GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909199459418112 |
|---|---|
| author | Dai, Guangzhao Shu, Xiangbo Wu, Wenhao Yan, Rui Zhang, Jiachao |
| author_facet | Dai, Guangzhao Shu, Xiangbo Wu, Wenhao Yan, Rui Zhang, Jiachao |
| contents | Vision-Language Models (VLMs), pre-trained on large-scale datasets, have shown impressive performance in various visual recognition tasks. This advancement paves the way for notable performance in Zero-Shot Egocentric Action Recognition (ZS-EAR). Typically, VLMs handle ZS-EAR as a global video-text matching task, which often leads to suboptimal alignment of vision and linguistic knowledge. We propose a refined approach for ZS-EAR using VLMs, emphasizing fine-grained concept-description alignment that capitalizes on the rich semantic and contextual details in egocentric videos. In this paper, we introduce GPT4Ego, a straightforward yet remarkably potent VLM framework for ZS-EAR, designed to enhance the fine-grained alignment of concept and description between vision and language. Extensive experiments demonstrate GPT4Ego significantly outperforms existing VLMs on three large-scale egocentric video benchmarks, i.e., EPIC-KITCHENS-100 (33.2%, +9.4%), EGTEA (39.6%, +5.5%), and CharadesEgo (31.5%, +2.6%). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10039 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition Dai, Guangzhao Shu, Xiangbo Wu, Wenhao Yan, Rui Zhang, Jiachao Computer Vision and Pattern Recognition Vision-Language Models (VLMs), pre-trained on large-scale datasets, have shown impressive performance in various visual recognition tasks. This advancement paves the way for notable performance in Zero-Shot Egocentric Action Recognition (ZS-EAR). Typically, VLMs handle ZS-EAR as a global video-text matching task, which often leads to suboptimal alignment of vision and linguistic knowledge. We propose a refined approach for ZS-EAR using VLMs, emphasizing fine-grained concept-description alignment that capitalizes on the rich semantic and contextual details in egocentric videos. In this paper, we introduce GPT4Ego, a straightforward yet remarkably potent VLM framework for ZS-EAR, designed to enhance the fine-grained alignment of concept and description between vision and language. Extensive experiments demonstrate GPT4Ego significantly outperforms existing VLMs on three large-scale egocentric video benchmarks, i.e., EPIC-KITCHENS-100 (33.2%, +9.4%), EGTEA (39.6%, +5.5%), and CharadesEgo (31.5%, +2.6%). |
| title | GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.10039 |