Optimizing GPT for Video Understanding: Zero-Shot Performance and Prompt Engineering
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _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 |