Saved in:
Bibliographic Details
Main Authors: Goudarzi, Sajad, Zamanifard, Samaneh
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.17160
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914001947983872
author Goudarzi, Sajad
Zamanifard, Samaneh
author_facet Goudarzi, Sajad
Zamanifard, Samaneh
contents Traditional video-based learning remains passive, offering limited opportunities for users to engage dynamically with content. While current AI-powered tools offer transcription and summarization, they lack real-time, region-specific interaction capabilities. This paper introduces Untwist, an AI-driven system that enables interactive video learning by allowing users to ask questions about the entire video or specific regions using a bounding box, receiving context-aware, multimodal responses. By integrating GPT APIs with Computer Vision techniques, Untwist extracts, processes, and structures video content to enhance comprehension. Our approach addresses GPT-4o spatial weakness by leveraging annotated frames instead of raw coordinate data, significantly improving accuracy in localizing and interpreting video content. This paper describes the system architecture, including video pre-processing and real-time interaction, and outlines how Untwist can transform passive video consumption into an interactive, AI-driven learning experience with the potential to enhance engagement and comprehension.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17160
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Play and Pause: Turning GPT-4o Spatial Weakness into a Strength for In-Depth Interactive Video Learning
Goudarzi, Sajad
Zamanifard, Samaneh
Computer Vision and Pattern Recognition
Artificial Intelligence
Traditional video-based learning remains passive, offering limited opportunities for users to engage dynamically with content. While current AI-powered tools offer transcription and summarization, they lack real-time, region-specific interaction capabilities. This paper introduces Untwist, an AI-driven system that enables interactive video learning by allowing users to ask questions about the entire video or specific regions using a bounding box, receiving context-aware, multimodal responses. By integrating GPT APIs with Computer Vision techniques, Untwist extracts, processes, and structures video content to enhance comprehension. Our approach addresses GPT-4o spatial weakness by leveraging annotated frames instead of raw coordinate data, significantly improving accuracy in localizing and interpreting video content. This paper describes the system architecture, including video pre-processing and real-time interaction, and outlines how Untwist can transform passive video consumption into an interactive, AI-driven learning experience with the potential to enhance engagement and comprehension.
title Beyond Play and Pause: Turning GPT-4o Spatial Weakness into a Strength for In-Depth Interactive Video Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.17160