Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912281805193216 |
|---|---|
| author | Zhang, Wentao Guo, Junliang He, Tianyu Zhao, Li Xu, Linli Bian, Jiang |
| author_facet | Zhang, Wentao Guo, Junliang He, Tianyu Zhao, Li Xu, Linli Bian, Jiang |
| contents | People interact with the real-world largely dependent on visual signal, which are ubiquitous and illustrate detailed demonstrations. In this paper, we explore utilizing visual signals as a new interface for models to interact with the environment. Specifically, we choose videos as a representative visual signal. And by training autoregressive Transformers on video datasets in a self-supervised objective, we find that the model emerges a zero-shot capability to infer the semantics from a demonstration video, and imitate the semantics to an unseen scenario. This allows the models to perform unseen tasks by watching the demonstration video in an in-context manner, without further fine-tuning. To validate the imitation capacity, we design various evaluation metrics including both objective and subjective measures. The results show that our models can generate high-quality video clips that accurately align with the semantic guidance provided by the demonstration videos, and we also show that the imitation capacity follows the scaling law. Code and models have been open-sourced. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_07356 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators Zhang, Wentao Guo, Junliang He, Tianyu Zhao, Li Xu, Linli Bian, Jiang Computer Vision and Pattern Recognition People interact with the real-world largely dependent on visual signal, which are ubiquitous and illustrate detailed demonstrations. In this paper, we explore utilizing visual signals as a new interface for models to interact with the environment. Specifically, we choose videos as a representative visual signal. And by training autoregressive Transformers on video datasets in a self-supervised objective, we find that the model emerges a zero-shot capability to infer the semantics from a demonstration video, and imitate the semantics to an unseen scenario. This allows the models to perform unseen tasks by watching the demonstration video in an in-context manner, without further fine-tuning. To validate the imitation capacity, we design various evaluation metrics including both objective and subjective measures. The results show that our models can generate high-quality video clips that accurately align with the semantic guidance provided by the demonstration videos, and we also show that the imitation capacity follows the scaling law. Code and models have been open-sourced. |
| title | Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.07356 |