Scale Coding Bag of Deep Features for Human Attribute and Action Recognition

12/14/2016
by   Fahad Shahbaz Khan, et al.
0

Most approaches to human attribute and action recognition in still images are based on image representation in which multi-scale local features are pooled across scale into a single, scale-invariant encoding. Both in bag-of-words and the recently popular representations based on convolutional neural networks, local features are computed at multiple scales. However, these multi-scale convolutional features are pooled into a single scale-invariant representation. We argue that entirely scale-invariant image representations are sub-optimal and investigate approaches to scale coding within a Bag of Deep Features framework. Our approach encodes multi-scale information explicitly during the image encoding stage. We propose two strategies to encode multi-scale information explicitly in the final image representation. We validate our two scale coding techniques on five datasets: Willow, PASCAL VOC 2010, PASCAL VOC 2012, Stanford-40 and Human Attributes (HAT-27). On all datasets, the proposed scale coding approaches outperform both the scale-invariant method and the standard deep features of the same network. Further, combining our scale coding approaches with standard deep features leads to consistent improvement over the state-of-the-art.

READ FULL TEXT

page 2

page 6

page 9

page 11

page 12

page 13

research
02/03/2016

Learning scale-variant and scale-invariant features for deep image classification

Convolutional Neural Networks (CNNs) require large image corpora to be t...
research
05/16/2018

Neural Multi-scale Image Compression

This study presents a new lossy image compression method that utilizes t...
research
06/29/2023

End-to-End Learnable Multi-Scale Feature Compression for VCM

The proliferation of deep learning-based machine vision applications has...
research
01/19/2021

Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences

Human action recognition is an active research area in computer vision. ...
research
05/18/2014

Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice

Video based action recognition is one of the important and challenging p...
research
02/23/2021

Automatic Ship Classification Utilizing Bag of Deep Features

Detection and classification of ships based on their silhouette profiles...
research
06/09/2020

Single Image Deraining via Scale-space Invariant Attention Neural Network

Image enhancement from degradation of rainy artifacts plays a critical r...

Please sign up or login with your details

Forgot password? Click here to reset