Can I read Similarity R-C3D for Few-shot Temporal Activity Detection on EtoBox?

Similarity R-C3D for Few-shot Temporal Activity Detection by Xu, Huijuan; Kang, Bingyi; Sun, Ximeng; Feng, Jiashi; Saenko, Kate; Darrell, Trevor is a scholarly article available to read on EtoBox.

What is Similarity R-C3D for Few-shot Temporal Activity Detection about?

Many activities of interest are rare events, with only a few labeled examples available. Therefore models for temporal activity detection which are able to learn from a few examples are desirable. In this paper, we present a conceptually simple and general yet novel framework for few-shot temporal activity detection which detects the start and end time of the few-shot input activities in an untrimmed video. Our model is end-to-end trainable and can benefit from more few-shot examples. At test time, each proposal is assigned the label of the few-shot activity class corresponding to the maximum similarity score. Our Similarity R-C3D method outperforms previous work on three large-scale benchmarks for temporal activity detection (THUMOS14, ActivityNet1.2, and ActivityNet1.3 datasets) in the few-shot setting. Our code will be made available.

Author

Xu, Huijuan; Kang, Bingyi; Sun, Ximeng; Feng, Jiashi; Saenko, Kate; Darrell, Trevor

Published

2018

Language

EN