Food image generation is an important research direction in food computing, aiming to produce highly realistic images that accurately capture the visual characteristics of various dishes while adhering to specified input conditions. Existing methods that rely solely on textual descriptions struggle to handle the large intra-class variability of food, often resulting in limited diversity and accuracy. Although some approaches incorporate additional conditions, they generally lack optimizations for food-specific challenges, leading to inconsistencies in texture, shape, and color fidelity. To address these limitations, we propose CondFoodGen, a diffusion-based two-stream network for controllable food image generation. The architecture consists of a control stream and a generation stream, where the control stream provides conditional guidance to regulate the generation process. To optimize bidirectional interactions between the two streams, we introduce the Bidirectional Adaptive Gating (BAG) mechanism, which not only guides synthesis but also adaptively refines control representations through feedback from the generation stream. In addition, we propose the Wavelet-Guided Hierarchical Attention (WGHA) module, which combines wavelet-based multi-frequency analysis with hierarchical attention to enhance fine-grained texture fidelity and structural realism. A progressive multi-stage training strategy further stabilizes optimization and enables seamless integration of conditional guidance with bidirectional interaction. Extensive experiments on three food image datasets demonstrate that CondFoodGen consistently generates high-quality and diverse images. Compared with the best existing food image generation methods, our approach achieves an average improvement of about 11.0% across three evaluation metrics and compared to the leading conditional generation approaches, the average improvement reaches 16.2%. The source code, trained models, and supplementary materials are publicly available at https://github.com/housujuan123/CondFoodGen.

Metaphorical expressions are abundant in Traditional Chinese Medicine (TCM), conveying complex disease mechanisms and holistic health concepts through culturally rich and often abstract terminology. Bridging these metaphors to anatomy-driven Western Medicine (WM) concepts poses significant challenges for both automated language processing and real-world clinical practice. To address this gap, we propose a novel multi-agent and chain-of-thought (CoT) framework designed to interpret TCM metaphors accurately and map them to WM pathophysiology. Specifically, our approach combines domain-specialized agents (TCM Expert, WM Expert) with a Coordinator Agent, leveraging stepwise chain-of-thought prompts to ensure transparent reasoning and conflict resolution. We detail a methodology for building a metaphor-rich TCM dataset, discuss strategies for effectively integrating multi-agent collaboration and CoT reasoning, and articulate the theoretical underpinnings that guide metaphor interpretation across distinct medical paradigms. We present a comprehensive system design and highlight both the potential benefits and limitations of our approach, while leaving placeholders for future experimental validation. Our work aims to support clinical decision-making, cross-system educational initiatives, and integrated healthcare research, ultimately offering a robust scaffold for reconciling TCM’s symbolic language with the mechanistic focus of Western medicine.

In requirements engineering (RE), there are three essential descriptions, i.e., requirements, specification and domain properties. Their relationship is proposed by Jackson et al, and verified in various requirements approaches. However, at present, there is no formal verification for the relationship in the Problem Frames (PF) which is a well known approach in the RE. Our previous work based on the PF explicitly captures the three descriptions. Based on that work, this paper further formalizes the three descriptions using Communicating Sequential Process (CSP), transforms the relationship into two "refines", and verifies them with Process Analysis Tool (PAT). The verification ensures that the machine which behaves as in the specification installed in a specific domain will satisfy the requirements.

Building up effective teams over a distance is a challenging but common problem in global software engineering. We propose an approach to help build up teams through collaborative online drawing. Our goal is to evaluate how drawing, as one activity that can facilitate expression of personal affective status, can benefit distributed teams. Preliminary results indicate positive effects of collaborative online drawing in increasing team cohesion and positive emotions. We discuss our approach and preliminary results in terms of design implications for future collaborative drawing systems for building up distributed teams.

One form of crowdsourcing is the competition, which poses an open call for competing solutions. Commercial systems such as TopCoder have begun to explore the application of competitions to software development, but have important limitations diminishing the potential benefits drawn from the crowd. In particular, they employ a model of independent work that ignores the opportunity for designs to arise from the ideas of multiple designers. In this paper, we examine the potential for software design competitions to incorporate recombination, in which competing designers are given the designs of others and encouraged to use them to revise their own designs. To explore this, we conducted two software design competitions in which participants were asked to produce both an initial and a revised design, drawing on lessons learned from the crowd. We found that, in both competitions, all participants borrowed ideas and most improved the quality of their designs. Our findings demonstrate the potential benefits of recombination in software design and suggest several ways in which software design competitions can be improved.

Applying team building in distributed teams is challenging. To address this problem, I propose a research agenda to use digital art mediated practices to support team building for distributed teams. The research will lead to designs and tools to help distributed teams conduct art mediated activities over distance and thus help teams build trust and cohesion. The proposed research consists of three major components: (1) design concepts based on theoretical foundations, (2) experiment design, and (3) qualitative investigations.

Self-expression and interpersonal sharing of emotion have been shown to strengthen groups. However, how to accomplish such interpersonal sharing in public settings is a challenge. In a pilot study of a prototype system, we sought to facilitate public self-expression and sharing of affective information. We followed five design principles around the concept of art-mediated self-expression and created a collective doodling installation. The pilot trial demonstrated positive results around engagement of end users. As we reflected on the results from this trial, we found implications for building trust and collaboration in teams.

3D telepresence is a next-generation multimedia application, offering remote users an immersive and natural video-conferencing environment with real-time 3D graphics. Kinect sensor, a consumer-grade range camera, facilitates the implementation of some recent 3D telepresence systems. However, conventional data filtering methods are insufficient to handle Kinect depth error because such error is quantized rather than just randomly-distributed. Hence, one could often observe large irregularly-shaped patches of pixels that receive the same depth values from Kinect. To enhance visual quality in 3D telepresence, we propose a novel depth data filtering method for Kinect by means of multi-scale and direction-aware support windows. In addition, we develop a GPU-based CUDA implementation that can perform real-time depth filtering. Results from the experiments show that our method can reconstruct hole-free surfaces that are smoother and less bumpy compared to existing methods like bilateral filtering.