While previous research has attempted to link features of individuals’ drawings to their emotional states, it often overlooks the deeply personal and context-driven nature of visual expression. To bridge the gap, we conducted a two‑week diary study with 21 participants, who used a custom‑built app to track daily emotions through free drawings, followed by interviews reflecting on their artwork. Among the 252 drawings gathered, we found no strong correlations between reported emotions and measurable drawing behaviors; instead, participants expressed emotions through diverse approaches, from illustrations of emotion sources (e.g., events, objects) and metaphors, to emojis, literal text and spontaneous, random mark-making. Participants developed consistent personal styles and described drawing as an intuitive, playful, and safe outlet, though some faced challenges with the ambiguity of visual expressions and interpreting their creations afterwards. With the lessons learned, we discuss opportunities for designing expression-centered emotion tracking technologies that embrace individuality and creativity.

Prewriting is the process of generating and organising ideas before a first draft. It consists of a combination of informal, iterative, and semi-structured strategies such as visual diagramming, which poses a challenge for collaborating with large language models (LLMs) in a turn-taking conversational manner. We present Polymind, a visual diagramming tool that leverages multiple LLM-powered agents to support prewriting. The system features a parallel collaboration workflow in place of the turn-taking conversational interactions. It defines multiple ''microtasks'' to simulate group collaboration scenarios such as collaborative writing and group brainstorming. Instead of repetitively prompting a chatbot for various purposes, Polymind enables users to orchestrate multiple microtasks simultaneously. Users can configure and delegate customised microtasks, and manage their microtasks by specifying task requirements and toggling visibility and initiative. Our evaluation revealed that, compared to ChatGPT, users had more customizability over collaboration with Polymind, and were thus able to quickly expand personalised writing ideas during prewriting.

Live streaming has become increasingly popular, driven by the desire for direct and real-time interactions between streamers and viewers. However, current text-based interactions and pre-defined emojis limit expressiveness, especially when referring to specific stream moments. We propose ThingMoji, a type of user-captured cut-outs to enhance user expression and foster more effective communication between streamers and their audience in the comment section. ThingMojis are unique digital icons created by users by capturing snapshots and annotating specific areas at any point during the stream. We developed StreamThing, a live-streaming platform integrated with ThingMojis, to explore their use during object-focused live streaming contexts. In a user study with three in-the-wild deployments reveals the expressive use of ThingMojis in diverse live-streaming scenarios with rich visual contents. Our findings show that ThingMojis enable viewers to reference specific objects, express emotions, and create shared visual narratives. Streamers found ThingMojis valuable for facilitating on-the-fly communication around visual content and fostering playful interactions. The study also uncovered challenges in ThingMoji comprehension, issues for long-term uses of ThingMojis, and potential concerns regarding misuse. Based on these insights, we discussed new opportunities for supporting object-focused communication during live streaming environments.

Dreams are a source of inspiration for writers, artists, and creative professionals for generations, but recent Generative AI (GenAI) tools make it possible to use natural language to record details of dreams in image form for creativity support. This workshop invites Creativity and Cognition participants working in creative fields with interest in recording and utilizing their dream materials to use GenAI to support their dream documentation. We aim to highlight the unique contribution of dream experiences to art and design inspiration and how it can be supported by technology. Participants bring their dream sketches or records for sharing, reinterpreting, and applying GenAI for visualization. Participants will use GenAI with partners to transcribe their dreams, then create an original visual story based on their own practice and the dream inspiration. The outcome is a hands-on experience with sharing dream inspiration and applying it to creative work, allowing participants to share their insights and enrich the emerging community of dream-supported creativity in HCI.

Human emotions are essentially molded by lived experiences, from which we construct personalised meaning. The engagement in such meaning-making process has been practiced as an intervention in various psychotherapies to promote wellness. Nevertheless, to support recollecting and recounting lived experiences in everyday life remains under explored in HCI. It also remains unknown how technologies such as generative AI models can facilitate the meaning making process, and ultimately support affective mindfulness. In this paper we present Metamorpheus, an affective interface that engages users in a creative visual storytelling of emotional experiences during dreams. Metamorpheus arranges the storyline based on a dream’s emotional arc, and provokes self-reflection through the creation of metaphorical images and text depictions. The system provides metaphor suggestions, and generates visual metaphors and text depictions using generative AI models, while users can apply generations to recolour and re-arrange the interface to be visually affective. Our experience-centred evaluation manifests that, by interacting with Metamorpheus, users can recall their dreams in vivid detail, through which they relive and reflect upon their experiences in a meaningful way.

Prewriting is the process of discovering and developing ideas before writing a first draft, which requires divergent thinking and often implies unstructured strategies such as diagramming, outlining, free-writing, etc. Although large language models (LLMs) have been demonstrated to be useful for a variety of tasks including creative writing, little is known about how users would collaborate with LLMs to support prewriting. The preferred collaborative role and initiative of LLMs during such a creative process is also unclear. To investigate human-LLM collaboration patterns and dynamics during prewriting, we conducted a three-session qualitative study with 15 participants in two creative tasks: story writing and slogan writing. The findings indicated that during collaborative prewriting, there appears to be a three-stage iterative Human-AI Co-creativity process that includes Ideation, Illumination, and Implementation stages. This collaborative process champions the human in a dominant role, in addition to mixed and shifting levels of initiative that exist between humans and LLMs. This research also reports on collaboration breakdowns that occur during this process, user perceptions of using existing LLMs during Human-AI Co-creativity, and discusses design implications to support this co-creativity process.

VTubers, or Virtual YouTubers, are live streamers who create streaming content using animated 2D or 3D virtual avatars. In recent years, there has been a significant increase in the number of VTuber creators and viewers across the globe. This practice has drawn research attention into topics such as viewers' engagement behaviors and perceptions, however, as animated avatars offer more identity and performance flexibility than traditional live streaming where one uses their own body, little research has focused on how this flexibility influences how creators present themselves. This research thus seeks to fill this gap by presenting results from a qualitative study of 16 Chinese-speaking VTubers' streaming practices. The data revealed that the virtual avatars that were used while live streaming afforded creators opportunities to present themselves using inflated presentations and resulted in inclusive interactions with viewers. The results also unveiled the inflated, and often sexualized, gender expressions of VTubers while they were situated in misogynistic environments. The socio-technical facets of VTubing were found to potentially reduce sexual harassment and sexism, whilst also raising self-objectification concerns.

During past decades, Artificial Intelligence (AI) has been consistently used in Creativity Support Tools (CSTs). Recently, with the development of generative AI models, particularly Generative Adversarial Nets (GAN) in Computer Vision, it became possible that AI directly generates visual ideas. However, there were rarely any work in creativity research that harnessed the design ideas generated by such models directly for design space exploration. In this paper, we propose a StyleGAN-driven digital mood board, GANCollage, that integrates AI generated visual ideas into the ideation phase for creativity support. GANCollage supports semantic explorations of StyleGAN generations in an iterative human-in-the-loop manner, using an AI-driven interactive tagging system. Our evaluation involving 10 participants manifests that GANCollage provides more creativity support without compromising the final results. It also offers a more enjoyable, explicit and effective way of exploring AI generated visual ideas for ideation.

Handwritten signature has long been a widely accepted biometric and applied in many verification scenarios. However, automatic signature verification remains an open research problem, which is mainly due to three reasons. 1) Skilled forgeries generated by persons who imitate the original writing pattern are very difficult to be distinguished from genuine signatures. It is especially so in the case of offline signatures, where only the signature image is captured as a feature for verification. 2) Most state-of-the-art models are writer-dependent, requiring a specific model to be trained whenever a new user is registered in verification, which is quite inconvenient. 3) Writer-independent models often have unsatisfactory performance. To this end, we propose a novel metric learning based method for offline writer-independent signature verification. Specifically, a dual triplet loss is used to train the model, where two different triplets are constructed for random and skilled forgeries, respectively. Experiments on three alphabet datasets - GPDS Synthetic, MCYT and CEDAR - show that the proposed method achieves competitive or superior performance to the state-of-the-art methods. Experiments are also conducted on a new offline Chinese signature dataset - CSIG-WHU, and the results show that the proposed method has a high feasibility on character-based signatures.