helpResearch questionMultimodal Video Editing Expression and Control
How can hand-drawn sketches be combined with real-time code editing to improve programming efficiency?Direction: Creativity, Design, and Generative Making
Multimodal Video Editing Expression and Control
Stats are based on currently indexed question data; missing sources remain visible.
44
items
11
sources
2025
latest
All questions
44 items
helpResearch questionMultimodal Video Editing Expression and Control
How do hand-drawn sketches at multiple abstraction levels (flowcharts, pseudocode, natural language) support code generation intent?helpResearch questionMultimodal Video Editing Expression and Control
How can sketch interpretation errors be reduced as disruption in programming workflows?lightbulbPractical problemMultimodal Video Editing Expression and Control
Programmers frequently switch between sketches and code, easily losing important ideas.helpResearch questionMultimodal Video Editing Expression and Control
How can YouTube replay heatmap data (MRD) be used to automatically generate highlight videos of user-specified length?helpResearch questionMultimodal Video Editing Expression and Control
How does dynamic programming optimize highlight editing paths to maximize retention of key moments?helpResearch questionMultimodal Video Editing Expression and Control
How can rapid transitions and clip misalignment be avoided when generating fixed-length highlight videos?lightbulbPractical problemMultimodal Video Editing Expression and Control
Viewers often lack flexible editing tools when they need highlight videos of specific durations.helpResearch questionMultimodal Video Editing Expression and Control
How can variant generation, comparison, and customization be performed efficiently in multi-version video editing?helpResearch questionMultimodal Video Editing Expression and Control
How can existing video editing tools be improved to better support multimodal, multi-timeline video variant comparison?helpResearch questionMultimodal Video Editing Expression and Control
Can natural language prompts help users more transparently understand and control generated video editing variants?lightbulbPractical problemMultimodal Video Editing Expression and Control
Video creators struggle to efficiently manage and compare multi-version video content.helpResearch questionMultimodal Video Editing Expression and Control
How can LLMs improve efficiency and flexibility in video editing tasks?helpResearch questionMultimodal Video Editing Expression and Control
How can natural language interaction provide semantic enhancement and intelligent support for video editing?helpResearch questionMultimodal Video Editing Expression and Control
In video editing, can LLMs effectively synthesize automation with user manual control?lightbulbPractical problemMultimodal Video Editing Expression and Control
Video editing is complex and time-consuming, and high technical barriers deter beginners.helpResearch questionMultimodal Video Editing Expression and Control
How can multimodal interaction combining natural language and hand-drawn sketches help users more accurately express video editing needs?helpResearch questionMultimodal Video Editing Expression and Control
Can the ExpressEdit system meet user expectations for parsing precision in time, space, and editing parameters?helpResearch questionMultimodal Video Editing Expression and Control
How much can multimodal interaction reduce video editing complexity and improve editing efficiency?lightbulbPractical problemMultimodal Video Editing Expression and Control
Beginners in informational video editing often face operational complexity and difficulty expressing intent.helpResearch questionMultimodal Video Editing Expression and Control
How can realistic, detail-rich 3D tree models be generated from simple 2D hand-drawn sketches?helpResearch questionMultimodal Video Editing Expression and Control
How can deep learning models effectively predict complex branch structures and enhance species diversity?helpResearch questionMultimodal Video Editing Expression and Control
How can precise control and automated model generation be balanced in user interaction?lightbulbPractical problemMultimodal Video Editing Expression and Control
Users find 3D tree modeling time-consuming and complex, and existing methods lack precision and diversity.helpResearch questionMultimodal Video Editing Expression and Control
How can 'chunking' techniques improve temporal efficiency in video editing?helpResearch questionMultimodal Video Editing Expression and Control
Can text-based semi-automatic video editing tools simultaneously meet needs for temporal efficiency and creative control?helpResearch questionMultimodal Video Editing Expression and Control
What role does topic modeling play in semantic grouping of video transcript content?lightbulbPractical problemMultimodal Video Editing Expression and Control
Early-stage video editing is time-consuming and causes cognitive overload, especially when handling large amounts of footage.helpResearch questionMultimodal Video Editing Expression and Control
What is the impact of different input modes (sketch-guided versus prompt-guided) on 3D generative AI design processes?helpResearch questionMultimodal Video Editing Expression and Control
How do sketch-guided and prompt-guided generative AI differ in creative diversity and design behavior?helpResearch questionMultimodal Video Editing Expression and Control
How can sketch and prompt input modes be integrated to support each stage of the design workflow?lightbulbPractical problemMultimodal Video Editing Expression and Control
Designers struggle to optimize design workflows through input mode choices for 3D generative AI tools.helpResearch questionMultimodal Video Editing Expression and Control
How can neural networks automatically match video segments with sounds from professional sound effect libraries?helpResearch questionMultimodal Video Editing Expression and Control
How can activation maps localize sound sources in video to enable 3D sound field adjustment?helpResearch questionMultimodal Video Editing Expression and Control
How does the Soundify system perform in reducing post-production editing workload?lightbulbPractical problemMultimodal Video Editing Expression and Control
Video editors spend substantial time and effort adding sound effects, and results are often imprecise.helpResearch questionMultimodal Video Editing Expression and Control
How can a voice-driven real-time augmented presentation system interact with augmented text and visual elements?helpResearch questionMultimodal Video Editing Expression and Control
How do voice-driven methods improve flexibility and improvisation in real-time augmented presentations?helpResearch questionMultimodal Video Editing Expression and Control
How can interaction patterns from existing video-edited augmented presentations be extracted and applied to real-time voice-driven system design?lightbulbPractical problemMultimodal Video Editing Expression and Control
Traditional augmented presentation preparation is cumbersome, and real-time presentations lack flexibility and interactivity.helpResearch questionMultimodal Video Editing Expression and Control
How can interactive interfaces improve vectorization of noisy hand-drawn sketches?helpResearch questionMultimodal Video Editing Expression and Control
How can users express design intent through simple operations and influence vectorization algorithm results?helpResearch questionMultimodal Video Editing Expression and Control
How do Delaunay triangulation and Bézier curves improve sketch partitioning and structuring?lightbulbPractical problemMultimodal Video Editing Expression and Control
Non-expert users struggle to efficiently manually vectorize complex sketches.Related papers
CHI 2025
Code Shaping: Iterative Code Editing with Free-form AI-Interpreted Sketching
Ryan Yen, Jian Zhao, Daniel Vogel
CHI 2025
Generating Highlight Videos of a User-Specified Length using Most Replayed Data
Minsun Kim, Dawon Lee, Junyong Noh
CHI 2025
VideoDiff: Human-AI Video Co-Creation with Alternatives
Mina Huh, Ding Li, Kim Pimmel
IUI 2024
LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing
Bryan Wang, Yuliang Li, Zhaoyang Lv
IUI 2024
ExpressEdit: Video Editing with Natural Language and Sketching
Bekzat Tilekbay, Saelyne Yang, Michal A Lewkowicz
CHI 2024
DeepTreeSketch: Neural Graph Prediction for Faithful 3D Tree Modeling from Sketches
Zhihao Liu, Yu LI, Fangyuan Tu
CHI 2024
ChunkyEdit: Text-first video interview editing via chunking
Mackenzie Leake, Wilmot Li
CHI 2024
The Impact of Sketch-guided vs. Prompt-guided 3D Generative AIs on the Design Exploration Process
Seung Won Lee, Tae Hee Jo, Semin Jin
UIST 2023
Soundify: Matching Sound Effects to Video
David Chuan-En Lin, Anastasis Germanidis, Cristóbal Valenzuela
UIST 2022
RealityTalk: Real-time Speech-driven Augmented Presentation for AR Live Storytelling
Jian Liao, Ryo Suzuki, Rubaiat Habib Kazi
CHI 2021
Color by Numbers: Interactive Structuring and Vectorization of Sketch Imagery
Amal Dev Parakkat, Marie-Paule R. Cani, Karan Singh
Adjacent categories
Creativity, Design, and Generative Making
Digital Fabrication Structural Design Tools
142 items
Creativity, Design, and Generative Making
Creative Inspiration and Divergent Thinking
139 items
Creativity, Design, and Generative Making
Control and Co-Creation in Generative Creation
136 items
Creativity, Design, and Generative Making
Creative Workflows and Multi-Stage Pipelines
128 items
Creativity, Design, and Generative Making
Human-AI Co-Creation and Collaborative Interaction
122 items
Creativity, Design, and Generative Making
Edible Information Encoding and Food Interaction Design
108 items
Creativity, Design, and Generative Making
Generative Image Creation and Editing Control
102 items
Creativity, Design, and Generative Making
3D Printing and Digital Fabrication
83 items