Online pre-training with long-form videos
Not on the map. Why?
Abstract (arXiv)
In this study, we investigate the impact of online pre-training with continuous video clips. We will examine three methods for pre-training (masked image modeling, contrastive learning, and knowledge distillation), and assess the performance on downstream action recognition tasks. As a result, online pre-training with contrast learning showed the highest performance in downstream tasks. Our findings suggest that learning from long-form videos can be helpful for action recognition with short videos.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 12 references that are in the map. First posted on arXiv 28 Aug 2024.
Builds on
10 of 12 references.
References · 10
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2017The Kinetics Human Action Video Datasetcited by 1,894
- 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,305
- 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
- 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
- 2021VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examplescited by 154
- 2022A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyondcited by 58
- 2023Teacher-Student Architecture for Knowledge Distillation: A Surveycited by 26
- 2023End-to-End Spatio-Temporal Action Localisation with Video Transformerscited by 20
Built on by
Not cited yet.