Music shapes the tone of videos, yet creators find it hard to find soundtracks that match their video’s mood and narrative. Recent text-to-music models let creators generate music from text prompts, but our formative study (N=8) shows creators struggle to construct diverse prompts, quickly review and compare tracks, and understand their impact on the video. We present VidTune, a system that supports soundtrack creation by generating diverse music options from a creator’s prompt and producing contextual thumbnails for rapid review. VidTune extracts representative video subjects to ground thumbnails in context, maps each track’s valence and energy onto visual cues like color and brightness, and depicts prominent genres and instruments. Creators can refine tracks with natural language edits, which VidTune expands into new generations. In a controlled user study (N=12) and an exploratory case study (N=6), participants found VidTune helpful for efficiently reviewing and comparing music options and described the process as playful and enriching.

Background music plays a crucial role in social media videos, yet finding the right music remains a challenge for video creators.These creators, often not music experts, struggle to describe their musical goals and compare options.AI text-to-music generation presents an opportunity to address these challenges by allowing users to generate music through text prompts; however, these models often require musical expertise and are difficult to control.In this paper, we explore how to incorporate music generation into video editing workflows.A formative study with video creators revealed challenges in articulating and iterating on musical preferences, as creators described music as "vibes" rather than with explicit musical vocabulary.Guided by these insights, we developed a creative assistant for music generation using editable vibe-based recommendations and structured refinement of music output.A user study showed that the assistant supports exploration, while direct prompting is more effective for precise goals.Our findings offer design recommendations for AI music tools for video creators.

Many artists broadcast their creative process through live streaming platforms like Twitch and YouTube, and people often watch archives of these broadcasts later for learning and inspiration. Unfortunately, because live stream videos are often multiple hours long and hard to skim and browse, few can leverage the wealth of knowledge hidden in these archives. We present an approach for automatic temporal segmentation of creative live stream videos. Using an audio transcript and a log of software usage, the system segments the video into sections that the artist can optionally label with meaningful titles. We evaluate this approach by gathering feedback from expert streamers and comparing automatic segmentations to those made by viewers. We find that, while there is no one "correct" way to segment a live stream, our automatic method performs similarly to viewers, and streamers find it useful for navigating their streams after making slight adjustments and adding section titles.

People often seek help online while using complex software. Currently, information search takes users' attention away from the task at hand by creating a separate search task. This paper investigates how multimodal interaction can make in-task help-seeking easier and faster. We introduce ReMap, a multimodal search interface that helps users find video assistance while using desktop and web applications. Users can speak search queries, add application-specific terms deictically (e.g., "how to erase this"), and navigate search results via speech, all without taking their hands (or mouse) off their current task. Thirteen participants who used ReMap in the lab found that it helped them stay focused on their task while simultaneously searching for and using learning videos. Users' experiences with ReMap also raised a number of important challenges with implementing system-wide context-aware multimodal assistance.

Many artists livestream their creative process, allowing viewers to learn and be inspired from the decisions -- and mistakes -- they make along the way. This paper presents the first broad look at the range of creative activities people stream. Through content analysis of livestream archives, interviews with 8 streamers, and online surveys with 165 viewers, we study current practices and challenges in creative livestream communities and compare them with prior observations of livestreaming in other domains. We observed four common types of creative livestreams: teaching, making, socializing, and performing. We identify three open questions for the research community around how to better support the goals of creative streamers and viewers: how to support richer audience interactions at scale, how to support all parts of the creative process, and how to support watching livestream archives.

Complex activities often require people to work across multiple software applications. However, people frequently lack valuable knowledge about at least one application, especially as software changes and new software emerges. Existing help systems either lack contextual knowledge or are tightly-knit into a single application. We introduce an application-independent approach for contextually presenting video learning resources and demonstrate it through the RePlay system. RePlay uses accessibility APIs to gather context about the user's activity. It leverages an existing search engine to present relevant videos and highlights key segments within them using video captions. We report on a week-long field study (n=7) and a lab study (n=24) showing that contextual assistance helps people spend less time away from their task than web video search and replaces current video navigation strategies. Our findings highlight challenges with representing and using context across applications.

Good feedback is critical to creativity and learning, yet rare. Many people do not know how to actually provide effective feedback. There is increasing demand for quality feedback -- and thus feedback givers -- in learning and professional settings. This paper contributes empirical evidence that two interactive techniques -- reusable suggestions and adaptive guidance -- can improve feedback on creative work. We present these techniques embodied in the CritiqueKit system to help reviewers give specific, actionable, and justified feedback. Two real-world deployment studies and two controlled experiments with CritiqueKit found that adaptively-presented suggestions improve the quality of feedback from novice reviewers. Reviewers also reported that suggestions and guidance helped them describe their thoughts and reminded them to provide effective feedback.

Physical construction and assembly tasks are often carried out by groups of collocated workers, and they can be difficult to coordinate. Group members must spend time deciding how to split up the task, how to assign subtasks to each other, and in what order subtasks should be completed. Informed by an observational study examining group coordination challenges, we built a task distribution system called WeBuild. Our custom algorithm dynamically assigns subtasks to workers in a group, taking into account factors such as the dependencies between subtasks and the skills of each group member. Each worker views personalized step-by-step instructions on a mobile phone, while a dashboard visualizes the entire process. An initial study found that WeBuild reduced the start-up time needed to coordinate and begin a task, and provides direction for future research to build on toward improving group efficiency and coordination for complex tasks.

Complex software offers power for experts, yet overwhelms new users. Novices often do not know how to execute tasks, what they want to achieve, or even what is possible. To address this, we introduce the DiscoverySpace interface for executable action suggestions. DiscoverySpace is a prototype extension panel for Adobe Photoshop that suggests task-level action macros to apply to photographs based on visual features. DiscoverySpace harvests these one-click actions from the online Photoshop user community. A between-subjects study indicated that action suggestions may help novices maintain confidence, accomplish tasks, and discover features. This work demonstrates how interfaces can leverage user-generated content to help novices navigate complex software.

Peer assessment is rapidly growing in online learning, as it presents a method to address scalability challenges. However, research suggests that the benefits of peer review are obtained inconsistently. This paper explores why, introducing three ways that framing task goals significantly changes reviews. Three experiments manipulated features in the review environment. First, adding a numeric scale to open text reviews was found to elicit more explanatory, but lower quality reviews. Second, structuring a review task into short, chunked stages elicited more diverse feedback. Finally, showing reviewers a draft along with finished work elicited reviews that focused more on the work's goals than aesthetic details. These findings demonstrate the importance of carefully structuring online learning environments to ensure high quality peer reviews.

Research suggests that online peer review can provide critical help to learners who would otherwise not be given individualized feedback on their work. However, little is known about how different characteristics of review systems impact reviewers. This extended abstract presents preliminary results from an online experiment examining how explicit numeric ratings change peer reviews. A between-subject experiment found that peer reviewers who were asked to generate a numeric rating as well as general feedback gave significantly more explanations and made more positive comments compared with reviewers who were asked to give general feedback only. These exploratory findings suggest the need to further examine how online peer review systems' affordances can impact the reviews given in these systems.