Related papers: Temporal-Viewpoint Transportation Plan for Skeleta…

Few-shot action recognition aims to enable models to quickly learn new action categories from limited labeled samples, addressing the challenge of data scarcity in real-world applications. Current research primarily addresses three core…

In skeleton-based human action recognition, temporal pooling is a critical step for capturing spatiotemporal relationship of joint dynamics. Conventional pooling methods overlook the preservation of motion information and treat each frame…

Human motion prediction is an increasingly interesting topic in computer vision and robotics. In this paper, we propose a new 2D CNN based network, TrajectoryNet, to predict future poses in the trajectory space. Compared with most existing…

Algorithms for video action recognition should consider not only spatial information but also temporal relations, which remains challenging. We propose a 3D-CNN-based action recognition model, called the blockwise temporal-spatial path-way…

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…

Skeleton-based human action recognition aims to classify human skeletal sequences, which are spatiotemporal representations of actions, into predefined categories. To reduce the reliance on costly annotations of skeletal sequences while…

Zero-shot skeleton action recognition is a non-trivial task that requires robust unseen generalization with prior knowledge from only seen classes and shared semantics. Existing methods typically build the skeleton-semantics interactions by…

Few-shot learning (FSL), which aims to recognise new classes by adapting the learned knowledge with extremely limited few-shot (support) examples, remains an important open problem in computer vision. Most of the existing methods for…

In this paper we propose a novel Temporal Attentive Relation Network (TARN) for the problems of few-shot and zero-shot action recognition. At the heart of our network is a meta-learning approach that learns to compare representations of…

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…

Skeleton data, which consists of only the 2D/3D coordinates of the human joints, has been widely studied for human action recognition. Existing methods take the semantics as prior knowledge to group human joints and draw correlations…

We present a simple unsupervised method for learning an encoder mapping short 3D pose sequences into embedding vectors suitable for sequence-to-sequence alignment by dynamic time warping. Training samples consist of temporal windows of…

Skeleton-based action recognition has recently attracted a lot of attention. Researchers are coming up with new approaches for extracting spatio-temporal relations and making considerable progress on large-scale skeleton-based datasets.…

Deep learning is ubiquitous across many areas areas of computer vision. It often requires large scale datasets for training before being fine-tuned on small-to-medium scale problems. Activity, or, in other words, action recognition, is one…

Spatio-temporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D).…

Few-shot action recognition, i.e. recognizing new action classes given only a few examples, benefits from incorporating temporal information. Prior work either encodes such information in the representation itself and learns classifiers at…

In this paper, we tackle the problem of action recognition using body skeletons extracted from video sequences. Our approach lies in the continuity of recent works representing video frames by Gramian matrices that describe a trajectory on…

In this paper, we study the problem of one-shot skeleton-based action recognition, which poses unique challenges in learning transferable representation from base classes to novel classes, particularly for fine-grained actions. Existing…

The dynamics of human skeletons have significant information for the task of action recognition. The similarity between trajectories of corresponding joints is an indicating feature of the same action, while this similarity may subject to…

Recent work on action recognition leverages 3D features and textual information to achieve state-of-the-art performance. However, most of the current few-shot action recognition methods still rely on 2D frame-level representations, often…