechanism among mobile terminals (MT), macro cell base station (MBS), and multiple small cell base station (SBS) for large-scale MEC applications. We propose a parallel multi-block Alternating Direction Method of Multipliers (ADMM) based method to model both requirements of low delay and low energy consumption in the MEC system which formulates the task allocation under those requirements as a nonlinear 0-1 integer programming problem. To solve the optimization problem, we develop an efficient combination of conjugate gradient, Newton and linear search techniques based algorithm with Logarithmic Smoothing (for global variables updating) and the Cyclic Block coordinate Gradient Projection (CBGP, for local variables updating) methods, which can guarantee convergence and reduce computational complexity with a good scalability. Numerical results demonstrate the effectiveness of the proposed mechanism and it can effectively reduce delay and energy consumption for a large-scale MEC system., Comment: 15 pages,4 figures, resource management for large-scale MEC. arXiv admin note: text overlap with arXiv:2003.12846

We consider the problem of intelligent and efficient resource management framework in mobile edge computing (MEC), which can reduce delay and energy consumption, featuring distributed optimization and efficient congestion avoidance mechanism. In this paper, we present a Cooperative Learning framework for resource management in MEC from an Alternating Direction Method of Multipliers (ADMM) perspective, called CL-ADMM framework. First, in order to caching task efficiently in a group, a novel task popularity estimating scheme is proposed, which is based on semi-Markov process model, then a greedy task cooperative caching mechanism has been established, which can effectively reduce delay and energy consumption. Secondly, for addressing group congestion, a dynamic task migration scheme based on cooperative improved Q-learning is proposed, which can effectively reduce delay and alleviate congestion. Thirdly, for minimizing delay and energy consumption for resources allocation in a group, we formulate it as an optimization problem with a large number of variables, and then exploit a novel ADMM based scheme to address this problem, which can reduce the complexity of problem with a new set of auxiliary variables, these sub-problems are all convex problems, and can be solved by using a primal-dual approach, guaranteeing its convergences. Then we prove that the convergence by using Lyapunov theory. Numerical results demonstrate the effectiveness of the CL-ADMM and it can effectively reduce delay and energy consumption for MEC., Comment: 17 pages, 11 figures, submitted to journal

Despite a general reduction in smoking in many areas of the developed world, it remains one of the biggest public health threats. As an alternative to tobacco, the use of electronic cigarettes (ECig) has been increased dramatically over the last decade. ECig use is hypothesized to impact smoking behavior through several pathways, not only as a means of quitting cigarettes and lowering risk of relapse, but also as both an alternative nicotine delivery device to cigarettes, as a visible use of nicotine that can lead to imitative behavior in the form of smoking, and as a gateway nicotine delivery technology that can build high levels of nicotine tolerance and pave the way for initiation of smoking. Evidence regarding the effect of ECig use on smoking behavior change remains inconclusive. To address these challenges, we built an agent-based model (ABM) of smoking and ECig use to examine the effects of ECig use on smoking behavior change. The impact of social network (SN) on the initiation of smoking and ECig use were also explored. Findings from the simulation suggest that the use of ECig generates substantially lower prevalence of current smoker (PCS), which demonstrates the potential for reducing smoking and lowering the risk of relapse. The effects of proximity-based influences within SN increases the prevalence of current ECig user (PCEU). The model also suggests the importance of improved understanding of drivers in cessation and relapse in ECig use, in light of findings that such aspects of behavior change may notably influence smoking behavior change and burden., Comment: 10 pages, SBP-BRiMS 2019

Diabetes in pregnancy (DIP) is an increasing public health priority in the Australian Capital Territory, particularly due to its impact on risk for developing Type 2 diabetes. While earlier diagnostic screening results in greater capacity for early detection and treatment, such benefits must be balanced with the greater demands this imposes on public health services. To address such planning challenges, a multi-scale hybrid simulation model of DIP was built to explore the interaction of risk factors and capture the dynamics underlying the development of DIP. The impact of interventions on health outcomes at the physiological, health service and population level is measured. Of particular central significance in the model is a compartmental model representing the underlying physiological regulation of glycemic status based on beta-cell dynamics and insulin resistance. The model also simulated the dynamics of continuous BMI evolution, glycemic status change during pregnancy and diabetes classification driven by the individual-level physiological model. We further modeled public health service pathways providing diagnosis and care for DIP to explore the optimization of resource use during service delivery. The model was extensively calibrated against empirical data., Comment: 10 pages, SBP-BRiMS 2019

Routing in opportunistic networks is a very important and challenging problem because opportunistic network utilizes the contact opportunities of mobile nodes to achieve data communication.Social-based routing uses behavior of human beings which can form a community with the same interests to deliver the message.In this paper,we analyze the drawbacks of the original friendship-based algorithm, which defined social pressure metric to determine nodes'friendship community, but the metric couldn't distinguish the distribution characterization of the connection length which has an important impact on the selection of links with better quality. Further, the existing friendship-based routing doesn't consider the buffer management, which is vital for routing design in opportunistic networks. We propose a New Friendship-based routing with buffer management based on Copy Utility, named NFCU. NFCU algorithm, which not only considers the contact periods in constructing social pressure metric to solve the drawbacks of the original friendship-based routing scheme efficiently, but also considers the buffer management, that can efficiently determine which copy of the message should be deleted timely according to the copy utility function. Our proposed strategy can reduce the network overhead significantly, and increase the message delivery ratio. The extensive simulation results demonstrate that NFCU performs better than the original friendship-based routing. Moreover, we compare NFCU with other four classicalrouting schemes in opportunistic networks in terms of message delivery ratio, average delay, and comprehensive metric- message delivery ratio*(1/average delay). The simulation results show that our scheme NFCU can achieve better performance., Comment: This paper has been withdrawn by the author due to some crucial parameters setting error in experiments

Cognitive radio (CR) has emerged as a promising technology to improve spectrum utilization. Capacity analysis is very useful in investigating the ultimate performance limits for wireless networks. Meanwhile, with increasing potential future applications for the CR systems, it is necessary to explore the limitations on their capacity in a dynamic spectrum access environment. However, due to spectrum sharing in cognitive radio networks (CRNs), the capacity of the secondary network (SRN) is much more difficult to analyze than that of traditional wireless networks. To overcome this difficulty, in this paper we introduce a novel solution based on small world model to analyze the capacity of SRN. First, we propose a new method of shortcut creation for CRNs, which is based on connectivity ratio. Also, a new channel assignment algorithm is proposed, which jointly considers the available time and transmission time of the channels. And then, we derive the capacity of SRN based on the small world model over multi-radio multi-channel (MRMC) environment. The simulation results show that our proposed scheme can obtain a higher capacity and smaller latency compared with traditional schemes in MRMC CRNs., Comment: Wireless Pers Commun(2014)79:2209-2225

Cognitive radio networks (CRNs) have emerged as a promising solution to enhance spectrum utilization by using unused or less used spectrum in radio environments. The basic idea of CRNs is to allow secondary users (SUs) access to licensed spectrum, under the condition that the interference perceived by the primary users (PUs) is minimal. In CRNs, the channel availability is uncertainty due to the existence of PUs, resulting in intermittent communication. Transmission control protocol (TCP) performance may significantly degrade in such conditions. To address the challenges, some transport protocols have been proposed for reliable transmission in CRNs. In this paper we survey the state-of-the-art transport protocols for CRNs. We firstly highlight the unique aspects of CRNs, and describe the challenges of transport protocols in terms of PU behavior, spectrum sensing, spectrum changing and TCP mechanism itself over CRNs. Then, we provide a summary and comparison of existing transport protocols for CRNs. Finally, we discuss several open issues and research challenges. To the best of our knowledge, our work is the first survey on transport protocols for CRNs., Comment: to appear in KSII Transactions on Internet and Information Systems

Cognitive radio (CR) is a promising technology to improve spectrum utilization. However, spectrum availability is uncertain which mainly depends on primary user's (PU's) behaviors. This makes it more difficult for most existing CR routing protocols to achieve high throughput in multi-channel cognitive radio networks (CRNs). Inter-session network coding and opportunistic routing can leverage the broadcast nature of the wireless channel to improve the performance for CRNs. In this paper we present a coding aware opportunistic routing protocol for multi-channel CRNs, cognitive radio opportunistic routing (CROR) protocol, which jointly considers the probability of successful spectrum utilization, packet loss rate, and coding opportunities. We evaluate and compare the proposed scheme against three other opportunistic routing protocols with multichannel. It is shown that the CROR, by integrating opportunistic routing with network coding, can obtain much better results, with respect to throughput, the probability of PU-SU packet collision and spectrum utilization efficiency., Comment: 6 pages, 8 figures, to appear in Proc. of IEEE GlobeCom 2014

In this paper, we consider the joint opportunistic routing and channel assignment problem in multi-channel multi-radio (MCMR) cognitive radio networks (CRNs) for improving aggregate throughput of the secondary users. We first present the nonlinear programming optimization model for this joint problem, taking into account the feature of CRNs-channel uncertainty. Then considering the queue state of a node, we propose a new scheme to select proper forwarding candidates for opportunistic routing. Furthermore, a new algorithm for calculating the forwarding probability of any packet at a node is proposed, which is used to calculate how many packets a forwarder should send, so that the duplicate transmission can be reduced compared with MAC-independent opportunistic routing & encoding (MORE) [11]. Our numerical results show that the proposed scheme performs significantly better that traditional routing and opportunistic routing in which channel assignment strategy is employed., Comment: 5 pages, 4 figures, to appear in Proc. of IEEE GlobeCom 2014