TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Long Video Retrieval (Background Removed)	YouCook2	MCN	Cap. Avg. R@1	53.4	# 4
Long Video Retrieval (Background Removed)	YouCook2	MCN	Cap. Avg. R@5	75.0	# 4
Long Video Retrieval (Background Removed)	YouCook2	MCN	Cap. Avg. R@10	81.4	# 5

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multimodal-clustering-networks-for-self/long-video-retrieval-background-removed-on)](https://paperswithcode.com/sota/long-video-retrieval-background-removed-on?p=multimodal-clustering-networks-for-self)`

Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos

ICCV 2021 · Brian Chen, Andrew Rouditchenko, Kevin Duarte, Hilde Kuehne, Samuel Thomas, Angie Boggust, Rameswar Panda, Brian Kingsbury, Rogerio Feris, David Harwath, James Glass, Michael Picheny, Shih-Fu Chang ·

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 self-supervised training framework that 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.