Text-based person retrieval is the process of searching a massive visual resource library for images of a particular pedestrian, based on a textual query. Existing approaches often suffer from a problem of color (CLR) over-reliance, which can result in a suboptimal person retrieval performance by distracting the model from other important visual cues such as texture and structure information. To handle this problem, we propose a novel framework to Excavate All-round Information Beyond Color for the task of text-based person retrieval, which is therefore termed EAIBC. The EAIBC architecture includes four branches, namely an RGB branch, a grayscale (GRS) branch, a high-frequency (HFQ) branch, and a CLR branch. Furthermore, we introduce a mutual learning (ML) mechanism to facilitate communication and learning among the branches, enabling them to take full advantage of all-round information in an effective and balanced manner. We evaluate the proposed method on three benchmark datasets, including CUHK-PEDES, ICFG-PEDES, and RSTPReid. The experimental results demonstrate that EAIBC significantly outperforms existing methods and achieves state-of-the-art (SOTA) performance in supervised, weakly supervised, and cross-domain settings.

The rapid expansion of Low Earth Orbit (LEO) satellite constellations presents new challenges for maintaining efficient inter-satellite communication under dynamic network topologies. Traditional minimum spanning tree (MST) algorithms, designed for static or quasi-static networks, are inefficient in handling frequent topology changes and fluctuating link costs in LEO environments. Moreover, existing dynamic MST approaches often rely on localized updates, which lack global foresight, resulting in scalability issues and poor real-time responsiveness. To address these challenges, we propose a novel time-varying topology model based on the inter-satellite link (ISL) properties and orbital prediction, introducing the concepts of Stable ISL Period (SIP) and Stable Communication Period (SCP) to identify intervals of topological stability. Building on this model, we develop the All-Time Dynamic Minimum Spanning Tree (ATDMST) algorithm, which incorporates a filtering mechanism to avoid unnecessary recomputations and employs an "edge swapping" strategy for incremental updates. The ATDMST algorithm dynamically maintains optimal spanning trees as ISL communication costs evolve, significantly reducing computational overhead while preserving communication efficiency. Evaluation results show that, that ATDMST outperforms existing methods, achieving up to an 8.8% reduction in communication costs, 95% fewer topology updates, and a 72% decrease in response time, while maintaining robust performance.

Recent mainstream masked distillation methods function by reconstructing selectively masked areas of a student network from the feature map of its teacher counterpart. In these methods, the masked regions need to be properly selected, such that reconstructed features encode sufficient discrimination and representation capability like the teacher feature. However, previous masked distillation methods only focus on spatial masking, making the resulting masked areas biased towards spatial importance without encoding informative channel clues. In this study, we devise a Dual Masked Knowledge Distillation (DMKD) framework which can capture both spatially important and channel-wise informative clues for comprehensive masked feature reconstruction. More specifically, we employ dual attention mechanism for guiding the respective masking branches, leading to reconstructed feature encoding dual significance. Furthermore, fusing the reconstructed features is achieved by self-adjustable weighting strategy for effective feature distillation. Our experiments on object detection task demonstrate that the student networks achieve performance gains of 4.1% and 4.3% with the help of our method when RetinaNet and Cascade Mask R-CNN are respectively used as the teacher networks, while outperforming the other state-of-the-art distillation methods.

Although window-based self-attention stands out as efficient and effective, a limitation in many previous window-based approaches lies in their reliance on fixed partition patterns within each encoder layer. This constraint restricts the potential for flexible interaction between query and key-value pairs and limits the effective receptive field. To address this issue, we introduce SParse Windows Attention (SPWA), which includes three meta partition patterns: square window, stripes window, and dilation window. In SPWA, each pattern is an independent encoding branch, allowing queries to interact with a broader set of key-value pairs while maintaining linear complexity. Additionally, we introduce Dense Regional Attention (DRA), where each query attends to a set of aggregated regions. By empirically combining sparse and dense encoding schedules, the derived network, SDViT, achieves both coarse and fine-grained interaction within a single layer, prompting the capability of multi-scale learning. Empirical experiments on a variety of tasks including ImageNet-1k classification, MS-COCO object detection, and ADE20K semantic segmentation validate the effectiveness of our approach.

Vision Transformers are born with the property of data-dependent and long-range dependencies, accomplishing a number of astonishing results against their contemporary competitor CNNs. To alleviate the excessive computational burden, previous methods apply the local operation (e.g., convolution, local attention) in the high-resolution stages. Although these designs are efficient for local relations learning, especially for the high redundancy stages, they inevitably lead to the losses of non-locality and are constrained by the limited receptive field. In this paper, we present an effective hybrid-style vision backbone that is explicitly built with dynamic convolution and self-attention to respectively undertake both local and global interaction, dubbed C2SFormer. We adopt two homogeneous modules whose structure follows the typical Transformers. For local relations learning, we take the parallel multi-scale design and additive aggregation as simple but effective ideas, named MS-SCDC. For the global context modeling, we leverage the efficient factorized self-attention mechanism proposed in CoaT and apply it with the MS-SCDC in a cross-stacking manner over the high-resolution stages. Additionally, we further introduce a general approach for multi-scale learning of transformer-based modules, named MS-MHSA. The experiments conducted on a variety of general-purpose vision tasks demonstrate the superiority of the proposed model.

As a general model compression paradigm, feature-based knowledge distillation allows the student model to learn expressive features from the teacher counterpart. In this paper, we mainly focus on designing an effective feature-distillation framework and propose a spatial-channel adaptive masked distillation (AMD) network for object detection. More specifically, in order to accurately reconstruct important feature regions, we first perform attention-guided feature masking on the feature map of the student network, such that we can identify the important features via spatially adaptive feature masking instead of random masking in the previous methods. In addition, we employ a simple and efficient module to allow the student network channel to be adaptive, improving its model capability in object perception and detection. In contrast to the previous methods, more crucial object-aware features can be reconstructed and learned from the proposed network, which is conducive to accurate object detection. The empirical experiments demonstrate the superiority of our method: with the help of our proposed distillation method, the student networks report 41.3%, 42.4%, and 42.7% mAP scores when RetinaNet, Cascade Mask-RCNN and RepPoints are respectively used as the teacher framework for object detection, which outperforms the previous state-of-the-art distillation methods including FGD and MGD.

Application offloading plays a crucial role in application deployment in edge-cloud computing. However, finding the optimal solution for application offloading is challenging due to the heterogeneous resources, computing dependency of tasks, and complex network. Existing research on application offloading problems often assumes that the communication delay between the edge and the cloud (inter-side) is symmetrical or that within the cloud or edge (intra-side) can be omitted. However, this assumption is not practical considering the distinct features of the clouds and the edge clusters. Therefore, we study application offloading in the heterogeneous edge-cloud environment by considering both intra-side communication delay between tasks assigned to the same side and asymmetry inter-side communication delay between edge and cloud sides. We first focus on the specific circumstances with a boundary condition that lead to an optimal offloading solution in a heterogeneous edge-cloud environment. Then we study the general case by designing an iterative algorithm with maximum gain technique to solve it. Furthermore, considering various bandwidths within each side and resource capacities of physical nodes, we develop two efficient algorithms by combining minimum cut and maximum gain approaches. Both simulations and real trace-based evaluations are conducted to validate that the proposed algorithms outperform existing solutions.

The core problem of text-based person retrieval is how to bridge the heterogeneous gap between multi-modal data. Many previous approaches contrive to learning a latent common manifold mapping paradigm following a cross-modal distribution consensus prediction (CDCP) manner. When mapping features from distribution of one certain modality into the common manifold, feature distribution of the opposite modality is completely invisible. That is to say, how to achieve a cross-modal distribution consensus so as to embed and align the multi-modal features in a constructed cross-modal common manifold all depends on the experience of the model itself, instead of the actual situation. With such methods, it is inevitable that the multi-modal data can not be well aligned in the common manifold, which finally leads to a sub-optimal retrieval performance. To overcome this CDCP dilemma, we propose a novel algorithm termed LBUL to learn a Consistent Cross-modal Common Manifold (C3 M) for text-based person retrieval. The core idea of our method, just as a Chinese saying goes, is to 'san si er hou xing', namely, to Look Before yoU Leap (LBUL). The common manifold mapping mechanism of LBUL contains a looking step and a leaping step. Compared to CDCP-based methods, LBUL considers distribution characteristics of both the visual and textual modalities before embedding data from one certain modality into C3 M to achieve a more solid cross-modal distribution consensus, and hence achieve a superior retrieval accuracy. We evaluate our proposed method on two text-based person retrieval datasets CUHK-PEDES and RSTPReid. Experimental results demonstrate that the proposed LBUL outperforms previous methods and achieves the state-of-the-art performance.

Given a natural language description, text-based person retrieval aims to identify images of a target person from a large-scale person image database. Existing methods generally face a color over-reliance problem, which means that the models rely heavily on color information when matching cross-modal data. Indeed, color information is an important decision-making accordance for retrieval, but the over-reliance on color would distract the model from other key clues (e.g. texture information, structural information, etc.), and thereby lead to a sub-optimal retrieval performance. To solve this problem, in this paper, we propose to Capture All-round Information Beyond Color (CAIBC) via a jointly optimized multi-branch architecture for text-based person retrieval. CAIBC contains three branches including an RGB branch, a grayscale (GRS) branch and a color (CLR) branch. Besides, with the aim of making full use of all-round information in a balanced and effective way, a mutual learning mechanism is employed to enable the three branches which attend to varied aspects of information to communicate with and learn from each other. Extensive experimental analysis is carried out to evaluate our proposed CAIBC method on the CUHK-PEDES and RSTPReid datasets in both supervised and weakly supervised text-based person retrieval settings, which demonstrates that CAIBC significantly outperforms existing methods and achieves the state-of-the-art performance on all the three tasks.

Many previous methods on text-based person retrieval tasks are devoted to learning a latent common space mapping, with the purpose of extracting modality-invariant features from both visual and textual modality. Nevertheless, due to the complexity of high-dimensional data, the unconstrained mapping paradigms are not able to properly catch discriminative clues about the corresponding person while drop the misaligned information. Intuitively, the information contained in visual data can be divided into person information (PI) and surroundings information (SI), which are mutually exclusive from each other. To this end, we propose a novel Deep Surroundings-person Separation Learning (DSSL) model in this paper to effectively extract and match person information, and hence achieve a superior retrieval accuracy. A surroundings-person separation and fusion mechanism plays the key role to realize an accurate and effective surroundings-person separation under a mutually exclusion constraint. In order to adequately utilize multi-modal and multi-granular information for a higher retrieval accuracy, five diverse alignment paradigms are adopted. Extensive experiments are carried out to evaluate the proposed DSSL on CUHK-PEDES, which is currently the only accessible dataset for text-base person retrieval task. DSSL achieves the state-of-the-art performance on CUHK-PEDES. To properly evaluate our proposed DSSL in the real scenarios, a Real Scenarios Text-based Person Reidentification (RSTPReid) dataset is constructed to benefit future research on text-based person retrieval, which will be publicly available.

Mobile edge computing (MEC) attracts a growing interests as its benefits for computation intensive and delay sensitive tasks. As an essential component in MEC architecture, cloudlet handles the computing tasks of applications offloaded from mobile devices, and pushes contents close to the mobile users, in order to improve the quality of experience, as well as application deployment and delivery efficiency. Existing work mostly focuses on cloudlet placement and assumes that the capacities of cloudlets are given and fixed, while little work has been done on resource allocation and scheduling among the cloudlets. Aiming to minimize the operator''s cost while preserving user experience, we proposes a pricing based cost-aware dynamic resource management framework (DRMF) for cooperative cloudlets with a centralized controller. Specifically, to stimulate the cooperation between cloudlets and the controller, we formulate the interactions as a Stackelberg game to minimize the cloudlets cost and increase the utility of the cloudlet-based edge computing system by eventually determining the amount of physical resources assigned to each cloudlet during deployment phase and the amount of resources shared among cooperated cloudlets during operation phase. Additionally, two algorithms have been proposed targeting latency-sensitive scenario and computation-intensive scenario, respectively. Evaluations validate the existence of Subgame Perfect Equilibrium (SPE), and show that the dynamic resource management framework could save the cost compared to static allocation.

Aiming to minimize the operators' cost while preserving user experience, we propose a resource scheduling mechanism for cooperative cloudlets in edge computing with a centralized controller. The interactions between cloudlets and the controller are formulated as a two-stage Stackelberg game to determine the amount of physical resources assigned to each cloudlet during deployment phase and the price of resources shared among cooperated cloudlets during operation phase.

In urban area, fast growth in the number of vehicles has led to a series of traffic problems, including traffic jams,high traffic accident rates, etc. Efficient traffic signal control methods has been shown to be an essential way to significantly mitigate traffic problems. In this poster, different from previous online methods, we propose a frame-based model and an efficient algorithm to solve the drawbacks of online algorithm by scheduling the vehicles that have accumulated at the intersection over a period of time. Preliminary experiments exhibit that the proposed algorithm could greatly improve the throughput of the intersection.

Deadline guaranteed packet scheduling for switches is a fundamental issue for providing guaranteed QoS in digital networks. It is a historically difficult NP-hard problem if three or more deadlines are involved. All existing algorithms have too low throughput to be used in practice. A key reason is they use packet deadlines as default priorities to decide which packets to drop whenever conflicts occur. Although such a priority structure can ease the scheduling by focusing on one deadline at a time, it hurts the throughput greatly. Since deadlines do not necessarily represent the actual importance of packets, we can greatly improve the throughput if deadline induced priority is not enforced. This paper first presents an algorithm that guarantees the maximum throughput for the case where only two different deadlines are allowed. Then, an algorithm called iterative scheduling with no priority (ISNOP) is proposed forthe general case where k > 2 different deadlines may occur. Not only does this algorithm have dramatically better average performance than all existing algorithms, but also guarantees approximation ratio of 2. ISNOP would provide a good practical solution for the historically difficult packet scheduling problem.

Packet scheduling in switches plays an important role in providing guaranteed service to meet Quality-of-Service (QoS) requirements. In this paper, we revisit a historical Maximum Traffic Time-slot Scheduling (MTTS) problem for both circuit- and packet-switched traffic in SS/TDMA satellite systems proposed two decades ago by Bonuccelli et al.. They developed a two-step approach to solve the MTTS problem, which scheduled the circuit-switched traffic first into TDMA frames and then inserted packets from packet-switched traffic into empty slots in these scheduled TDMA frames as many as possible. This problem was referred as Incremental Time-slot Assignment (ITSA) Problem in their paper, and was proved to be NP-hard. Therefore, MTTS problem seems to be NP-hard due the the NP-hardness of ITSA problem induced by their two-step approach. However, in this paper, we show that MTTS problem is NOT NP-hard, since there exists an optimal algorithm for this problem. By aggregating the traffic in scheduled TDMA frames, an optimal algorithm based on network flow method is developed for MTTS problem, which can solve the MTTS problem in polynomial time. Theoretic proof for the optimality of our algorithm is given and simulations results further validate the correctness of our algorithm.