Improving Human Activity Recognition Through Ranking and Re-ranking

12/11/2015
by   Zhenzhong Lan, et al.
0

We propose two well-motivated ranking-based methods to enhance the performance of current state-of-the-art human activity recognition systems. First, as an improvement over the classic power normalization method, we propose a parameter-free ranking technique called rank normalization (RaN). RaN normalizes each dimension of the video features to address the sparse and bursty distribution problems of Fisher Vectors and VLAD. Second, inspired by curriculum learning, we introduce a training-free re-ranking technique called multi-class iterative re-ranking (MIR). MIR captures relationships among action classes by separating easy and typical videos from difficult ones and re-ranking the prediction scores of classifiers accordingly. We demonstrate that our methods significantly improve the performance of state-of-the-art motion features on six real-world datasets.

READ FULL TEXT

page 3

page 5

page 6

page 7

page 8

research
12/03/2019

RSA: Randomized Simulation as Augmentation for Robust Human Action Recognition

Despite the rapid growth in datasets for video activity, stable robust a...
research
04/25/2018

From Real to Complex: Enhancing Radio-based Activity Recognition Using Complex-Valued CSI

Activity recognition is an important component of many pervasive computi...
research
10/21/2021

A scale invariant ranking function for learning-to-rank: a real-world use case

Nowadays, Online Travel Agencies provide the main service for booking ho...
research
08/03/2021

Non-local Graph Convolutional Network for joint Activity Recognition and Motion Prediction

3D skeleton-based motion prediction and activity recognition are two int...
research
05/14/2019

Disparity-Augmented Trajectories for Human Activity Recognition

Numerous methods for human activity recognition have been proposed in th...
research
04/26/2016

Towards Miss Universe Automatic Prediction: The Evening Gown Competition

Can we predict the winner of Miss Universe after watching how they strid...
research
06/13/2019

Iterative subtraction method for Feature Ranking

Training features used to analyse physical processes are often highly co...

Please sign up or login with your details

Forgot password? Click here to reset