Video understanding using multimodal deep learning
<p>Our experience of the world is multimodal, however deep learning networks have been traditionally designed for and trained on unimodal inputs such as images, audio segments or text. In this thesis we develop strategies to exploit multimodal information (in the form of vision, text, speech a...
Main Author: | Nagrani, A |
---|---|
Other Authors: | Zisserman, A |
Format: | Thesis |
Language: | English |
Published: |
2020
|
Subjects: |
Similar Items
-
Sign language understanding using multimodal learning
by: Momeni, L
Published: (2024) -
End-to-end learning, and audio-visual human-centric video understanding
by: Brown, A
Published: (2022) -
Learning with multimodal self-supervision
by: Chen, H
Published: (2021) -
Holistic image understanding with deep learning and dense random fields
by: Zheng, S
Published: (2016) -
Self-supervised video representation learning
by: Han, T
Published: (2022)