Saved in:
Bibliographic Details
Main Authors: Beliaev, Mark, Yang, Victor, Raju, Madhura, Sun, Jiachen, Hu, Xinghai
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.09573
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908338016485376
author Beliaev, Mark
Yang, Victor
Raju, Madhura
Sun, Jiachen
Hu, Xinghai
author_facet Beliaev, Mark
Yang, Victor
Raju, Madhura
Sun, Jiachen
Hu, Xinghai
contents In this study, we tackle industry challenges in video content classification by exploring and optimizing GPT-based models for zero-shot classification across seven critical categories of video quality. We contribute a novel approach to improving GPT's performance through prompt optimization and policy refinement, demonstrating that simplifying complex policies significantly reduces false negatives. Additionally, we introduce a new decomposition-aggregation-based prompt engineering technique, which outperforms traditional single-prompt methods. These experiments, conducted on real industry problems, show that thoughtful prompt design can substantially enhance GPT's performance without additional finetuning, offering an effective and scalable solution for improving video classification.
format Preprint
id arxiv_https___arxiv_org_abs_2502_09573
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimizing GPT for Video Understanding: Zero-Shot Performance and Prompt Engineering
Beliaev, Mark
Yang, Victor
Raju, Madhura
Sun, Jiachen
Hu, Xinghai
Computer Vision and Pattern Recognition
Computation and Language
Machine Learning
In this study, we tackle industry challenges in video content classification by exploring and optimizing GPT-based models for zero-shot classification across seven critical categories of video quality. We contribute a novel approach to improving GPT's performance through prompt optimization and policy refinement, demonstrating that simplifying complex policies significantly reduces false negatives. Additionally, we introduce a new decomposition-aggregation-based prompt engineering technique, which outperforms traditional single-prompt methods. These experiments, conducted on real industry problems, show that thoughtful prompt design can substantially enhance GPT's performance without additional finetuning, offering an effective and scalable solution for improving video classification.
title Optimizing GPT for Video Understanding: Zero-Shot Performance and Prompt Engineering
topic Computer Vision and Pattern Recognition
Computation and Language
Machine Learning
url https://arxiv.org/abs/2502.09573