علي سلطاني نژاد

Recently still image-based human action recognition has become an active research topic in computer vision and pattern recognition. It focuses on identifying a person's action or behavior from a single image. Unlike the traditional action recognition approaches, where videos or image sequences are used, a still image contains no temporal information for action characterization. Therefore, it is demanding to develop efficient methods for still image-based action recognition. Deep learning methods such as convolutional neural networks (CNNs) have recently emerged as a dominant paradigm for machine learning in a variety of domains and they can deliver highly accurate classification results when provided with large enough data sets and respective labels. However, acquiring a suitably large data set for training DCNN is often a significant challenge. This is a major issue in the action recognition domain, where we lack large enough labeled data. Using CNNs along with limited labeled data can be problematic, as this leads to extensive overfitting. In this research, we use transfer learning for human action recognition. For this purpose, three different methods were presented. The TNT method allows us to use the pre-trained weights optimally. The second method, the guidance branch method, increases the network's focus on the person performing the activity, and finally, the third method, the self-attention method, draws the network's attention to more distant objects. In the end, by combining these 3 methods, we benefited from the advantages of each. The proposed method has been eva‎luated on four datasets Stanford40 and Pascal Action VOC, BU101+ and IHAR and it is clear that the proposed method has a higher classification accuracy (93.17%, 92.37%, 92.03% and 92.08%) than the presented methods in this field while using fewer parameters.

شناسايي عمل انسان , يادگيري عميق , شبكه عصبي كانولوشني , يادگيري انتقالي

Human Action Recognition , Deep Learning , Convolutional Neural Networks , Transfer Learning

Ali Soltaninezhad

Dr. Shokoohi