English

Sharingan: Extract User Action Sequence from Desktop Recordings

Computer Vision and Pattern Recognition 2024-11-14 v1 Artificial Intelligence

Abstract

Video recordings of user activities, particularly desktop recordings, offer a rich source of data for understanding user behaviors and automating processes. However, despite advancements in Vision-Language Models (VLMs) and their increasing use in video analysis, extracting user actions from desktop recordings remains an underexplored area. This paper addresses this gap by proposing two novel VLM-based methods for user action extraction: the Direct Frame-Based Approach (DF), which inputs sampled frames directly into VLMs, and the Differential Frame-Based Approach (DiffF), which incorporates explicit frame differences detected via computer vision techniques. We evaluate these methods using a basic self-curated dataset and an advanced benchmark adapted from prior work. Our results show that the DF approach achieves an accuracy of 70% to 80% in identifying user actions, with the extracted action sequences being re-playable though Robotic Process Automation. We find that while VLMs show potential, incorporating explicit UI changes can degrade performance, making the DF approach more reliable. This work represents the first application of VLMs for extracting user action sequences from desktop recordings, contributing new methods, benchmarks, and insights for future research.

Keywords

Cite

@article{arxiv.2411.08768,
  title  = {Sharingan: Extract User Action Sequence from Desktop Recordings},
  author = {Yanting Chen and Yi Ren and Xiaoting Qin and Jue Zhang and Kehong Yuan and Lu Han and Qingwei Lin and Dongmei Zhang and Saravan Rajmohan and Qi Zhang},
  journal= {arXiv preprint arXiv:2411.08768},
  year   = {2024}
}
R2 v1 2026-06-28T19:58:34.608Z