Dr. Adil Mehmood Khan
Associate Dean of Education,
Associate Professor,
Head of Machine Learning & Knowledge Representation Lab,
Innopolis University, Russia
Title: Improving Complex Human Action Recognition through Video Recordin
Abstract:
Automatic understanding of sensory data and especially videos is one of the complex problems in machine learning and computer vision. An important area in the field of video analysis is human action recognition (HAR). Though a large number of HAR systems have already been developed, there is plenty of daily life actions that are difficult to recognize, due to several reasons, such as recording on different devices, poor video quality and similarities among actions. Development in the field of deep learning, especially in convolutional neural networks (CNN), has provided us with methods that are well-suited for the tasks of image and video recognition. In this talk I’ll share our experience of implementing a CNN-based hierarchical recognition approach to recognize 20 most difficult-to-recognize actions from the Kinetics dataset. In addition, will setup the direction how we can explore and utilize deep learning approaches in the field of sensory network efficacy and application on the data captured from such networks.