Related papers: Texture-Based Input Feature Selection for Action R…
Action recognition is an important yet challenging task in computer vision. In this paper, we propose a novel deep-based framework for action recognition, which improves the recognition accuracy by: 1) deriving more precise features for…
Objective monitoring and assessment of human motor behavior can improve the diagnosis and management of several medical conditions. Over the past decade, significant advances have been made in the use of wearable technology for continuously…
We address the problem of action detection in videos. Driven by the latest progress in object detection from 2D images, we build action models using rich feature hierarchies derived from shape and kinematic cues. We incorporate appearance…
Anomaly detection (AD) in images is a fundamental computer vision problem by deep learning neural network to identify images deviating significantly from normality. The deep features extracted from pretrained models have been proved to be…
Upsurging abnormal activities in crowded locations such as airports, train stations, bus stops, shopping malls, etc., urges the necessity for an intelligent surveillance system. An intelligent surveillance system can differentiate between…
Detecting and recognizing human action in videos with crowded scenes is a challenging problem due to the complex environment and diversity events. Prior works always fail to deal with this problem in two aspects: (1) lacking utilizing…
This article proposes a novel approach for augmenting generative adversarial network (GAN) with a self-supervised task in order to improve its ability for encoding video representations that are useful in downstream tasks such as human…
This paper studies introducing viewpoint invariant feature representations in existing action recognition architecture. Despite significant progress in action recognition, efficiently handling geometric variations in large-scale datasets…
Recent research into human action recognition (HAR) has focused predominantly on skeletal action recognition and video-based methods. With the increasing availability of consumer-grade depth sensors and Lidar instruments, there is a growing…
Pedestrian analysis plays a vital role in intelligent video surveillance and is a key component for security-centric computer vision systems. Despite that the convolutional neural networks are remarkable in learning discriminative features…
Recently, there has been a remarkable increase in the interest towards skeleton-based action recognition within the research community, owing to its various advantageous features, including computational efficiency, representative features,…
Research on human action classification has made significant progresses in the past few years. Most deep learning methods focus on improving performance by adding more network components. We propose, however, to better utilize auxiliary…
The recognition of human actions in videos is one of the most active research fields in computer vision. The canonical approach consists in a more or less complex preprocessing stages of the raw video data, followed by a relatively simple…
Despite the notable progress made in action recognition tasks, not much work has been done in action recognition specifically for human-robot interaction. In this paper, we deeply explore the characteristics of the action recognition task…
Most action recognition models today are highly parameterized, and evaluated on datasets with appearance-wise distinct classes. It has also been shown that 2D Convolutional Neural Networks (CNNs) tend to be biased toward texture rather than…
This paper studies how to introduce viewpoint-invariant feature representations that can help action recognition and detection. Although we have witnessed great progress of action recognition in the past decade, it remains challenging yet…
The current paper proposes a novel neural network model for recognizing visually perceived human actions. The proposed multiple spatio-temporal scales recurrent neural network (MSTRNN) model is derived by introducing multiple timescale…
Human Pose (HP) estimation is actively researched because of its wide range of applications. However, even estimators pre-trained on large datasets may not perform satisfactorily due to a domain gap between the training and test data. To…
Most existing Convolutional Neural Networks(CNNs) used for action recognition are either difficult to optimize or underuse crucial temporal information. Inspired by the fact that the recurrent model consistently makes breakthroughs in the…
Human action recognition still exists many challenging problems such as different viewpoints, occlusion, lighting conditions, human body size and the speed of action execution, although it has been widely used in different areas. To tackle…