This paper investigates how virtual reality (VR) can foster empathy and ecological literacy for urban herpetofauna—reptiles and amphibians often overlooked in conservation. We present The Wetland Quest (TWQ), an immersive VR experience set in a Shanghai wetland that employs embodiment and scale-shift mechanics to situate users in the world of local species. In a mixed-methods study with 62 participants, TWQ significantly improved species literacy and attitudes toward herpetofauna, supported by large quantitative gains and qualitative themes of immersion, empathy, and reduced aversion. This work contributes to HCI and environmental communication by: (1) introducing TWQ as a design case of VR for underrepresented species; (2) providing empirical evidence that immersive perspective-taking can enhance literacy and pro-environmental attitudes; and (3) demonstrating a methodological protocol that combines knowledge tests, validated attitude scales, observations, and interviews, offering a transferable approach for future VR conservation research.

• Design a self-attention aggregation module using a pre-trained diffusion model. • Integrate high-precision masks into RGB-D SLAM for robust dynamic tracking. • Validate superior accuracy and efficiency on dynamic simulation datasets. In dynamic environments, performing RGB-D SLAM (Simultaneous Localization and Mapping) faces significant challenges primarily due to the presence of moving objects. The motion of these objects can introduce tracking errors and inaccuracies in map construction, thereby compromising the stability and overall performance of the system. To maintain high-precision localization and mapping under such conditions, a SLAM system must effectively detect and handle dynamic objects. To address these challenges, this paper presents a novel RGB-D SLAM method, referred to as DMSAA-SLAM (Dynamic Scene SLAM Based on Diffusion Model Self-Attention Aggregation). The core idea is to leverage a pre-trained stable diffusion model, particularly its self-attention layers, to handle the complexity of dynamic scenes. By employing a multi-resolution aggregation approach, combined with iterative merging and nonmaximum suppression, the proposed method generates high-precision segmentation masks. These masks enable fine-grained segmentation of moving objects and effectively eliminate dynamic feature points, thereby mitigating the impact of dynamic elements on the SLAM process and ensuring efficient and accurate tracking and mapping.

With global warming driving more extreme weather events, real-time monitoring and forecasting of severe convective weather are increasingly critical. This letter presents a multitask generative adversarial network (MT-GAN) to improve nowcasting (short-term prediction) of severe weather, specifically precipitation and lightning. MT-GAN forecasts with 6-min temporal resolution and up to 60-min lead times. Its dual-stream architecture handles radar reflectivity and lightning data, using an encoder-decoder framework with SimVP for temporal feature extraction. A two-level feature fusion enhances spatiotemporal predictions, while a Patch-D discriminator improves realism. Tested on a central China dataset, MT-GAN outperforms ConvLSTM and PredRNN++ in image quality and nowcasting accuracy, with a stronger emphasis on convective regions for better lightning initiation detection.

This innovative practice full paper proposes Creator-Thon, a novel teaching project designed to introduce Generative AI into traditional interior design workflows. The project adopts an interdisciplinary approach including application scenario investigation, workflow construction, collaborative innovation, and iterative optimization. The underlying research is grounded in a six-level goal hierarchy, comprising sub-goals of integrating AI capabilities and design knowledge, embedding AI skills into workflows, enhancing the learning engagement, empowering personal career development, fostering (human-AI and human-human) collaboration, and transforming the design paradigms. The teaching framework is progressively refined across multiple iterations, enhancing learning engagement by simplifying tool operations, refining design language, and re-engineering the design process. The findings underscore that integration of authentic application scenarios markedly boosts engagement and motivation among learners, modular instruction also enhances teaching quality and practical skills, and the adaptive optimization of the teaching framework informed by participants' feedback, is key to a successful Generative AI involved interior design pedagogy. This work provides insights that contribute to the application of Generative AI technology in interior design education and practice, facilitating transformations and progress in AI literacy in the field.

This innovation practice explores whether using spatial computing technologies in the form of the Apple Vision Pro and Nomad Sculpt in a mixed-reality environment affects student outcomes on learning goals and creative expression in the context of a chair design project in design education. The primary hypothesis of the study is that, even though students are provided with the exact project specifications, goals, and assessment rubrics, student design outcomes on learning goals and creative expression in the chair design project will improve when using the Apple Vision Pro and Nomad Sculpt as opposed to traditional digital design technologies (the control group using iPads and Nomad Sculpt). In the chair design project, learning goals and course outcomes were framed around projects that included mass, support, openings, shape expression, technical articulation, conversation, structure, sustainability, form, and fulfillment. On average, the subset of students using the Apple Vision Pro and Nomad Sculpt reported more intuitive, immersive, and creative experiences in the design process and the resulting chair designs in reflective essays. These findings are mainly based on quantitative measures of flexibility, idea originality, idea execution, depth of conceptual understanding, engagement, and qualitative measures of experiences through surveys and interviews. Developing an understanding of these tools to provide rich, relevant feedback and enabling productive critique and implementation on the device seems almost insurmountable hurdles due to access, new technologies' learning curve, and the inefficiency of integrating spatial computing tools into pedagogical frameworks. Overall, the research highlights the critical pedagogical advantages of using spatial computing technologies such as the Apple Vision Pro in design education, particularly in design fields requiring high visual-spatial aptitude levels. Furthermore, it provides guidelines for future research into the educational merits of immersive technologies and argues that we need to move beyond the predominantly uni-directional pedagogical models that have characterized the field for more than half a century. This study illustrates the potential of spatial-computing tools to enhance creative problem-solving and the substantial merits for future research into its broader educational applications.

Interference is a serious problem in Wireless Body Area Networks (WBANs) and heavily weakens system performance. In this paper, we propose an exchange-free resource scheduling scheme to overcome the interference of dynamic coexisting WBANs. For each data transmission period, we design a transmission channel/slot allocation scheme based on a Latin square, where each character denotes a specific combination of a channel and a time slot. For each data retransmission period, we design a retransmission time-slot selection scheme based on a hash function, in which the unique identity information of the collided node is used to calculate the retransmission slot. Compared with existing solutions, our work has two key advantages. First, all nodes can independently allocate and coordinate resources rather than exchange information with each other in traditional methods, and thus guaranteeing strong adaptability to the fast changes of WBANs. Second, the contention-free resource allocation pattern is implemented for both the data transmission period as well as the data retransmission period, and thus guaranteeing no intra-WBAN interference and extremely low probability of inter-WBAN interference. Our simulation results show that interferences can be well addressed based on the metrics of the packet loss rate, throughput, power dissipation, and data delivery delay.

The application of the compressed sensing (CS) method in the radar field enables the radar imaging system to satisfy both low data cost and high reconstruction quality, however, it is accompanied by enormous iterative operations and difficult adjustments of parameters. In this paper, we propose a learning-based split unfolding framework, dubbed as split iterative sparse reconstruction network (SISR-Net), for near-field 3-D millimeter-wave (mmW) radar sparse imaging. Firstly, a sparse reconstruction algorithm, i.e., SISRA, is proposed to theoretically guide the structure of the imaging framework. Subsequently, by combining the model-based CS method and data-driven deep learning method, SISR-Net is constructed by SISRA to produce 3-D mmW radar images efficiently with excellent explainability and generalization ability. Joint the radar-imaging kernel, echo-generation kernel, and the split Bregman method, the efficiency and stability of SISR-Net are guaranteed, all parameters are layer-varied and learned steadily by end-to-end training to improve the convergence and robustness of the imaging network. Simulated data and the echo from a high-resolution mmW radar dataset 3DRIED, are used to train and test the SISR-Net based on the Adam optimizer. For both simulation and extensive 3-D mmW radar measured experiments, the proposed SISR-Net outperforms other state-of-the-art imaging methods in terms of imaging accuracy and generalization ability.

In this paper, we present a denoising sequence-to-sequence (seq2seq) autoencoder via contrastive learning for abstractive text summarization. Our model adopts a standard Transformer-based architecture with a multi-layer bi-directional encoder and an auto-regressive decoder. To enhance its denoising ability, we incorporate self-supervised contrastive learning along with various sentence-level document augmentation. These two components, seq2seq autoencoder and contrastive learning, are jointly trained through fine-tuning, w hich i mproves the performance of text summarization with regard to ROUGE scores and human evaluation. We conduct experiments on two datasets and demonstrate that our model outperforms many existing benchmarks and even achieves comparable performance to the state-of-the-art abstractive systems trained with more complex architecture and extensive computation resources.

This paper discusses the digital elevation model (DEM) estimation problem for the linear array synthetic aperture radar based on the variational model. Compared with the sparse recovery model, the one-to-one mapping between the horizontal grid nodes and the elevations is preserved explicitly, which is important for the topographic surveying and mapping mission. During the research, we find that since the mean square error criterion is insensitive to the amount of the elevation offsets, the numerical method by solving the Euler-Lagrange equation is unreliable and the global optimization method is necessary to solve the variational problem. With the ambiguity function localization and the sliding-window architecture, the global optimal path can be obtained by solving a series of local optimization problems provided that the observation matrix is row full rank. Furthermore, the local optimization problem can be relaxed as a sparse recovery problem and can be solved by a modified orthogonal matching pursuit (OMP) method (named as Var-OMP), whose computational cost is acceptable for the actual data processing. By a series of numerical experiments, we show that the performance of Var-OMP is influenced by both the resolution enhancement factor (L) and the signal-to-noise ratio (SNR). The larger the SNR is, the better the performance is; the smaller L is, the more stable and faster the Var-OMP algorithm is. Compared with the sparse recovery methods, the variational model and the Var-OMP algorithm are more suitable for the DEM estimation application in the face of all kinds of terrains.

A novel synthetic aperture radar (SAR) sidelobe suppression method via a dual-Delta factorization (DDF) algorithm is proposed in this letter. Its basic idea is to divide the point spread function (PSF) into a group of different simple subsystems (dual-Delta operators) and to asymptotically approach the solution by the subsystem iterations based on the greedy strategy. The convergence of the DDF algorithm is discussed based on theoretical analyses and numerical experiments. We find that, to keep the algorithm convergent, the sidelobe sum should be soundly smaller than that of the main lobe during the iterations. Simulation experiments and actual SAR image results show that the DDF algorithm can deal with all kinds of PSFs without their exact expressions and is compatible with nonseparable cases, which makes it suitable to process the squint SAR and bistatic SAR images.

This paper presents a knowledge-aided Hough transform (KA-HT) method based on target Doppler property for Track-before-detect (TBD) to detect dim target in low SNR environments. The method substitutes a point-slope form of Hough transform (HT) with useful prior information for the standard HT, which can avoid the problem of determining the optimum parameter space granularity and carry out the dim target detection in three-dimensional range-Doppler-frame space data. Simulation experiments validate the proposed method.