Related papers: Mining Mid-level Features for Action Recognition B…
The computer vision community is currently focusing on solving action recognition problems in real videos, which contain thousands of samples with many challenges. In this process, Deep Convolutional Neural Networks (D-CNNs) have played a…
Fine-grained human action recognition is a core research topic in computer vision. Inspired by the recently proposed hierarchy representation of fine-grained actions in FineGym and SlowFast network for action recognition, we propose a novel…
Algorithmic detection of facial palsy offers the potential to improve current practices, which usually involve labor-intensive and subjective assessments by clinicians. In this paper, we present a multimodal fusion-based deep learning model…
Skeleton data is of low dimension. However, there is a trend of using very deep and complicated feedforward neural networks to model the skeleton sequence without considering the complexity in recent year. In this paper, a simple yet…
Object skeletons are useful for object representation and object detection. They are complementary to the object contour, and provide extra information, such as how object scale (thickness) varies among object parts. But object skeleton…
Human action recognition is an active research area in computer vision. Although great process has been made, previous methods mostly recognize actions based on depth data at only one scale, and thus they often neglect multi-scale features…
Human action recognition involves the characterization of human actions through the automated analysis of video data and is integral in the development of smart computer vision systems. However, several challenges like dynamic backgrounds,…
This paper addresses the medical imaging problem of joint detection in the upper limbs, viz. elbow, shoulder, wrist and finger joints. Localization of joints from X-Ray and Computerized Tomography (CT) scans is an essential step for the…
Gait recognition captures gait patterns from the walking sequence of an individual for identification. Most existing gait recognition methods learn features from silhouettes or skeletons for the robustness to clothing, carrying, and other…
Articulated hand pose estimation is a challenging task for human-computer interaction. The state-of-the-art hand pose estimation algorithms work only with one or a few subjects for which they have been calibrated or trained. Particularly,…
In person re-identification (ReID) tasks, many works explore the learning of part features to improve the performance over global image features. Existing methods explicitly extract part features by either using a hand-designed image…
Recently, with the availability of cost-effective depth cameras coupled with real-time skeleton estimation, the interest in skeleton-based human action recognition is renewed. Most of the existing skeletal representation approaches use…
Automated human action recognition is one of the most attractive and practical research fields in computer vision, in spite of its high computational costs. In such systems, the human action labelling is based on the appearance and patterns…
Vision-based person, hand or face detection approaches have achieved incredible success in recent years with the development of deep convolutional neural network (CNN). In this paper, we take the inherent correlation between the body and…
In recent years, camera-based localization has been widely used for robotic applications, and most proposed algorithms rely on local features extracted from recorded images. For better performance, the features used for open-loop…
Part-level representations are essential for robust person re-identification. However, common errors that arise during pedestrian detection frequently result in severe misalignment problems for body parts, which degrade the quality of part…
Human gesture recognition has assumed a capital role in industrial applications, such as Human-Machine Interaction. We propose an approach for segmentation and classification of dynamic gestures based on a set of handcrafted features, which…
The data-driven approach that learns an optimal representation of vision features like skeleton frames or RGB videos is currently a dominant paradigm for activity recognition. While great improvements have been achieved from existing single…
The aim of this work is to contribute to the development of a tactile device for visually impaired and blind persons in order to let them to understand actions of the surrounding people and to interact with them. First, based on the…
Automatic vertebrae identification and localization from arbitrary CT images is challenging. Vertebrae usually share similar morphological appearance. Because of pathology and the arbitrary field-of-view of CT scans, one can hardly rely on…