Unsupervised Action Proposal Ranking Through Proposal Recombination

Keywords

Action proposal ranking; Action recognition; Unsupervised method

Abstract

Recently, action proposal methods have played an important role in action recognition tasks, as they reduce the search space dramatically. Most unsupervised action proposal methods tend to generate hundreds of action proposals which include many noisy, inconsistent, and unranked action proposals, while supervised action proposal methods take advantage of predefined object detectors (e.g., human detector) to refine and score the action proposals, but they require thousands of manual annotations to train. Given the action proposals in a video, the goal of the proposed work is to generate a few better action proposals that are ranked properly. In our approach, we first divide action proposal into sub-proposal and then use Dynamic Programming based graph optimization scheme to select the optimal combinations of sub-proposals from different proposals and assign each new proposal a score. We propose a new unsupervised image-based actionness detector that leverages web images and employs it as one of the node scores in our graph formulation. Moreover, we capture motion information by estimating the number of motion contours within each action proposal patch. The proposed method is an unsupervised method that neither needs bounding box annotations nor video level labels, which is desirable with the current explosion of large-scale action datasets. Our approach is generic and does not depend on a specific action proposal method. We evaluate our approach on several publicly available trimmed and untrimmed datasets and obtain better performance compared to several proposal ranking methods. In addition, we demonstrate that properly ranked proposals produce significantly better action detection as compared to state-of-the-art proposal based methods.

Publication Date

8-1-2017

Publication Title

Computer Vision and Image Understanding

Volume

161

Number of Pages

42-50

Document Type

Article

Personal Identifier

scopus

DOI Link

https://doi.org/10.1016/j.cviu.2017.06.001

Socpus ID

85020680717 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85020680717

This document is currently not available here.

Share

COinS