10 citations · 30 across the 9 of their papers we have counts for
10 papers
Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning
Chen Zhao, Jiajun Ma, Qilong Huang +6
While Multimodal Large Language Models (MLLMs) have advanced video understanding, achieving precise temporal and cross-modal alignment in audiovisual video captioning remains a for…
Artistic Practice Opportunities in CST Evaluations: A Longitudinal Group Deployment of ArtKrit
Catherine Liu, Tao Long, Asya Vaisberg +3
Creativity support tools (CSTs) aim to elevate the quality of artists' creative processes and artifacts. Yet most current CST evaluations overlook temporal and social aspects of to…
Self-Consistency for LLM-Based Motion Trajectory Generation and Verification
Jiaju Ma, R. Kenny Jones, Jiajun Wu +1
Self-consistency has proven to be an effective technique for improving LLM performance on natural language reasoning tasks in a lightweight, unsupervised manner. In this work, we s…
Collaposer: Transforming Photo Collections into Visual Assets for Storytelling with Collages
Jiayi Zhou, Liwenhan Xie, Jiaju Ma +3
Digital collage is an artistic practice that combines image cutouts to tell stories. However, preparing cutouts from a set of photos remains a tedious and time-consuming task. A fo…
Computational Scaffolding of Composition, Value, and Color for Disciplined Drawing
Jiaju Ma, Chau Vu, Asya Lyubavina +2
One way illustrators engage in disciplined drawing - the process of drawing to improve technical skills - is through studying and replicating reference images. However, for many no…
Script2Screen: Supporting Dialogue Scriptwriting with Interactive Audiovisual Generation
Zhecheng Wang, Jiaju Ma, Eitan Grinspun +2
Scriptwriting has traditionally been text-centric, a modality that only partially conveys the produced audiovisual experience. A formative study with professional writers informed…
MoVer: Motion Verification for Motion Graphics Animations
Jiaju Ma, Maneesh Agrawala
While large vision-language models can generate motion graphics animations from text prompts, they regularly fail to include all spatio-temporal properties described in the prompt.…
OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering
Jiahao Nick Li, Zhuohao Jerry Zhang, Jiaju Ma
People often capture memories through photos, screenshots, and videos. While existing AI-based tools enable querying this data using natural language, they only support retrieving…
Editing Motion Graphics Video via Motion Vectorization and Transformation
Sharon Zhang, Jiaju Ma, Jiajun Wu +2
Motion graphics videos are widely used in Web design, digital advertising, animated logos and film title sequences, to capture a viewer's attention. But editing such video is chall…
Automated Conversion of Music Videos into Lyric Videos
Jiaju Ma, Anyi Rao, Li-Yi Wei +3
Musicians and fans often produce lyric videos, a form of music videos that showcase the song's lyrics, for their favorite songs. However, making such videos can be challenging and…