Designing and Evaluating an Advanced Dance Video Comprehension Tool with In-situ Move Identification Capabilities

Abstract

Analyzing dance moves and routines is a foundational step in learn- ing dance. Videos are often utilized at this step, and advancements in machine learning, particularly in human-movement recognition, could further assist dance learners. We developed and evaluated a Wizard-of-Oz prototype of a video comprehension tool that of- fers automatic in-situ dance move identification functionality. Our system design was informed by an interview study involving 12 dancers to understand the challenges they face when trying to comprehend complex dance videos and taking notes. Subsequently, we conducted a within-subject study with 8 Cuban salsa dancers to identify the benefits of our system compared to an existing tra- ditional feature-based search system. We found that the quality of notes taken by participants improved when using our tool, and they reported a lower workload. Based on participants’ interactions with our system, we offer recommendations on how an AI-powered span-search feature can enhance dance video comprehension tools

Saad Hassan

Assistant Professor

My research interests include human-computer interaction (HCI), accessibility, and computational social science.

Caluã de Lacerda Pataca

PhD Student at RIT

Laleh Nourian

PhD Student at Rochester Institute of Technology

Garreth Tigwell

Assistant Professor at Rochester Institute of Technology

Brianna Davis

Former BS ASL-English Interpreting Student at Rochester Institute of Technology

Will Silver Wagman

CELT Student Researcher

I am set to begin my Master’s in Computer Science, specializing in Machine Learning, at Tulane University in January 2024.