Adaptive Video Understanding Agent: Enhancing efficiency with dynamic frame sampling and feedback-driven reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916456191492096 |
|---|---|
| author | Jeoung, Sullam Huybrechts, Goeric Ganesh, Bhavana Galstyan, Aram Bodapati, Sravan |
| author_facet | Jeoung, Sullam Huybrechts, Goeric Ganesh, Bhavana Galstyan, Aram Bodapati, Sravan |
| contents | Understanding long-form video content presents significant challenges due to its temporal complexity and the substantial computational resources required. In this work, we propose an agent-based approach to enhance both the efficiency and effectiveness of long-form video understanding by utilizing large language models (LLMs) and their tool-harnessing ability. A key aspect of our method is query-adaptive frame sampling, which leverages the reasoning capabilities of LLMs to process only the most relevant frames in real-time, and addresses an important limitation of existing methods which typically involve sampling redundant or irrelevant frames. To enhance the reasoning abilities of our video-understanding agent, we leverage the self-reflective capabilities of LLMs to provide verbal reinforcement to the agent, which leads to improved performance while minimizing the number of frames accessed. We evaluate our method across several video understanding benchmarks and demonstrate that not only it enhances state-of-the-art performance but also improves efficiency by reducing the number of frames sampled. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20252 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adaptive Video Understanding Agent: Enhancing efficiency with dynamic frame sampling and feedback-driven reasoning Jeoung, Sullam Huybrechts, Goeric Ganesh, Bhavana Galstyan, Aram Bodapati, Sravan Computer Vision and Pattern Recognition Artificial Intelligence Understanding long-form video content presents significant challenges due to its temporal complexity and the substantial computational resources required. In this work, we propose an agent-based approach to enhance both the efficiency and effectiveness of long-form video understanding by utilizing large language models (LLMs) and their tool-harnessing ability. A key aspect of our method is query-adaptive frame sampling, which leverages the reasoning capabilities of LLMs to process only the most relevant frames in real-time, and addresses an important limitation of existing methods which typically involve sampling redundant or irrelevant frames. To enhance the reasoning abilities of our video-understanding agent, we leverage the self-reflective capabilities of LLMs to provide verbal reinforcement to the agent, which leads to improved performance while minimizing the number of frames accessed. We evaluate our method across several video understanding benchmarks and demonstrate that not only it enhances state-of-the-art performance but also improves efficiency by reducing the number of frames sampled. |
| title | Adaptive Video Understanding Agent: Enhancing efficiency with dynamic frame sampling and feedback-driven reasoning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2410.20252 |