.png){kind=icon}
.png){kind=icon}
Return
Self-Supervised Learning for Videos: A Survey
.png){kind=icon}
OA
AI
DOI：10.1145/3577925.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The remarkable success of deep learning in various domains relies on the availability of large-scale annotated datasets. However, obtaining annotations is expensive and requires great effort, which is especially challenging for videos. Moreover, the use of human-generated annotations leads to models with biased learning and poor domain generalization and robustness. As an alternative, self-supervised learning provides a way for representation learning that does not require annotations and has shown promise in both image and video domains. In contrast to the image domain, learning video representations are more challenging due to the temporal dimension, bringing in motion and other environmental dynamics. This also provides opportunities for video-exclusive ideas that advance self-supervised learning in the video and multimodal domains. In this survey, we provide a review of existing approaches on self-supervised learning focusing on the video domain. We summarize these methods into four different categories based on their learning objectives: (1) pretext tasks, (2) generative learning, (3) contrastive learning, and (4) cross-modal agreement. We further introduce the commonly used datasets, downstream evaluation tasks, insights into the limitations of existing works, and the potential future directions in this area.
Keywords:
Self-supervised learning
deep learning
video understanding
zero-shot learning
representation learning
multimodal learning
visual-language models
Journal
IF:
28
Papers:
2.4K
Citations:
3.5W
