Related papers: A Self-Supervised Gait Encoding Approach with Loca…
Gait recognition is a promising video-based biometric for identifying individual walking patterns from a long distance. At present, most gait recognition methods use silhouette images to represent a person in each frame. However, silhouette…
Robust gait recognition requires highly discriminative representations, which are closely tied to input modalities. While binary silhouettes and skeletons have dominated recent literature, these 2D representations fall short of capturing…
In real-world video surveillance applications, person re-identification (ReID) suffers from the effects of occlusions and detection errors. Despite recent advances, occlusions continue to corrupt the features extracted by state-of-art CNN…
Skeleton-based action recognition is a central task in computer vision and human-robot interaction. However, most previous methods suffer from overlooking the explicit exploitation of the latent data distributions (i.e., the intra-class…
Structured representations such as keypoints are widely used in pose transfer, conditional image generation, animation, and 3D reconstruction. However, their supervised learning requires expensive annotation for each target domain. We…
In video surveillance, person re-identification is the task of searching person images in non-overlapping cameras. Though supervised methods for person re-identification have attained impressive performance, obtaining large scale cross-view…
This paper proposes a novel paradigm for the unsupervised learning of object landmark detectors. Contrary to existing methods that build on auxiliary tasks such as image generation or equivariance, we propose a self-training approach where,…
Unsupervised person re-identification (Re-ID) aims to retrieve person images across cameras without any identity labels. Most clustering-based methods roughly divide image features into clusters and neglect the feature distribution noise…
Most existing gait recognition methods are appearance-based, which rely on the silhouettes extracted from the video data of human walking activities. The less-investigated skeleton-based gait recognition methods directly learn the gait…
This work focuses on unsupervised representation learning in person re-identification (ReID). Recent self-supervised contrastive learning methods learn invariance by maximizing the representation similarity between two augmented views of a…
Most recent view-invariant action recognition and performance assessment approaches rely on a large amount of annotated 3D skeleton data to extract view-invariant features. However, acquiring 3D skeleton data can be cumbersome, if not…
Gait recognition is a significant biometric technique for person identification, particularly in scenarios where other physiological biometrics are impractical or ineffective. In this paper, we address the challenges associated with gait…
Gait-based person identification from videos captured at surveillance sites using Computer Vision-based techniques is quite challenging since these walking sequences are usually corrupted with occlusion, and a complete cycle of gait is not…
Person Re-identification (re-id) aims to match people across non-overlapping camera views in a public space. It is a challenging problem because many people captured in surveillance videos wear similar clothes. Consequently, the differences…
Gait analysis provides an objective characterization of locomotor function and is widely used to support diagnosis and rehabilitation monitoring across neurological and orthopedic disorders. Deep learning has been increasingly applied to…
Gait, an unobtrusive biometric, is valued for its capability to identify individuals at a distance, across external outfits and environmental conditions. This study challenges the prevailing assumption that vision-based gait recognition, in…
The goal of gait recognition is to extract identity-invariant features of an individual under various gait conditions, e.g., cross-view and cross-clothing. Most gait models strive to implicitly learn the common traits across different gait…
Gait recognition (GR) is a growing biometric modality used for person identification from a distance through visual cameras. GR provides a secure and reliable alternative to fingerprint and face recognition, as it is harder to distinguish…
Person re-identification via 3D skeletons is an important emerging research area that attracts increasing attention within the pattern recognition community. With distinctive advantages across various application scenarios, numerous 3D…
In this paper, we address self-supervised representation learning from human skeletons for action recognition. Previous methods, which usually learn feature presentations from a single reconstruction task, may come across the overfitting…