Generalized rank pooling for activity recognition
-
Altmetric Citations
Cherian, Anoop; Fernando, Basura; Harandi, Mehrtash; Gould, Stephen
Description
Most popular deep models for action recognition split video sequences into short sub-sequences consisting of a few frames, frame-based features are then pooled for recognizing the activity. Usually, this pooling step discards the temporal order of the frames, which could otherwise be used for better recognition. Towards this end, we propose a novel pooling method, generalized rank pooling (GRP), that takes as input, features from the intermediate layers of a CNN that is trained on tiny...[Show more]
Collections | ANU Research Publications |
---|---|
Date published: | 2017 |
Type: | Conference paper |
URI: | http://hdl.handle.net/1885/294472 |
Source: | Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 |
DOI: | 10.1109/CVPR.2017.172 |
Access Rights: | Open Access |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
grp_v3.pdf | 1.54 MB | Adobe PDF |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator