Related papers: Skeleton-Based Action Recognition with Spatial Rea…
This paper propose a novel dictionary learning approach to detect event action using skeletal information extracted from RGBD video. The event action is represented as several latent atoms and composed of latent spatial and temporal…
Zero-shot human skeleton-based action recognition aims to construct a model that can recognize actions outside the categories seen during training. Previous research has focused on aligning sequences' visual and semantic spatial…
Sign language is commonly used by deaf or mute people to communicate but requires extensive effort to master. It is usually performed with the fast yet delicate movement of hand gestures, body posture, and even facial expressions. Current…
Contrastive learning has achieved great success in skeleton-based action recognition. However, most existing approaches encode the skeleton sequences as entangled spatiotemporal representations and confine the contrasts to the same level of…
This paper strives for self-supervised learning of a feature space suitable for skeleton-based action recognition. Our proposal is built upon learning invariances to input skeleton representations and various skeleton augmentations via a…
Skeleton-based human action recognition has recently attracted increasing attention thanks to the accessibility and the popularity of 3D skeleton data. One of the key challenges in skeleton-based action recognition lies in the large view…
Recognition of human actions and associated interactions with objects and the environment is an important problem in computer vision due to its potential applications in a variety of domains. The most versatile methods can generalize to…
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…
Graph convolutional networks have been widely used for skeleton-based action recognition due to their excellent modeling ability of non-Euclidean data. As the graph convolution is a local operation, it can only utilize the short-range joint…
There exist a wide range of intra class variations of the same actions and inter class similarity among the actions, at the same time, which makes the action recognition in videos very challenging. In this paper, we present a novel…
Graph convolutional networks (GCNs) have been very successful in modeling non-Euclidean data structures, like sequences of body skeletons forming actions modeled as spatio-temporal graphs. Most GCN-based action recognition methods use deep…
Traditional approaches in unsupervised or self supervised learning for skeleton-based action classification have concentrated predominantly on the dynamic aspects of skeletal sequences. Yet, the intricate interaction between the moving and…
This paper presents a new framework for human action recognition from a 3D skeleton sequence. Previous studies do not fully utilize the temporal relationships between video segments in a human action. Some studies successfully used very…
Triggered by the success of transformers in various visual tasks, the spatial self-attention mechanism has recently attracted more and more attention in the computer vision community. However, we empirically found that a typical vision…
Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatiotemporal features and another flow stream to learn motion…
Contrastive learning has gained significant attention in skeleton-based action recognition for its ability to learn robust representations from unlabeled data. However, existing methods rely on a single skeleton convention, which limits…
Deep convolutional networks have achieved great success for image recognition. However, for action recognition in videos, their advantage over traditional methods is not so evident. We present a general and flexible video-level framework…
Among the existing modalities for 3D action recognition, 3D flow has been poorly examined, although conveying rich motion information cues for human actions. Presumably, its susceptibility to noise renders it intractable, thus challenging…
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…
Graph convolutional networks (GCNs) achieved promising performance in skeleton-based human action recognition by modeling a sequence of skeletons as a spatio-temporal graph. Most of the recently proposed GCN-based methods improve the…