Speech2Action: Cross-Modal Supervision for Action Recognition

CVPR 2020

Speech2Action: Cross-Modal Supervision for Action Recognition

Nov 12, 2020
|
46 views
|
Details
Authors: Arsha Nagrani, Chen Sun, David Ross, Rahul Sukthankar, Cordelia Schmid, Andrew Zisserman Description: Is it possible to guess human action from dialogue alone? In this work we investigate the link between spoken words and actions in movies. We note that movie screenplays describe actions, as well as contain the speech of characters and hence can be used to learn this correlation with no additional supervision. We train a BERT-based Speech2Action classifier on over a thousand movie screenplays, to predict action labels from transcribed speech segments. We then apply this model to the speech segments of a large unlabelled movie corpus (188M speech segments from 288K movies). Using the predictions of this model, we obtain weak action labels for over 800K video clips. By training on these video clips, we demonstrate superior action recognition performance on standard action recognition benchmarks, without using a single manually labelled action example.

Comments
loading...