Related papers: FastPose: Towards Real-time Pose Estimation and Tr…

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 this paper, we propose a novel distance-based camera network topology inference method for efficient person re-identification. To this end, we first calibrate each camera and estimate relative scales between cameras. Using the…

Person re-identification (re-ID) aims to accurately re- trieve a person from a large-scale database of images cap- tured across multiple cameras. Existing works learn deep representations using a large training subset of unique per- sons.…

In this work we adapt multi-person pose estimation architecture to use it on edge devices. We follow the bottom-up approach from OpenPose, the winner of COCO 2016 Keypoints Challenge, because of its decent quality and robustness to number…

Pose-based action recognition has drawn considerable attention recently. Existing methods exploit the joint positions to extract the body-part features from the activation map of the convolutional networks to assist human action…

Person Re-Identification (Re-ID) has gained popularity in computer vision, enabling cross-camera pedestrian recognition. Although the development of deep learning has provided a robust technical foundation for person Re-ID research, most…

The rapid development of autonomous driving, abnormal behavior detection, and behavior recognition makes an increasing demand for multi-person pose estimation-based applications, especially on mobile platforms. However, to achieve high…

Precise motion timing (PMT) is crucial for swift motion analysis. A millisecond difference may determine victory or defeat in sports competitions. Despite substantial progress in human pose estimation (HPE), PMT remains largely overlooked…

In addition to considering the recognition difficulty caused by human posture and occlusion, it is also necessary to solve the modal differences caused by different imaging systems in the Visible-Thermal cross-modal person re-identification…

We present a deep learning-based multi-task approach for head pose estimation in images. We contribute with a network architecture and training strategy that harness the strong dependencies among face pose, alignment and visibility, to…

In this paper, we focus on category-level 6D pose and size estimation from monocular RGB-D image. Previous methods suffer from inefficient category-level pose feature extraction which leads to low accuracy and inference speed. To tackle…

Frequent interactions between individuals are a fundamental challenge for pose estimation algorithms. Current pipelines either use an object detector together with a pose estimator (top-down approach), or localize all body parts first and…

Human pose estimation (i.e., locating the body parts / joints of a person) is a fundamental problem in human-computer interaction and multimedia applications. Significant progress has been made based on the development of depth sensors,…

Visual tempo characterizes the dynamics and the temporal scale of an action. Modeling such visual tempos of different actions facilitates their recognition. Previous works often capture the visual tempo through sampling raw videos at…

The task of 2D human pose estimation is challenging as the number of keypoints is typically large (~ 17) and this necessitates the use of robust neural network architectures and training pipelines that can capture the relevant features from…

This paper proposes a fast and online method for jointly performing 3D multi-object tracking and pose estimation using multiple monocular cameras. Our algorithm requires only 2D bounding box and pose detections, eliminating the need for…

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…

We present MovePose, an optimized lightweight convolutional neural network designed specifically for real-time body pose estimation on CPU-based mobile devices. The current solutions do not provide satisfactory accuracy and speed for human…

Person re-identification (re-id) is the task of recognizing and matching persons at different locations recorded by cameras with non-overlapping views. One of the main challenges of re-id is the large variance in person poses and camera…

Recently, there has been a growing interest in predicting human motion, which involves forecasting future body poses based on observed pose sequences. This task is complex due to modeling spatial and temporal relationships. The most…