Video recordings of interviews, lectures, and meetings contain valuable moments surrounded by less essential talk. Making a shareable and meaningful shorter version of this content requires significant effort because it combines tedious, repeated operations with personal editorial decisions, which require human judgment. We introduce an editing approach that operates on video transcripts and combines a three-stage large language model pipeline with a timeline-anchored, marker-based interface so editors can inspect and refine suggestions before final assembly. The pipeline first produces an overview summary to maximize content coverage, then induces plain-language selection rules that encode editorial intent, and finally applies rule-conditioned ranking on small transcript windows to mitigate long-context limits, yielding strictly extractive, time-aligned spans under duration constraints. The interface displays groupings of short excerpts using markers with priorities and confidence cues, converting opaque model output into verifiable units within standard video editing workflows. On MeetingBank and MeetingBank-QA datasets, our method outperforms practical extractive baselines at matched lengths. In a within-subjects study with experienced video editors familiar with Premiere Pro video editing software, we found that our marker-based interface provided editors higher efficiency, control, and satisfaction than both a manual editing baseline and an opaque auto-cut condition.

UIST ’25, Busan, Republic of Korea

B-roll is vital when producing high-quality videos, but finding the right images can be difficult and time-consuming. Moreover, what B-roll is most effective can depend on a video content creator’s intent—is the goal to entertain, to inform, or something else? While new text-to-image generation models provide promising avenues for streamlining B-roll production, it remains unclear how these tools can provide support for content creators with different goals. To close this gap, we aimed to understand how video content creator’s goals guide which visual concepts they prioritize for B-roll generation. Here we introduce a benchmark containing judgments from > 800 people as to which terms in 12 video transcripts should be assigned highest priority for B-roll imagery accompaniment. We verified that participants reliably prioritized different visual concepts depending on whether their goal was help produce informative or entertaining videos. We next explored how well several algorithms, including heuristic approaches and large language models (LLMs), could predict systematic patterns in human judgments. We found that none of these methods fully captured human judgments in either goal condition, with state-of-the-art LLMs (i.e., GPT-4) even underperforming a baseline that sampled only nouns or nouns and adjectives. Overall, our work identifies opportunities to develop improved algorithms to support video production workflows.

The early stages of video editing present many cognitively demanding tasks that require editors to remember and structure large amounts of video. In our formative work we learned that editors break down the editing process into smaller parts by labeling and organizing footage around central themes. Using current video editing tools, this process is slow and largely manual. We present a system called ChunkyEdit for helping editors group video interview clips into thematically coherent chunks, which can then be exported to existing video editing tools and composed into an edited narrative. By focusing on this intermediate step, we leverage computation to do tedious organizational tasks, while preserving the editor’s ability to control the primary storytelling decisions. We explore four different topic modeling approaches to creating video chunks. We then evaluate our tool with eight professional video editors to learn how a chunking-based approach could be incorporated into video editing workflows.

Scrap quilting is a popular sewing process that involves combining leftover pieces of fabric into traditional patchwork designs. Imagining the possibilities for these leftovers and arranging the fabrics in such a way that achieves visual goals, such as high contrast, can be challenging given the large number of potential fabric assignments within the quilt’s design. We formulate the task of designing a scrap quilt as a graph coloring problem with domain-specific coloring and material constraints. Our interactive tool called ScrapMap helps quilters explore these potential designs given their available materials by leveraging the hierarchy of scrap quilt construction (e.g., quilt blocks and motifs) and providing user-directed automatic block coloring suggestions. Our user evaluation indicates that quilters find ScrapMap useful for helping them consider new ways to use their scraps and create visually striking quilts.

The commonly used cut-and-sew garment construction process, in which 2D fabric panels are cut from sheets of fabric and assembled into 3D garments, contributes to widespread textile waste in the fashion industry. There is often a significant divide between the design of the garment and the layout of the panels. One opportunity for bridging this gap is the emerging study and practice of zero waste fashion design, which involves creating clothing designs with maximum layout efficiency. Enforcing the strict constraints of zero waste sewing is challenging, as edits to one region of the garment necessarily affect neighboring panels. Based on our formative work to understand this emerging area within fashion design, we present WasteBanned, a tool that combines CAM and CAD to help users prioritize efficient material usage, work within these zero waste constraints, and edit existing zero waste garment patterns. Our user evaluation indicates that our tool helps fashion designers edit zero waste patterns to fit different bodies and add stylistic variation, while creating highly efficient fabric layouts.

There is a rapidly growing group of people learning to sew online. Without hands-on instruction, these learners are often left to discover the challenges and pitfalls of sewing through trial and error, which can be a frustrating and wasteful process. We present InStitches, a software tool that augments existing sewing patterns with targeted practice tasks to guide users through the skills needed to complete their chosen project. InStitches analyzes the difficulty of sewing instructions relative to a user’s reported expertise in order to determine where practice will be helpful and then solves for a new pattern layout that incorporates additional practice steps while optimizing for efficient use of available materials. Our user evaluation indicates that InStitches can successfully identify challenging sewing tasks and augment existing sewing patterns with practice tasks that users find helpful, showing promise as a tool for helping those new to the craft.

Polarized light mosaics (PLMs) are color-changing structures that alter their appearance based on the orientation of incident polarized light. While a few artists have developed techniques for crafting PLMs by hand, the underlying material properties are difficult to reason about; there exist no tools to bridge the high-level design objectives with the low-level physics knowledge needed to create PLMs. In this paper, we introduce the first system for creating Polagons: machine-made PLMs crafted from cellophane with user-defined color changing behaviors. Our system includes an interface for designing and visualizing Polagons as well as a fabrication process based on laser cutting and welding that requires minimal assembly by the user. We define the design space for Polagons and demonstrate how formalizing the process for creating PLMs can enable new applications in fields such as education, data visualization, and fashion.

With recent advances in Generative AI, it is becoming easier to automatically manipulate 3D models. However, current methods tend to apply edits to models globally, which risks compromising the intended functionality of the 3D model when fabricated in the physical world. For example, modifying functional segments in 3D models, such as the base of a vase, could break the original functionality of the model, thus causing the vase to fall over. We introduce a method for automatically segmenting 3D models into functional and aesthetic elements. This method allows users to selectively modify aesthetic segments of 3D models, without affecting the functional segments. To develop this method we first create a taxonomy of functionality in 3D models by qualitatively analyzing 1000 models sourced from a popular 3D printing repository, Thingiverse. With this taxonomy, we develop a semi-automatic classification method to decompose 3D models into functional and aesthetic elements. We propose a system called Style2Fab that allows users to selectively stylize 3D models without compromising their functionality. We evaluate the effectiveness of our classification method compared to human-annotated data, and demonstrate the utility of Style2Fab with a user study to show that functionality-aware segmentation helps preserve model functionality.

Foundation paper piecing is a widely used quilt-making technique in which fabric pieces are sewn onto a paper guide to facilitate construction. But, designing paper pieceable quilt patterns is challenging because the sewing process imposes constraints on both the geometry and sewing order of the fabric pieces. Based on a formative study with expert quilt designers, we develop a novel sketch-based tool for designing such quilt patterns. Our tool lets designers sketch a partial design as a set of edges, which may intersect but do not have to form closed polygons, and our tool automatically completes it into a fully paper pieceable pattern. We contribute a new sketch-completion algorithm that extends the input sketched edges into a planar mesh composed of closed polygonal faces representing fabric pieces, determines a paper pieceable sewing order for the faces, and breaks complicated sketches into independently paper pieceable sections when necessary. A partial input design often admits multiple visually different completions. Thus, our tool lets designers specify completion heuristics, which are based on current quilt design practices, to control the appearance of the completed quilt. Initial user evaluations with novice and expert quilt designers suggest that our tool fits within current design workflows and greatly facilitates designing foundation paper pieceable quilts by allowing users to focus on the visual design rather than tedious constraint checks.

The craft of improvisational quilting involves working without the use of a predefined pattern. Design decisions are made “in the fabric,” with design experimentation tightly interleaved with the creation of the final artifact. To investigate how this type of design process can be supported, and to address challenges faced by practitioners, this paper presents PatchProv, a system for supporting improvisational quilt design. Based on a review of popular books on improvisational quilting, a set of design principles and key challenges to improvisational quilt design were identified, and PatchProv was developed to support the unique aspects of this process. An evaluation with a small group of quilters showed enthusiasm for the approach and revealed further possibilities for how computational tools can support improvisational quilting and improvisational design practices more broadly.

Foundation paper piecing is a popular technique for constructing fabric patchwork quilts using printed paper patterns. But, the construction process imposes constraints on the geometry of the pattern and the order in which the fabric pieces are attached to the quilt. Manually designing foundation paper pieceable patterns that meet all of these constraints is challenging. In this work we mathematically formalize the foundation paper piecing process and use this formalization to develop an algorithm that can automatically check if an input pattern geometry is foundation paper pieceable. Our key insight is that we can represent the geometric pattern design using a certain type of dual hypergraph where nodes represent faces and hyperedges represent seams connecting two or more nodes. We show that determining whether the pattern is paper pieceable is equivalent to checking whether this hypergraph is acyclic, and if it is acyclic, we can apply a leaf-plucking algorithm to the hypergraph to generate viable sewing orders for the pattern geometry. We implement this algorithm in a design tool that allows quilt designers to focus on producing the geometric design of their pattern and let the tool handle the tedious task of determining whether the pattern is foundation paper pieceable.

We present a system that automatically transforms text articles into audio-visual slideshows by leveraging the notion of word concreteness, which measures how strongly a word or phrase is related to some perceptible concept. In a formative study we learn that people not only prefer such audio-visual slideshows but find that the content is easier to understand compared to text articles or text articles augmented with images. We use word concreteness to select search terms and find images relevant to the text. Then, based on the distribution of concrete words and the grammatical structure of an article, we time-align selected images with audio narration obtained through text-to-speech to produce audio-visual slideshows. In a user evaluation we find that our concreteness-based algorithm selects images that are highly relevant to the text. The quality of our slideshows is comparable to slideshows produced manually using standard video editing tools, and people strongly prefer our slideshows to those generated using a simple keyword-search based approach.

Many organizations have developed websites to support high school computer science (CS) teachers by providing them with collections of teaching resources. Yet rarely do these sites take into account the unique challenges of new CS teachers who often have not had formal training in CS. In response to a documented lack of teachers' engagement on these sites, we interviewed 17 CS teachers to learn more about the ways in which these sites are and are not meeting teachers' needs for curriculum resources. We discuss our findings about how teachers use, adapt, and share resources and then provide several suggestions for designing resource sharing sites that support teachers who have varying levels of experience teaching CS.

We present a system for efficiently editing video of dialogue-driven scenes. The input to our system is a standard film script and multiple video takes, each capturing a different camera framing or performance of the complete scene. Our system then automatically selects the most appropriate clip from one of the input takes, for each line of dialogue, based on a user-specified set of film-editing idioms. Our system starts by segmenting the input script into lines of dialogue and then splitting each input take into a sequence of clips time-aligned with each line. Next, it labels the script and the clips with high-level structural information (e.g., emotional sentiment of dialogue, camera framing of clip, etc.). After this pre-process, our interface offers a set of basic idioms that users can combine in a variety of ways to build custom editing styles. Our system encodes each basic idiom as a Hidden Markov Model that relates editing decisions to the labels extracted in the pre-process. For short scenes (< 2 minutes, 8--16 takes, 6--27 lines of dialogue) applying the user-specified combination of idioms to the pre-processed inputs generates an edited sequence in 2--3 seconds. We show that this is significantly faster than the hours of user time skilled editors typically require to produce such edits and that the quick feedback lets users iteratively explore the space of edit designs.

Dozens of online communities have been developed to support high school computer science (CS) teachers by providing them with CS teaching resources. However, these sites have failed to meet teachers' needs and are widely underused. Despite this underutilization, organizations continue to create new communities with content that overlaps with the materials provided within existing communities. Our research explores the barriers to CS teachers' engagement with online resources and their attitudes toward online communities. We find that teachers are frustrated by the time and difficulty required to navigate the sites and find useful information. It appears the barriers to accessing these resources cannot be overcome by creating additional large, multipurpose communities. Even though it seems that having large communities would be valuable for increasing access to resources, our research indicates teachers prefer smaller, more specialized communities. We are eager to discuss ideas for designing new communities that provide more relevant content for teachers in a way that is easy for them to find.

In the Hierarchical Temporal Memory (HTM) paradigm the effect of overlap between inputs on the activation of columns in the spatial pooler is studied. Numerical results suggest that similar inputs are represented by similar sets of columns and dissimilar inputs are represented by dissimilar sets of columns. It is shown that the spatial pooler produces these results under certain conditions for the connectivity and proximal thresholds at initialization. Qualitative arguments about the learning dynamics of the spatial pooler are then discussed.