Report
Espresso: High Compression For Rich Extraction From Videos for Your Vision-Language Model
| العنوان: | Espresso: High Compression For Rich Extraction From Videos for Your Vision-Language Model |
|---|---|
| المؤلفون: | Yu, Keunwoo Peter, Dave, Achal, Ambrus, Rares, Mercat, Jean |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | Most of the current vision-language models (VLMs) for videos struggle to understand videos longer than a few seconds. This is primarily due to the fact that they do not scale to utilizing a large number of frames. In order to address this limitation, we propose Espresso, a novel method that extracts and compresses spatial and temporal information separately. Through extensive evaluations, we show that spatial and temporal compression in Espresso each have a positive impact on the long-form video understanding capabilities; when combined, their positive impact increases. Furthermore, we show that Espresso's performance scales well with more training data, and that Espresso is far more effective than the existing projectors for VLMs in long-form video understanding. Moreover, we devise a more difficult evaluation setting for EgoSchema called "needle-in-a-haystack" that multiplies the lengths of the input videos. Espresso achieves SOTA performance on this task, outperforming the SOTA VLMs that have been trained on much more training data. Comment: 11 pages |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2412.04729 |
| رقم الانضمام: | edsarx.2412.04729 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |