Video self-supervised learning (VSSL) has made significant progress in recent years. However, the exact behavior and dynamics of these models under different forms of …
C Nakatani, H Kawashima… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Abstract This paper proposes Group Activity Feature (GAF) learning in which features of multi-person activity are learned as a compact latent vector. Unlike prior work in which the …
X Li, J Wu, S He, S Kang, Y Yu, L Nie… - Proceedings of the 31st …, 2023 - dl.acm.org
Self-supervised learning methods have shown significant promise in acquiring robust spatiotemporal representations from unlabeled videos. In this work, we address three critical …
Z Chen, H Wang, CW Chen - IEEE Transactions on Multimedia, 2023 - ieeexplore.ieee.org
Self-supervised video representation learning leaves out heavy manual annotation by automatically excavating supervisory signals. Although contrastive learning based …
Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive …
Self-supervised learning is an effective way for label-free model pre-training, especially in the video domain where labeling is expensive. Existing self-supervised works in the video …
IR Dave, S Jenni, M Shah - Proceedings of the AAAI Conference on …, 2024 - ojs.aaai.org
Self-supervised approaches for video have shown impressive results in video understanding tasks. However, unlike early works that leverage temporal self-supervision …
S Bi, Z Hu, H Zhang, J Di, Z Sun - Neural Networks, 2024 - Elsevier
Self-supervised contrastive learning draws on power representational models to acquire generic semantic features from unlabeled data, and the key to training such models lies in …
Q Lai, A Zeng, Y Wang, L Cao, Y Li… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
In this paper, we propose a self-supervised video representation learning (video SSL) method by taking inspiration from cognitive science and neuroscience on human visual …