Multimodal sentiment analysis (MSA) aims to infer emotional states by effectively integrating textual, acoustic, and visual modalities. Despite notable progress, existing multimodal fusion methods often neglect modality-specific structural dependencies and semantic misalignment, limiting their quality, interpretability, and robustness. To address these challenges, we propose a novel framework called the Structural-Semantic Unifier (SSU), which systematically integrates modality-specific structural information and cross-modal semantic grounding for enhanced multimodal representations. Specifically, SSU dynamically constructs modality-specific graphs by leveraging linguistic syntax for text and a lightweight, text-guided attention mechanism for acoustic and visual modalities, thus capturing detailed intra-modal relationships and semantic interactions. We further introduce a semantic anchor, derived from global textual semantics, that serves as a cross-modal alignment hub, effectively harmonizing heterogeneous semantic spaces across modalities. Additionally, we develop a multi-view contrastive learning objective that promotes discriminability, semantic consistency, and structural coherence across intra- and inter-modal views. Extensive evaluations on two widely-used benchmark datasets, CMU-MOSI and CMU-MOSEI, demonstrate that SSU consistently achieves state-of-the-art performance while significantly reducing computational overhead compared to prior methods. Comprehensive qualitative analyses further validate SSU’s interpretability and its ability to capture nuanced emotional patterns through semantically-grounded interactions.

Human-defined creativity is highly abstract, posing a challenge for multimodal large language models (MLLMs) to comprehend and assess creativity that aligns with human judgments. The absence of an existing benchmark further exacerbates this dilemma. To this end, we propose CreBench, which consists of two key components: 1) an evaluation benchmark covering the multiple dimensions from creative idea to process to products; 2) CreMIT (Creativity Multimodal Instruction Tuning dataset), a multimodal creativity evaluation dataset, consisting of 2.2K diverse-sourced multimodal data, 79.2K human feedbacks and 4.7M multityped instructions. Specifically, to ensure MLLMs can handle diverse creativity-related queries, we prompt GPT to refine the human feedback to activate stronger creativity assessment capabilities. CreBench serves as a foundation for building MLLMs that understand human-aligned creativity. Based on the CreBench, we fine-tune open-source general MLLMs, resulting in CreExpert, a multimodal creativity evaluation expert model. Extensive experiments demonstrate that the proposed CreExpert models achieve significantly better alignment with human creativity evaluation compared to state-ofthe-art MLLMs, including the most advanced GPT-4V and Gemini-Pro-Vision.

Cross-domain adaptation has achieved significant development in recent years. Nevertheless, the models' performance varies dramatically across different scenarios. How to quantitatively measure inter-domain discrepancies to guide model training remains a challenging problem. Existing methods mainly focus on the trivial pixel-wise differences between the cross domain images, while they ignore the holistic discrepancies of the domain-specific distributions in various scenarios. Thus their effectivenesses are greatly limited in realistic applications. In this paper, we propose a universal method for measuring inter domain discrepancies based on Wasserstein distance. It alleviates the impact of intra-domain discrepancies on measurements and enables precise and quantitative representation of inter-domain discrepancies. We further integrate this metric into the generative models, and propose an assistant domain to conduct domain knowledge transfer for cross-domain object detection task. Experiments on three benchmarks validate the effectiveness of the proposed inter-domain measurement metric. Specifically, we achieve 51.8% mAP on CityScapes, 45.3% mAP on Clipart and 58.9% mAP on Watercolor, which are 1.5%, 0.5% and 0.8% higher than the state-of-the-art schemes, respectively.

Cross-modal retrieval maps data under different modalities via semantic relevance. Existing approaches implicitly assume that data pairs are well-aligned and ignore the widely existing annotation noise, i.e., noisy correspondence (NC). Consequently, it inevitably causes performance degradation. Despite attempts that employ the co-teaching paradigm with identical architectures to provide distinct data perspectives, the differences between these architectures primarily stem from random initialization. Thus, the model becomes increasingly homogeneous along with the training process. Consequently, the additional information brought by this paradigm is severely limited. In order to resolve this problem, we introduce Tripartite Learning with Semantic Variation Consistency (TSVC) for robust image-text retrieval. We design a tripartite cooperative learning mechanism comprising a Coordinator, a Master, and an Assistant model. The Coordinator distributes data, and the Assistant model supports the Master model's noisy label prediction with diverse data. Moreover, we introduce a soft label estimation method based on mutual information variation, which quantifies the noise in new samples and assigns corresponding soft labels. We also present a new loss function to enhance robustness and optimize training effectiveness. Extensive experiments on three widely used datasets demonstrate that, even at increasing noise ratios, TSVC exhibits significant advantages in retrieval accuracy and maintains stable training performance.

Session-Based Recommendation (SBR) based on Graph Neural Networks (GNN) has become a new paradigm for recommender systems, and plays a fundamental role in e-commerce and other relevant domains. Existing graph aggregation methods primarily form node representations by capturing basic relationships between neighboring and central nodes. Despite their encouraging results, the global relationships of items and user intentions within sessions typically change over time, which degrades the effectiveness of existing embedding schemes. To resolve this challenge, we propose a Long and Short-Term Temporal Graph Neural Network (LS-TGNN) for SBR. LS-TGNN employs a novel temporal session graph to aggregate neighborhood information, and models user interests from both long and short-term perspectives. Specifically, we design long-term and short-term encoders to model the long and short-term interests of users, respectively. In order to better model the interests of users in different time dimensions, we introduce an item-granularity method that distinguishes between long and short-term interests. Extensive experiments on three widely used datasets demonstrate that LS-TGNN outperforms existing methods with a large margin.

Training on diverse, internet-scale data is a key factor in the success of recent large foundation models. Yet, using the same recipe for building embodied agents has faced noticeable difficulties. Despite the availability of many crowd-sourced embodied datasets, their action spaces often exhibit significant heterogeneity due to distinct physical embodiment and control interfaces for different robots, causing substantial challenges in developing embodied foundation models using cross-domain data. In this paper, we introduce UniAct, a new embodied foundation modeling framework operating in a Universal Act ion Space. Our learned universal actions capture the generic atomic behaviors across diverse robots by exploiting their shared structural features, and enable enhanced cross-domain data utilization and cross-embodiment generalizations by eliminating the notorious heterogeneity. The universal actions can be efficiently translated back to heterogeneous actionable commands by simply adding embodiment-specific details, from which fast adaptation to new robots becomes simple and straightforward. Our 0.5B instantiation of Uni-Act reaches 14X larger SOTA embodied foundation models in extensive evaluations on various real-world and simulation robots, showcasing exceptional cross-embodiment control and adaptation capability, highlighting the crucial benefit of adopting universal actions. Project page: https://2toinf.github.io/UniAct/

Multimodal 3D object detection has garnered considerable interest in autonomous driving. However, multimodal detectors suffer from dimension mismatches that derive from fusing 3D points with 2D pixels coarsely, which leads to suboptimal fusion performance. In this paper, we propose a multimodal framework FGU3R to tackle the issue mentioned above via unified 3D representation and fine-grained fusion, which consists of two important components. First, we propose an efficient feature extractor for raw and pseudo points, termed Pseudo-Raw Convolution (PRConv), which modulates multimodal features synchronously and aggregates the features from different types of points on key points based on multimodal interaction. Second, a Cross-Attention Adaptive Fusion (CAAF) is designed to fuse homogeneous 3D RoI (Region of Interest) features adaptively via a cross-attention variant in a fine-grained manner. Together they make fine-grained fusion on unified 3D representation. The experiments conducted on the KITTI and nuScenes show the effectiveness of our proposed method.

Current robotic planning methods often rely on predicting multi-frame images with full pixel details. While this fine-grained approach can serve as a generic world model, it introduces two significant challenges for downstream policy learning: substantial computational costs that hinder real-time deployment, and accumulated inaccuracies that can mislead action extraction. Planning with coarse-grained subgoals partially alleviates efficiency issues. However, their forward planning schemes can still result in off-task predictions due to accumulation errors, leading to misalignment with long-term goals. This raises a critical question: Can robotic planning be both efficient and accurate enough for real-time control in long-horizon, multi-stage tasks? To address this, we propose a **B**ackward **P**lanning scheme in **L**atent space (**LBP**), which begins by grounding the task into final latent goals, followed by recursively predicting intermediate subgoals closer to the current state. The grounded final goal enables backward subgoal planning to always remain aware of task completion, facilitating on-task prediction along the entire planning horizon. The subgoal-conditioned policy incorporates a learnable token to summarize the subgoal sequences and determines how each subgoal guides action extraction. Through extensive simulation and real-robot long-horizon experiments, we show that LBP outperforms existing fine-grained and forward planning methods, achieving SOTA performance. Project Page: [https://lbp-authors.github.io](https://lbp-authors.github.io).

Emotion recognition from EEG signals is crucial for understanding complex brain dynamics. Existing methods typically rely on static frequency bands and graph convolutional networks (GCNs) to model brain connectivity. However, EEG signals are inherently non-stationary and exhibit substantial individual variability, making static-band approaches inadequate for capturing their dynamic properties. Moreover, spatial-temporal dependencies in EEG often lead to feature degradation during node aggregation, ultimately limiting recognition performance. To address these challenges, we propose the Spatial-Temporal Electroencephalograph Collaboration framework (Stella). Our approach introduces an Adaptive Bands Selection module (ABS) that dynamically extracts low- and high-frequency components, generating dual-path features comprising phase brain networks for connectivity modeling and time-series representations for local dynamics. To further mitigate feature degradation, the Fourier Graph Operator (FGO) operates in the spectral domain, while the Spatial-Temporal Encoder (STE) enhances representation stability and density. Extensive experiments on benchmark EEG datasets demonstrate that Stella achieves state-of-the-art performance in emotion recognition, offering valuable insights for graph-based modeling of non-stationary neural signals. The code is available at https://github.com/sun2017bupt/EEGBrainNetwork.

Recently, LiDAR-based fully sparse 3D object detection has gained great attention, which utilizes point clouds to boost efficiency. Nevertheless, the relationship between well-studied dense representation and fully sparse representation is under-explored in existing studies, which focuses solely on building sparse representation by feature diffusion to solve the notorious center point missing problem. To this end, we propose a dense-guided fully sparse detection scheme, named DGFSD, to bridge the gap between dense and sparse features by dense-guided diffusion. Different from prior studies, we propose DgD (Dense-guided Diffusion) to overcome the center feature missing problem by dense knowledge transferring. Specifically, DgD transfers high-quality central point features from dense representations to endow sparse representations with dense knowledge. Moreover, we customize DFW (Dense Feature Weighting) to express uninformative representation and lift foreground representation. It makes high-quality dense feature contribute more to arcuate regression. To the best of our knowledge, we are the first to explore dense knowledge's impact on fully sparse framework. Extensive experiments conducted on nuScenes and Argoverse2 benchmark demonstrate the effectiveness of the proposed method. Specifically, DGFSD achieves 71.6% NDS and 67.3% mAP on the nuScenes test benchmark. On Argoverse2, DGFSD achieves 40.6% mAP, outperforming previous best hybrid and fully sparse methods. The code is available at https://github.com/Raiden-cn/DGFSD.

Acquiring reviewers for academic submissions is a challenging recommendation scenario. Recent graph learning-driven models have made remarkable progress in the field of recommendation, but their performance in the academic reviewer recommendation task may suffer from a significant false negative issue. This arises from the assumption that unobserved edges represent negative samples. In fact, the mechanism of anonymous review results in inadequate exposure of interactions between reviewers and submissions, leading to a higher number of unobserved interactions compared to those caused by reviewers declining to participate. Therefore, investigating how to better comprehend the negative labeling of unobserved interactions in academic reviewer recommendations is a significant challenge. This study aims to tackle the ambiguous nature of unobserved interactions in academic reviewer recommendations. Specifically, we propose an unsupervised Pseudo Neg-Label strategy to enhance graph contrastive learning (GCL) for recommending reviewers for academic submissions, which we call RevGNN. RevGNN utilizes a two-stage encoder structure that encodes both scientific knowledge and behavior using Pseudo Neg-Label to approximate review preference. Extensive experiments on three real-world datasets demonstrate that RevGNN outperforms all baselines across four metrics. Additionally, detailed further analyses confirm the effectiveness of each component in RevGNN.

Accurate matching between user and candidate news plays a fundamental role in news recommendation. Most existing studies capture fine-grained user interests through effective user modeling. Nevertheless, user interest representations are often extracted from multiple history news items, while candidate news representations are learned from specific news items. The asymmetry of information density causes invalid matching of user interests and candidate news, which severely affects the click-through rate prediction for specific candidate news. To resolve the problems mentioned above, we propose a symmetrical information interaction modeling for news recommendation (SIIR) in this article. We first design a light interactive attention network for user (LIAU) modeling to extract user interests related to the candidate news and reduce interference of noise effectively. LIAU overcomes the shortcomings of complex structure and high training costs of conventional interaction-based models and makes full use of domain-specific interest tendencies of users. We then propose a novel heterogeneous graph neural network (HGNN) to enhance candidate news representation through the potential relations among news. HGNN builds a candidate news enhancement scheme without user interaction to further facilitate accurate matching with user interests, which mitigates the cold-start problem effectively. Experiments on two realistic news datasets, i.e., MIND and Adressa, demonstrate that SIIR outperforms the state-of-the-art (SOTA) single-model methods by a large margin.

Session-based recommendation plays a critical role in a number of scenarios, e.g., e-commerce, which predicts user behavior based on sessions. The primary challenge is to match user interests and candidate items accurately. Existing studies mainly learn the representation of session items and candidate items independently, and aggregate session representations through an attention mechanism. Nevertheless, user interests are usually cross-domain, and the characteristics of the items are also multifactorial. Fixed session and candidate item representations lead to suboptimal matching. To some extent, it limits the representation capability of the model. In this paper, we present an Interaction Graph Neural Network with Fine-grained Matching, named FM-IGNN, for session-based recommendation. It incorporates interactive features into item and session modeling to match candidate items and user interests more accurately. We first propose an Interaction Graph Neural Network(IGNN) to learn candidate-aware session item representation and session-aware candidate item representation interactively. We then design a Fine-grained interest Matching (FM) framework to learn user interests related to candidate items, and calculate the matching scores of users and candidate items at multi-levels. Experiments on three benchmark datasets demonstrate that FM-IGNN outperforms the state-of-the-art(SOTA) schemes with a large margin. Specifically, on the Tmall dataset, it achieves relative improvement of up to 20.54%, 16.07%, 13.41%, and 15.52% on the Precision@10, MRR@10, Precision@20, and MRR@20, respectively.

With the large-scale commercialization of 5G networks, Internet of Things (IoT) applications keep on emerging in recent years. Real-time environmental awareness is an essential part of various IoT applications, e.g., self-driving vehicles. Object detection plays a fundamental role in real-time environmental awareness, which is responsible for acquiring valuable object information from the environment automatically. Despite of the fast progress for object detection in general, small object detection still faces challenges. Because of the restricted scales, small objects are only capable of generating relatively week features after multiple convolutional layers, thus causing low detection accuracy. Existing schemes mostly focus on extracting rich multiscale features, e.g., generating high-resolution features through generative adversarial networks (GANs), or generating multiscale features through feature combination. Nevertheless, these schemes require complex network implementation, and usually suffer from high processing delay because of high-resolution images. To resolve the problems mentioned above, we propose an adaptive dynamic neural network (AD-RCNN) that consists of three fundamental improvements. We first propose a dynamic region proposal network to improve the quality of region proposals. We then introduce a visual attention scheme to generate features of regions. Finally, we put forward an adaptive dynamic training module to optimize final detection results. Experimental results demonstrate that AD-RCNN outperforms the state-of-the-art from the perspectives of mAP and frames per second (FPS). Specifically, at the resolution of 1024 of TT100K data set, AD-RCNN achieves 68.8% mAP, which outperforms the baseline Faster RCNN by 8.52%.

Object detection for aerial images has achieved remarkable progress in recent years. Nevertheless, most exiting studies do not differentiate oriented object detection from horizontal detection. Certain schemes ignore the ambiguity of oriented object representation and leverage label assignment designed for horizontal object detection directly. Consequently, it leads to unstable training and causes performance degradation, because high-quality samples surrounding the oriented bounding boxes can not be leveraged effectively. To address this problem, we propose a gliding Free, orientation Free, and anchor Free Network (Free$\rm ^{3}$Net) with high-efficiency for oriented object detection. Specifically, we propose an unambiguous oriented object representation scheme, named FreeGliding, by gliding the projection points of samples on each edge of horizontal bounding boxes. It makes the detection largely free from representation ambiguity and multi-task dependency. To overcome the restrictions of label assignment, we put forward a novel Loss-aware Outer Sample Selection (LOSS) scheme, which takes into consideration spatial information and localization capability to retain high-quality samples surrounding the objects. Moreover, we introduce an Oriented Feature Fusion (OFF) scheme to tackle feature alignment by adjusting the receptive field and fusing oriented features dynamically. Experimental results on two large-scale remote sensing datasets HRSC2016 and DOTA demonstrate that Free$\rm ^{3}$Net outperforms the state-of-the-art schemes with a large margin. We hope our work can inspire rethinking the design of anchor-free detectors, and serve as a strong baseline for oriented object detection.

The increasing demands of safety-critical computer vision applications have attracted extensive research on Out-of-Distribution (OOD) detection in recent years. Nevertheless, a large proportion of real-world tasks are in low-data regime, and the gap between meta-learning paradigm and OOD detection mechanism causes low performance in few-shot settings. In order to bridge the gap, we first propose an simple yet effective Episodic Projection Scheme (EPS). EPS is designed to project feature vectors to task-specific feature space for OOD detection, without sacrificing generalization of few-shot models. We then construct a multi-modal representation space for few-shot OOD detection by employing representations of the labels and their synonyms. At last, we put forward a few-shot OOD detection framework named Episodic Projection Network (EPN), which can integrate many kinds of perturbation based OOD algorithms with ease. To verify effectiveness of the proposed scheme, we implement several OOD algorithms into EPN and conduct experiments on two few-shot classification datasets, i.e., Omniglot and mini-ImageNet. Experimental results demonstrate that accuracy has been increased by 5% by integrating the OOD algorithms into the EPN framework.

Attention-based techniques have been successfully used for rating image quality, and have been widely employed for set-based face recognition. Nevertheless, for video face recognition, where the base convolutional neural network (CNN) trained on large-scale data already provides discriminative features, fusing features with only predicted quality scores to generate representation are likely to cause duplicate sample dominant problem, and degrade performance correspondingly. To resolve the problem mentioned above, we propose a redundancy removing aggregation network (RRAN) for video face recognition. Compared with other quality-aware aggregation schemes, RRAN can take advantage of similarity information to tackle the noise introduced by redundant video frames. By leveraging metric learning, RRAN introduces a distance calibration scheme to align distance distributions of negative pairs of different video representations, which improves the accuracy under a uniform threshold. A series of experiments is conducted on multiple realistic data sets to evaluate the performance of RRAN, including YouTube Faces, IJB-A, and IJB-C. In comprehensive experiments, we demonstrate that our method can diminish the overall influence of poor quality components with large proportion in the video and further improve the overall recognition performance with individual difference. Specifically, RRAN achieves a 96.84% accuracy on YouTube Face, outperforming all existing aggregation schemes.

Recent advances from wearables have significantly changed the way how humans communicate with the surrounding environment. To some extent, they have extended and augmented the capability of humans. For example, with a Google Glass, people can take pictures simply by winking eyes twice, which releases human hands from the cumbersome image-taking process. Thus, it enables new application scenarios that were not possible before. In this paper, we investigate utilizing vision-based techniques to provide a wearable positioning system. Specifically, we propose a Human-centric Positioning System (HoPS) that utilizes traffic signposts together with context information for real-time positioning. Towards that direction, we make three primary contributions: (1) we make several important observations that guide our design of HoPS system; for example, we find out that approximately 40 percent of traffic signposts monopolize a cell tower, and there are at most six signposts within the coverage of a single cell tower; (2) we investigate the impact factors of object detection success rate, and find its correlation with image quality, and resolution; and (3) we design and implement HoPS and an advanced version of HoPS based on additional context information from Wi-Fi network, which we name HoPS-WiFi. Experimental results demonstrate the effectiveness of HoPS, especially HoPS-WiFi, which can estimate the relevant location correctly within 1.3 seconds.

Cloud storage has gained increasing popularity in the past few years. In cloud storage, data is stored in the service provider’s data centers, and users access data via the network. For such a new storage model, our prior wisdom about conventional storage may not remain valid nor applicable to the emerging cloud storage. In this article, we present a comprehensive study to gain insight into the unique characteristics of cloud storage and optimize user experiences with cloud storage from a client’s perspective. Unlike prior measurement work that mostly aims to characterize cloud storage providers or specific client applications, we focus on analyzing the effects of various client-side factors on the user-experienced performance. Through extensive experiments and quantitative analysis, we have obtained several important findings. For example, we find that (1) a proper combination of parallelism and request size can achieve optimized bandwidths, (2) a client’s capabilities and geographical location play an important role in determining the end-to-end user-perceivable performance, and (3) the interference among mixed cloud storage requests may cause performance degradation. Based on our findings, we showcase a sampling- and inference-based method to determine a proper combination for different optimization goals. We further present a set of case studies on client-side chunking and parallelization for typical cloud-based applications. Our studies show that specific attention should be paid to fully exploiting the capabilities of clients and the great potential of cloud storage services.

Analysing the power usage of an Internet of Things (IoT) device is essential in contexts such as smart building, testbed and forensics. For example, in the smart building case, schemes have been proposed to detect and analyse the activity of electric appliances based on the total power usage. In this work, we intend to take this concept a step further and devise a method to analyse the activity of a single IoT device (mote) based on its power usage. To that end, we develop a neural network (NN) based classifier PowerShark that is capable of classifying mote activity based solely on the power usage of the mote, both in online and offline mode. PowerShark can detect radio activity, hardware, operating system (OS), and the MAC layer used. To verify the accuracy of PowerShark, we use power traces from OpenMote and Zolertia Z1 motes, with ContikiOS configured either with ContikiMAC or X-MAC. Experimental results demonstrate the accuracy of our proposed classifier. Specifically, PowerShark can achieve over 95% accuracy in both training and testing phases.

Using crowdsourced visual and inertial sensor data for indoor mapping has attracted much attention in recent years. Nevertheless, the opportunities and challenges of indoor tracking using crowdsourced maps have not been fully explored. In this work, we aim at tackling the challenges due to incomplete obstacle information in crowdsourced indoor maps, especially at the initialization stage of crowdsourcing. We propose a novel solution for particle-filtering-based indoor tracking, using the crowdsourced maps derived from image-based 3D point clouds. Our solution enhances particle filtering with density-based collision detection and history-based particle regeneration. Evaluation with real user traces demonstrates that our solution outperforms the state-of-the-art. In particular, it reduces the average distance error of indoor tracking by 47% when using crowdsourced 3D point clouds.

Cloud storage has gained increasing popularity in the past few years. In cloud storage, data is stored in the service provider's data centers, and users access data via the network. For such a new storage model, our prior wisdom about conventional storage may not remain valid nor applicable to the emerging cloud storage. In this paper, we present a comprehensive study and attempt to gain insight into the unique characteristics of cloud storage, primarily from the client's perspective. Through extensive experiments and quantitative analysis, we have acquired several interesting, and in some cases unexpected, findings. (1) Parallelizing I/Os and increasing request sizes are keys to improving the performance, but optimal bandwidth may only be achieved with a proper combination of parallelism and request size. (2) Client capabilities, including CPU, memory, and storage, play an unexpectedly important role in determining the achievable performance. (3) A geographically long distance affects client-perceived performance but does not always result in lower bandwidth and longer latency. Based on our experimental studies, we further present a case study on appropriate chunking and parallelization in a cloud storage client. Our studies show that specific attention should be paid to fully exploiting the capabilities of clients and the great potential of cloud storage services.

Energy efficiency has become a primary concern for data centers in recent years. Understanding where the energy has been spent within a software is fundamental for energy-efficiency study as a whole. In this paper, we take the first step towards this direction by building an energy profiling module on top of IgProf. IgProf is an application profiler developed at CERN for scientific computing workloads. The energy profiling module is based on sampling and obtains energy measurements from the Running Average Power Limit (RAPL) interface present on the latest Intel processors. The initial profiling results of a single-threaded program demonstrates potential, showing a close correlation between the execution time and the energy spent within a function.

Utilizing network traffic scheduling to improve the energy efficiency of smartphones has been studied extensively in the past few years. These studies usually take certain approaches and make some assumptions concerning traffic predictability, regardless of whether these assumptions hold or whether the approaches have been studied before. In this paper, we conduct an analysis of existing work to find common approaches and assumptions among the proposed solutions. We find out the following: 1. A large part of the solutions target a specific (single) application or category of applications, and do not schedule the whole traffic transmitted on the smartphone. 2. A common assumption is that network traffic for smart phones is predictable. The focus of our work is to test these assumptions against real-world data and analyze whether the approaches presented in the literature are feasible. By leveraging two data sets from NetSense, we make several major contributions: 1. We demonstrate clearly, based on a large dataset, that background apps are the largest energy consumers for smart phones. 2. although some traffic traces exhibit long-term trends, in general traffic from a single app or a user is not predictable in the short-term. 3. achieving energy savings is difficult by scheduling traffic only from a specific app, since multi-app scenarios are so prevalent on today's smartphones. We also pinpoint future directions for traffic scheduling schemes.

The adoption of indoor navigation for smartphones has been relatively slow in the past years, although it would be direly needed in complex indoor areas. The primary barriers for its adoption include the lack of fine-grained and up-to-date indoor maps and the potential deployment and maintenance cost. In this paper we investigate the feasibility of utilizing crowdsourced data for building a smartphone-based indoor navigation system, focusing on the technical challenges caused by the varying quality of crowdsourced data. We developed iMoon, an indoor navigation system based on sensor-enriched 3D models of indoor environment, and evaluated its performance via a field study in a public building covering around 1,100 square meters.

The indoor location market is growing rapidly. However, fine-grained and up-to-date indoor maps are rarely available, and the existing indoor localization and navigation services mostly require extra infrastructures to provide accurate locations. In this demonstration we show iMoon, an indoor navigation system that provides indoor mapping, localization and navigation services using photos and sensor data collected from widely available mobile devices. The demonstration leverages a cohesive suite of computer vision, mobile sensing, and wireless networking techniques.

Large wireless sensor networks (WSNs) with thousands of motes are expected to be a significant part of the future connected world. As battery life of such motes is still an issue, it is important to provide scalable methods to estimate energy usage without introducing significant overhead. We foresee that in the future significant amount of data will be collected and inferred on the behavior of motes. Such collection and inference of data can be considered as a virtual representation of the physical mote, with a potentially longer life-cycle. The virtual mote is a valuable resource for application development, diagnostics and behavior prediction. In this paper, we focus on the energy consumption aspect of such motes. To that end, we develop a packet-based real-time energy model, which works by analyzing network traffic traces collected at the backend to estimate energy consumption of the mote. Such approach scales well to the number of motes and does not require modification to the mote or its network stack. Experimental results from extensive measurements conducted on two platforms, i.e., OpenMote and Zolertia Z1, demonstrate promising potential. The energy model can achieve an estimation accuracy over 90% for platform power, and over 85% accuracy for radio power consumption, on various scenarios.

With the tremendous growth in wireless network deployment and increasing use of mobile devices, e.g., smartphones and tablets, improving energy efficiency in such devices, especially with communication driven workloads, is critical to providing a satisfactory user experience. Studies show that signal strength plays an important role on energy consumption of cellular data communications. While energy consumption can be minimized by accurately predicting signal strengths and reacting to it in real-time, the dynamic nature of wireless environments makes signal strengths highly unpredictable. In this paper, after analyzing in detail the signal strength variation and its impact on energy consumption, we propose to use crowdsourcing approach to optimize mobile devices' energy efficiency by utilizing signal strength traces reported/shared by other users/devices in cellular networks. Via a comprehensive measurement study, we observe that signal strength traces collected from different devices are pseudo-identical, and they even exhibit similar threshold-based behaviors in the relationship between signal strength and device power consumption. Based on our observations, we propose a predictive scheduling algorithm that: (i) selects the right set of signal strength traces based on its location, (ii) applies a filter to smooth out signal strengths and hide abrupt changes, (iii) digitizes the signal strength to “good” and “bad” areas, and (iv) schedules transmissions based on power-throughput characteristics to optimize the transmission energy efficiency. To demonstrate the efficacy of the proposed algorithms, we prototype the crowdsourcing-based predicative scheduling algorithm on Android-based smartphones. Our experiment results from real-life driving tests demonstrate that, by leveraging others' signal traces, mobile devices can save energy up to 35 percent compared to the conventional opportunistic scheduling, i.e., schedule transmissions only based on instantaneous channel conditions.

With the prosperity of cloud computing, an increasing number of Small and Medium-sized Enterprises (SMEs) move their business to public clouds such as Amazon EC2. To help tenants deploy services in the cloud, researchers either conduct performance evaluations or design mechanisms and software on seeking virtual machines of better performance. However, few studies have investigated the impact of instance seeking strategies on resource allocation in clouds if every tenant starts to apply the same method to find the better performing virtual machine. In this paper, we propose a cloud and a tenant model in order to simulate the process of tenants' seeking better-performing instances in the cloud. We discuss, implement and evaluate six cloud resource allocation strategies and five instance seeking strategies. We perform the evaluation via simulation based on real data traces. Our results show that instance seeking strategies can cause the exhaustion of better-performing instances and significant request growth in the cloud. Furthermore, we find that tenants could save time and budget through collaborative seeking strategies. Finally, we discuss the implications of our findings from perspectives of both tenants and providers.

One challenging problem in Machine-to-Machine (M2M) applications is to efficiently discover the resources provided by a huge number of heterogeneous devices. This paper proposes distributed resource discovery architecture (DRD) for M2M applications. The DRD supports heterogeneous devices in resource description registration and discovery of resource value. It achieves interoperability among heterogeneous devices in disparate networks and enables resource access from the Internet. In the DRD, a resource registration component is designed for storing resource descriptions, a resource discovery component is designed to retrieve resource values on behalf of clients after getting address information by looking up resource descriptions. The DRD utilizes a peer-to-peer overlay to distribute workload and avoid single point of failure. A real-world prototype is implemented and verified with a simple demo. Preliminary evaluation on response time of resource discovery is provided.

Machine-to-Machine (M2M) communications emerge to achieve ubiquitous communications among all the networked devices. One challenging problem in M2M applications is to discover the resources provided by the devices efficiently. This challenge arises from two perspectives: (1) a large number of heterogeneous devices co-exist and most of them are constrained devices (e.g., limited processing capability), (2) different communication protocols are utilized to get access to different types of resources provided by the devices (e.g., humidity information provided by a sensor). This paper proposes distributed resource directory architecture for M2M applications, referred to as DRD4M. The DRD4M supports heterogeneous devices using HTTP and CoAP protocols for resource registration and lookup. This enables the interoperability among heterogeneous devices and resource access to constrained devices from disparate network including the Internet. The DRD4M introduces two components: a resource registration component for registering resources and a resource lookup component with caching functionality for handling resource lookup with filtering. A peer-to-peer (P2P) overlay is introduced in DRD4M to connect resource peers to avoid single point of failure. A real-world prototype is implemented and is verified with a demo application. Preliminary performance evaluation in terms of response time of resource lookup is provided.

Public cloud platforms might start with homogeneous hardware; nevertheless, because of inevitable hardware upgrades, or adding more capacity, the initial homogeneous platform will gradually evolve into heterogeneous as time passes by. The consequent performance heterogeneity is of concern to cloud users. In this paper, we evaluate performance variations from hardware heterogeneity and scheduling mechanisms of public clouds. Amazon Elastic Compute Cloud (Amazon EC2) and Rackspace Cloud are used as the representatives because of their relatively long record and wide usage among small and medium enterprises (SMEs). A comprehensive set of microbenchmarks and application-level macrobenchmarks have been used to investigate performance variation. Several major contributions have been made. First, we find out that heterogeneous hardware is a commonality among the relatively long-lasting cloud platforms, although the level of heterogeneity varies. Second, we observe that heterogeneous hardware is the primary culprit of performance variation of cloud platforms. Third, we discover that varied CPU acquisition percentages and different virtual machine scheduling mechanisms exacerbate the performance variation problem, especially for network related operations. Finally, based on the observations, we propose cost-saving approaches and analyze Nash equilibrium from cloud user perspective. By using a simple "trial-and-better" approach, i.e., keep good-performing instances and discard bad-performing instances, cloud users can achieve up to 30 percent cost saving.

General-purpose computing domain has experienced strategy transfer from scale-up to scale-out in the past decade. In this paper, we take a step further to analyze ARM-processor based cluster against Intel X86 workstation, from both energy-efficiency and cost-efficiency perspectives. Three applications are selected and evaluated to represent diversified applications, including Web server throughput, in-memory database, and video transcoding. Through detailed measurements, we make the observations that the energy-efficiency ratio of the ARM cluster against the Intel workstation varies from 2.6-9.5 in in-memory database, to approximately 1.3 in Web server application, and 1.21 in video transcoding. We also find out that for the Intel processor that adopts dynamic voltage and frequency scaling (DVFS) techniques, the power consumption is not linear with the CPU utilization level. The maximum energy saving achievable from DVFS is 20%. Finally, by utilizing a monthly cost model of data centers, we conclude that ARM cluster based data centers are feasible, and are advantageous in computationally lightweight applications, e.g. in-memory database and network-bounded Web applications. The cost advantage of ARM cluster diminishes progressively for computation-intensive applications, i.e. dynamic Web server application and video transcoding, because the number of ARM processors needed to provide comparable performance increases.

Energy consumption of wireless data transmission heavily depends on the shape of the outgoing traffic of the mobile device. In this paper, we propose a traffic scheduler that shapes the packets into consistent bursts based on per-packet performance constraints in order to reduce the overall transmission cost. Our scheduler takes into account the scenarios where multiple network applications run concurrently on the mobile device. We evaluate the traffic scheduler with real-life traffic traces from delay-sensitive applications, e.g. Internet radio and YouTube, and delay-tolerant applications e.g. Web browsing. The results show that depending on scenarios 23% to 72% energy savings can be achieved without noticeable performance degradation. Furthermore, our traffic scheduler is of low time complexity O(n), which makes it suitable to be deployed on proxies or directly on mobile devices.

Peer-to-Peer (P2P) technologies have many advantages over traditional client/server technologies, including cost- effectiveness, scalability and robustness, due to their decentralized network structure. However, the performance has traditionally been an issue in P2P systems. Especially the higher lookup latencies, when compared with the traditional client/server systems, have been the bottleneck in many P2P systems. In this paper, we propose a truncated pyramid P2P architecture together with an enhanced model, Vertical Tunneling Model (VTM) for improving the lookup performance. The proposed architecture is built on Peer-to-Peer SIP (P2PSIP) network. VTM builds up vertical tunnels between the upper and lower sub-overlays to speed up the service lookup and decrease the session setup delay. Based on the performance analysis and results, it is shown that VTM has better performance compared with the existing systems in average lookup hops, which is about 1/3 of that of the existing systems, the predominance is more evident as the network scale increases.

We present the effects of different churn models on the performance of structured peer-to-peer (P2P) networks in this paper. Specifically, Exponential distribution (ED), Pareto distribution (PD), and Weibull distribution (WD) are evaluated to provide a comparative analysis. Kademlia-based Peer-to-Peer Protocol (P2PP) is utilized as the underlying signaling protocol. Through simulations, we conclude that the simulated different churn models do not have a significant effect on the performance of the simulated structured P2P network. Quantitatively, ED and PD result in better performance compared to WD from the viewpoints of lookup success rate, mean network traffic load, and mean number of messages.

Though a lot of research has been done on fault tolerance for MPI applications, process migration has not gained widespread use because the complexity of the requirement that the knowledge about the location of a migrated process has to be made known to every other process in the MPI application. In this paper, we present a novel and effective process migration method for MPI application. We implement a prototype called LAM/Migration which based on LAM/MPI + BLCR to provide transparent process migration for MPI application and the migration mechanism is built into LAM/MPI. All processes in MPI application including mpirun and MPI processes can be migrated to any different set of spare nodes in cluster under user specified in case of nodes failure in our method. Performance evaluation results showed that the checkpoint overhead is similar to plain LAM/MPI + BLCR, and the migration method is feasible and promising for overcoming nodes failure in large-scale parallel computing. By using LAM/Migration, the high availability and reliability of parallel computation can be achieved.

This paper evaluates the feasibility of mobile nodes as peers in a structured peer-to-peer overlay network. Our performance analysis is based on the Peer-to-Peer Protocol (P2PP), which is a peer protocol candidate for the Peer-to-Peer Session Initiation Protocol (P2PSIP). We use both, live-network measurements and simulations, to evaluate two performance metrics: resource lookup success rate and mobile battery duration. While lookup success rate measures P2PP performance in general, battery duration is crucial for mobile use of P2PP. Restricted battery life limits the feasibility of mobile peers. We reveal the tradeoff between lookup success rate and battery duration. Based on the findings it is possible to find more suitable protocol parameters for mobile peers. The battery duration measurements, made with UDP in UMTS and WLAN access networks, are also applicable in the wireless usage of other application-layer protocols.

A novel fault-tolerant architecture based on COTS components is put forward and implemented in this paper. In order to make observable the internal states of COTS components, and in order to concurrently perform fault-tolerance function and normal function and control the behavior of each COTS component, the authors have devised an intelligent hardware module dedicated to fault-tolerance processing, which can significantly offload application processors. This architecture digs every inherent fault-detection mechanism and adopts layered fault protection mechanism to raise fault-tolerance coverage. This architecture is efficient, flexible, scalable and transparent with respect to fault-tolerance. It is Byzantine fault safe and also supports online repair. The authors also raise some design tradeoffs when designing COTS components based fault-tolerant computer.