Discriminative Dictionary Design for Action Classification in Still Images and Videos

05/20/2020
by   Abhinaba Roy, et al.
0

In this paper, we address the problem of action recognition from still images and videos. Traditional local features such as SIFT, STIP etc. invariably pose two potential problems: 1) they are not evenly distributed in different entities of a given category and 2) many of such features are not exclusive of the visual concept the entities represent. In order to generate a dictionary taking the aforementioned issues into account, we propose a novel discriminative method for identifying robust and category specific local features which maximize the class separability to a greater extent. Specifically, we pose the selection of potent local descriptors as filtering based feature selection problem which ranks the local features per category based on a novel measure of distinctiveness. The underlying visual entities are subsequently represented based on the learned dictionary and this stage is followed by action classification using the random forest model followed by label propagation refinement. The framework is validated on the action recognition datasets based on still images (Stanford-40) as well as videos (UCF-50) and exhibits superior performances than the representative methods from the literature.

READ FULL TEXT
research
03/13/2016

Learning zeroth class dictionary for human action recognition

In this paper, a discriminative two-phase dictionary learning framework ...
research
03/27/2015

Discriminative Bayesian Dictionary Learning for Classification

We propose a Bayesian approach to learn discriminative dictionaries for ...
research
07/13/2020

IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos

Most current action recognition methods heavily rely on appearance infor...
research
07/14/2022

Deep Dictionary Learning with An Intra-class Constraint

In recent years, deep dictionary learning (DDL)has attracted a great amo...
research
11/13/2015

Transductive Zero-Shot Action Recognition by Word-Vector Embedding

The number of categories for action recognition is growing rapidly and i...
research
07/13/2020

Universal-to-Specific Framework for Complex Action Recognition

Video-based action recognition has recently attracted much attention in ...
research
07/20/2014

Feature and Region Selection for Visual Learning

Visual learning problems such as object classification and action recogn...

Please sign up or login with your details

Forgot password? Click here to reset