RT Conference Proceedings
T1 DA-VLAD: Discriminative action vector of locally aggregated descriptors for action recognition
A1 Murtaza, Fiza
A1 Yousaf, Muhammad Haroon
A1 Velastin Carroza, Sergio Alejandro
AB In this paper, we propose a novel encoding method for the representation of human action videos, that we call Discriminative Action Vector of Locally Aggregated Descriptors (DA-VLAD). DA-VLAD is motivated by the fact that there are many unnecessary and overlapping frames that cause non-discriminative codewords during the training process. DA-VLAD deals with this issue by extracting class-specific clusters and learning the discriminative power of these codewords in the form of informative weights. We use these discriminative action weights with standard VLAD encoding as a contribution of each codeword. DA-VLAD reduces the inter-class similarity efficiently by diminishing the effect of common codewords among multiple action classes during the encoding process. We present the effectiveness of DA-VLAD on two challenging action recognition datasets: UCF101 and HMDB51, improving the state-of-the-art with accuracies of 95.1% and 80.1% respectively.
PB IEEE
SN 978-1-4799-7061-2
YR 2018
FD 2018-09-06
LK https://hdl.handle.net/10016/28937
UL https://hdl.handle.net/10016/28937
LA eng
NO This paper has been presented at : 25th IEEE International Conference on Image Processing (ICIP 2018)
NO We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan X Pascal GPU used for this research. We also acknowledge the support from the Directorate of Advance Studies, Research and Technological development (ASR) & TD, University of Engineering and Technology Taxila, Pakistan. Sergio A Velastin acknowledges funding by the Universidad Carlos III de Madrid, the European Unions Seventh Framework Programme for research, technological development and demonstration under grant agreement n 600371, el Ministerio de Economia y Competitividad (COFUND2013-51509) and Banco Santander.
DS e-Archivo
RD 18 jul. 2024