Learning from Multiview Correlations in Open-domain Videos

By Nils Holzenberger, Shruti Palaskar, Pranava Swaroop Madhyastha, Florian Metze, Raman Arora. 2018

11 citations recorded by the source corpus.

An increasing number of datasets contain multiple views, such as video, sound and automatic captions. A basic challenge in representation learning is how to leverage multiple views to learn better representations. This is further complicated by the existence of a latent alignment between views, such as between speech and its transcription, and by the multitude of choices for the learning objective. We explore an advanced, correlation-based representation learning method on a 4-way parallel, multimodal dataset, and assess the quality of the learned representations on retrieval-based tasks. We show that the proposed approach produces rich representations that capture most of the information shared across views. Our best models for speech and textual modalities achieve retrieval rates from 70.7% to 96.9% on open-domain, user-generated instructional videos. This shows it is possible to learn reliable representations across disparate, unaligned and noisy modalities, and encourages using the proposed approach on larger datasets.

Subfields: Computer Vision and Pattern Recognition, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Multimodal Learning

Citations in the corpus

Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech (2019, background): “…by the models (Harwath & Glass, 2017; Harwath et al., 2018b; Drexler & Glass, 2017; Alishahi et al., 2017; Harwath et al., 2019; Harwath & Glass, 2019; Havard et al., 2019b), and the impact of jointly training with textual input (Holzenberger et al., 2019; Chrupała, 2019; Pasad et al., 2019).”