Related papers: Gate-Shift-Pose: Enhancing Action Recognition in S…
Skeleton-based human action recognition has attracted a lot of research attention during the past few years. Recent works attempted to utilize recurrent neural networks to model the temporal dependencies between the 3D positional…
Both accuracy and efficiency are significant for pose estimation and tracking in videos. State-of-the-art performance is dominated by two-stages top-down methods. Despite the leading results, these methods are impractical for real-world…
Recent works on pose-based gait recognition have demonstrated the potential of using such simple information to achieve results comparable to silhouette-based methods. However, the generalization ability of pose-based methods on different…
For the two-stream style methods in action recognition, fusing the two streams' predictions is always by the weighted averaging scheme. This fusion method with fixed weights lacks of pertinence to different action videos and always needs…
Human skeleton, as a compact representation of human action, has received increasing attention in recent years. Many skeleton-based action recognition methods adopt graph convolutional networks (GCN) to extract features on top of human…
Gait recognition, which refers to the recognition or identification of a person based on their body shape and walking styles, derived from video data captured from a distance, is widely used in crime prevention, forensic identification, and…
The emergence of RGB-D sensors offered new possibilities for addressing complex artificial vision problems efficiently. Human posture recognition is among these computer vision problems, with a wide range of applications such as ambient…
Extensive research has been conducted on assessing grasp stability, a crucial prerequisite for achieving optimal grasping strategies, including the minimum force grasping policy. However, existing works employ basic feature-level fusion…
Real-time recognition and prediction of surgical activities are fundamental to advancing safety and autonomy in robot-assisted surgery. This paper presents a multimodal transformer architecture for real-time recognition and prediction of…
Gait, the walking pattern of individuals, is one of the important biometrics modalities. Most of the existing gait recognition methods take silhouettes or articulated body models as gait features. These methods suffer from degraded…
Most two-stream action recognition networks apply the same convolutional backbone to both RGB and optical flow streams, ignoring the fact that the two modalities have fundamentally different structural properties. Optical flow captures…
WiFi-based human pose estimation has emerged as a promising non-visual alternative approaches due to its pene-trability and privacy advantages. This paper presents VST-Pose, a novel deep learning framework for accurate and continuous pose…
The gait, as a kind of soft biometric characteristic, can reflect the distinct walking patterns of individuals at a distance, exhibiting a promising technique for unrestrained human identification. With largely excluding gait-unrelated cues…
Recent graph convolutional neural networks (GCNs) have shown high performance in the field of human action recognition by using human skeleton poses. However, it fails to detect human-object interaction cases successfully due to the lack of…
We present a new deep learning approach for real-time 3D human action recognition from skeletal data and apply it to develop a vision-based intelligent surveillance system. Given a skeleton sequence, we propose to encode skeleton poses and…
We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates successfully in generic scenes which may contain occlusions by objects and by other people. Our method operates in…
In recent years, 3D Gaussian Splatting (3D-GS)-based scene representation demonstrates significant potential in real-time rendering and training efficiency. However, most existing methods primarily focus on single-map reconstruction, while…
RGB-Thermal (RGB-T) crowd counting is a challenging task, which uses thermal images as complementary information to RGB images to deal with the decreased performance of unimodal RGB-based methods in scenes with low-illumination or similar…
Video based fall detection accuracy has been largely improved due to the recent progress on deep convolutional neural networks. However, there still exists some challenges, such as lighting variation, complex background, which degrade the…
Existing 3D skeleton-based action recognition approaches reach impressive performance by encoding handcrafted action features to image format and decoding by CNNs. However, such methods are limited in two ways: a) the handcrafted action…