Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Yanting, Ren, Yi, Qin, Xiaoting, Zhang, Jue, Yuan, Kehong, Han, Lu, Lin, Qingwei, Zhang, Dongmei, Rajmohan, Saravan, Zhang, Qi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2411.08768
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910696494596096
author Chen, Yanting
Ren, Yi
Qin, Xiaoting
Zhang, Jue
Yuan, Kehong
Han, Lu
Lin, Qingwei
Zhang, Dongmei
Rajmohan, Saravan
Zhang, Qi
author_facet Chen, Yanting
Ren, Yi
Qin, Xiaoting
Zhang, Jue
Yuan, Kehong
Han, Lu
Lin, Qingwei
Zhang, Dongmei
Rajmohan, Saravan
Zhang, Qi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_08768
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sharingan: Extract User Action Sequence from Desktop Recordings
Chen, Yanting
Ren, Yi
Qin, Xiaoting
Zhang, Jue
Yuan, Kehong
Han, Lu
Lin, Qingwei
Zhang, Dongmei
Rajmohan, Saravan
Zhang, Qi
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Sharingan: Extract User Action Sequence from Desktop Recordings
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2411.08768