Transfer learning with fine tuning for human action recognition from still images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F21%3A50018494" target="_blank" >RIV/62690094:18450/21:50018494 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/article/10.1007/s11042-021-10753-y" target="_blank" >https://link.springer.com/article/10.1007/s11042-021-10753-y</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s11042-021-10753-y" target="_blank" >10.1007/s11042-021-10753-y</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Transfer learning with fine tuning for human action recognition from still images

Popis výsledku v původním jazyce

Still image-based human action recognition (HAR) is one of the most challenging research problems in the field of computer vision. Some of the significant reasons to support this claim are the availability of few datasets as well as fewer images per action class and the existence of many confusing classes in the datasets and comparing with video-based data. There is the unavailability of temporal information. In this work, we train some of the most reputed Convolutional Neural Network (CNN) based architectures using transfer learning after fine-tuned those suitably to develop a model for still image-based HAR. Since the number of images per action classes is found to be significantly less in number, we have also applied some well-known data augmentation techniques to increase the amount of data, which is always a need for deep learning-based models. Two benchmark datasets used for validating our model are Stanford 40 and PPMI, which are better known for their confusing action classes and the presence of occluded images and random poses of subjects. Results obtained by our model on these datasets outperform some of the benchmark results reported in the literature by a considerable margin. Class imbalance is deliberately introduced in the said datasets to better explore the robustness of the proposed model. The source code of the present work is available at: https://github.com/saikat021/Transfer-Learning-Based-HAR

Název v anglickém jazyce

Transfer learning with fine tuning for human action recognition from still images

Popis výsledku anglicky

Still image-based human action recognition (HAR) is one of the most challenging research problems in the field of computer vision. Some of the significant reasons to support this claim are the availability of few datasets as well as fewer images per action class and the existence of many confusing classes in the datasets and comparing with video-based data. There is the unavailability of temporal information. In this work, we train some of the most reputed Convolutional Neural Network (CNN) based architectures using transfer learning after fine-tuned those suitably to develop a model for still image-based HAR. Since the number of images per action classes is found to be significantly less in number, we have also applied some well-known data augmentation techniques to increase the amount of data, which is always a need for deep learning-based models. Two benchmark datasets used for validating our model are Stanford 40 and PPMI, which are better known for their confusing action classes and the presence of occluded images and random poses of subjects. Results obtained by our model on these datasets outperform some of the benchmark results reported in the literature by a considerable margin. Class imbalance is deliberately introduced in the said datasets to better explore the robustness of the proposed model. The source code of the present work is available at: https://github.com/saikat021/Transfer-Learning-Based-HAR

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Multimedia Tools and Applications

ISSN

1380-7501

e-ISSN

—

Svazek periodika

80

Číslo periodika v rámci svazku

13

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

32

Strana od-do

20547-20578

Kód UT WoS článku

000626425600001

EID výsledku v databázi Scopus

2-s2.0-85102308234