Domain generalizable person Re-identification methods (DG person ReID) often focus on aligning source-domain distributions to learn domain-invariant features. However, they commonly overlook the pivotal role of hard samples and subtle yet important appearance differences across domains in refining decision boundaries, leading to suboptimal performance when encountering visually similar pedestrians. To address these issues, we propose a framework that combines adaptive uncertainty-driven hard identity mining with a multi-level feature propagation strategy. Specifically, we first identify and prioritize challenging samples across domains through an uncertainty estimation mechanism coupled with dynamic cross-domain weight allocation, thereby adaptively enhancing the model’s discriminative capability for confusable identities. We then incorporate both cross-domain and intra-domain feature propagation to integrate fine-grained information across multiple source domains, strengthening the model’s adaptability to unseen target domains. Extensive experiments on nine real-world benchmarks demonstrate that our method consistently outperforms state-of-the-art DG person ReID approaches, achieving up to 5.3% mAP and 6.6% Rank-1 improvements over the leading baselines.

Network traffic classification has become an essential technology for information service providers. While existing methods predominantly focus on packet-level features such as port numbers and payload content, they fundamentally overlook the dynamic interaction patterns revealed by traffic burst sequences and the inherent relational characteristics between consecutive traffic bursts. To overcome the limitation of existing methods, we design a new burst position relational graph attention network (BP-RGAT) for traffic classification. We introduce the Heterogeneous Traffic Burst Graph (HTBG) to obtain more traffic interaction information. We also incorporate Relative Traffic Burst Position Encoding (RBPE) to capture sequence information between bursts. To evaluate the performance of BPRGAT, we conduct experiments with ISCX-VPN and USTC-TFC datasets. The results show that BP-RGAT achieves the highest F1 score compared to existing baseline methods (e.g. NetMamba, ET-BERT, BehavSniffer, TFE-GNN).

Randomized Smoothing (RS) is currently a scalable certified defense method providing robustness certification against adversarial examples. Although significant progress has been achieved in providing defenses against $\ell_p$ adversaries, the interaction between the smoothing distribution and the robustness certification still remains vague. In this work, we comprehensively study the effect of two families of distributions, named Exponential Standard Gaussian (ESG) and Exponential General Gaussian (EGG) distributions, on Randomized Smoothing and Double Sampling Randomized Smoothing (DSRS). We derive an analytic formula for ESG’s certified radius, which converges to the origin formula of RS as the dimension $d$ increases. Additionally, we prove that EGG can provide tighter constant factors than DSRS in providing $\Omega(\sqrt{d})$ lower bounds of $\ell_2$ certified radius, and thus further addresses the curse of dimensionality in RS. Our experiments on real-world datasets confirm our theoretical analysis of the ESG distributions, that they provide almost the same certification under different exponents $\eta$ for both RS and DSRS. In addition, EGG brings a significant improvement to the DSRS certification, but the mechanism can be different when the classifier properties are different. Compared to the primitive DSRS, the increase in certified accuracy provided by EGG is prominent, up to 6.4% on ImageNet.

Recently a line of research has delved into the use of graph neural networks (GNNs) for decentralized control in swarm robotics. However, it has been observed that relying solely on the states of immediate neighbors is insufficient to imitate a centralized control policy. To address this limitation, prior studies proposed incorporating L-hop delayed states into the computation. While this approach shows promise, it can lead to a lack of consensus among distant flock members and the formation of small clusters, consequently failing cohesive flocking behaviors. Instead, our approach leverages spatiotemporal GNN, named STGNN that encompasses both spatial and temporal expansions. The spatial expansion collects delayed states from distant neighbors, while the temporal expansion incorporates previous states from immediate neighbors. The broader information gathered from both expansions results in more effective and accurate predictions. We develop an expert algorithm for controlling a swarm of robots and employ imitation learning to train our decentralized STGNN model based on the expert algorithm. We simulate the proposed STGNN approach in various settings, demonstrating its decentralized capacity to emulate the global expert algorithm. Further, we implemented our approach to achieve cohesive flocking, leader following, and obstacle avoidance by a group of Crazyflie drones. The performance of STGNN underscores its potential as an effective and reliable approach for achieving cohesive flocking, leader following, and obstacle avoidance tasks.

Recent research has explored the use of graph neural networks (GNNs) for decentralized control in swarm robotics. However, it has been observed that relying solely on local states is insufficient to imitate a centralized control policy. To address this limitation, previous studies proposed incorporating K-hop delayed states into the computation. While this approach shows promise, it can lead to a lack of consensus among distant flock members and the formation of small localized groups, ultimately resulting in task failure. Our approach is to include the delayed states to build a spatiotemporal GNN model (ST-GNN) by two levels of expansion: spatial expansion and temporal expansion. The spatial expansion utilizes K-hop delayed states to broaden the network while temporal expansion, can effectively predict the trend of swarm behavior, making it more robust against local noise. To validate the effectiveness of our approach, we conducted simulations in two distinct scenarios: free flocking and flocking with a leader. In both scenarios, the simulation results demonstrated that our decentralized ST-GNN approach successfully overcomes the limitations of local controllers. We performed a comprehensive analysis on the effectiveness of spatial expansions and temporal expansions independently. The results clearly demonstrate that both significantly improve overall performance. Furthermore, when combined, they achieve the best performance compared to global solution and delayed states solutions. The performance of ST-GNN underscores its potential as an effective and reliable approach for achieving cohesive flocking behavior while ensuring safety and maintaining desired swarm characteristics.

Exploration is one of the main challenges in Reinforcement Learning (RL), especially in environments with sparse rewards. Learning from Demonstrations (LfD) is a promising approach to solving this problem by leveraging expert demonstrations. However, expert demonstrations of high quality are usually costly or even impossible to collect in real-world applications. In this work, we propose a novel RL algorithm called HYbrid Policy Optimization (HYPO), which uses a small number of imperfect demonstrations to accelerate an agent's online learning process. The key idea is to train an offline guider policy using imitation learning in order to instruct an online agent policy to explore efficiently. Through mutual update of the guider policy and the agent policy, the agent can leverage suboptimal demonstrations for efficient exploration while avoiding the conservative policy caused by imperfect demonstrations. Empirical results show that HYPO significantly outperforms several baselines in various challenging tasks, such as MuJoCo with sparse rewards, Google Research Football, and the AirSim drone simulation.

Pictorial visualizations portray data with figurative messages and approximate the audience to the visualization. Previous research on pictorial visualizations has developed authoring tools or generation systems, but their methods are restricted to specific visualization types and templates. Instead, we propose to augment pictorial visualization authoring with visual style transfer, enabling a more extensible approach to visualization design. To explore this, our work presents Vistylist, a design support tool that disentangles the visual style of a source pictorial visualization from its content and transfers the visual style to one or more intended pictorial visualizations. We evaluated Vistylist through a survey of example pictorial visualizations, a controlled user study, and a series of expert interviews. The results of our evaluation indicated that Vistylist is useful for creating expressive and faithful pictorial visualizations.

Visualization dashboards serve as an information presentation that uses a tiled layout of key metrics visualized in charts for collaborative decision-making. Existing work has developed tools and techniques for computational color design. Much of these efforts have focused on selecting effective color palettes for independent charts while few attempts have been made to support the expressive color design of multiple coordinated charts in dashboards. In this work, we describe ColorCook, an interactive system that helps design expressive and effective dashboard colorings using domain-associated palettes. ColorCook employs an integrated color workflow for dashboarding, consisting of color selection, assignment, and adjustment. We evaluated ColorCook through a crowdsourcing experiment and a user study. The results of our evaluation indicated that ColorCook is useful for effective and expressive color design.

Storyboarding is an important ideation technique that uses sequential art to depict important scenarios of user experience. Existing data-driven support for storyboarding focuses on constructing user stories, but fail to address its benefit as a graphic narrative device. Instead, we propose to develop a data-driven design support tool that increases the expressiveness of user stories by facilitating sketching storyboards. To explore this, we focus on supporting the sketching of emotional expressions of characters in storyboards. In this paper, we present EmoG, an interactive system that generates sketches of characters with emotional expressions based on input strokes from the user. We evaluated EmoG with 21 participants in a controlled user study. The results showed that our tool has significantly better performance in usefulness, ease of use, and quality of results than the baseline system.

Apart from the received signal energy, geo-location information plays an important role in ameliorating spectrum sensing performance. In this paper, a novel wireless fingerprint (WFP) aided spectrum sensing scheme is proposed. Assisted by the wireless fingerprint database (WFPD), secondary user equipments (SUEs) first identify their locations in the cellular cognitive radio network (CCRN) and then ascertain the white licensed spectrum for opportunistic access. The SUEs can pinpoint their geographical locations via time of arrival (TOA) estimate over the signals received from their surrounding base-stations (BSs). In view of the fact that locations of the primary user (PU) transmitters are either readily known or practically unavailable, the SUEs can search the WFPD or perform support vector machine (SVM) algorithm to determine the availability of the licensed spectrum, according to the locations of themselves and the PU transmitters (PUTs). In addition, to alleviate the deficiency of single SU based sensing, a joint prediction mechanism is proposed on the basis of cooperations of multiple SUs that are geographically nearby. Simulations verify that the proposed scheme achieves higher detection probability and demands less energy consumption than conventional spectrum sensing algorithms.