Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos
By Brian Chen, Andrew Rouditchenko, Kevin Duarte, Hilde Kuehne, Samuel Thomas, Angie Boggust, Rameswar Panda, Brian Kingsbury, Rogério Schmidt Feris, David F. Harwath and 3 more. 2021
100 citations recorded by the source corpus.
Multimodal self-supervised learning is getting more and more attention as it allows not only to train large networks without human supervision but also to search and retrieve data across various modalities. In this context, this paper proposes a framework that, starting from a pre-trained backbone, learns a common multimodal embedding space that, in addition to sharing representations across different modalities, enforces a grouping of semantically similar instances. To this end, we extend the concept of instance-level contrastive learning with a multimodal clustering step in the training pipeline to capture semantic similarities across modalities. The resulting embedding space enables retrieval of samples across all modalities, even from unseen datasets and different domains. To evaluate our approach, we train our model on the HowTo100M dataset and evaluate its zero-shot retrieval capabilities in two challenging domains, namely text-to-video retrieval, and temporal action localization, showing state-of-the-art results on four different datasets.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
- Jianfeng Gao
- Jianwei Yang
- Lu Yuan
- Luc Van Gool
- Dacheng Tao
- Zicheng Liu
- Cordelia Schmid
- Ming-Hsuan Yang
In Representation & Self-Supervised Learning
Citations in the corpus
- Florence: A New Foundation Model for Computer Vision (2021, background): “7 MCN (Chen et al., 2021) Image and Video HowTo100M - 33.”
- MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval (2022, unknown): “MCN [10] 2021 ResNeXt-101 HowTo100M 120M 10.”
- BridgeFormer: Bridging Video-text Retrieval with Multiple Choice Questions (2022, unknown): “0 MCN [7] 2021 ResNeXt-101 HowTo100M 120M 10.”