Related papers: Informative Sample Selection Model for Skeleton-ba…

The performance of learning-based algorithms improves with the amount of labelled data used for training. Yet, manually annotating data is particularly difficult for medical image segmentation tasks because of the limited expert…

Due to the fast processing-speed and robustness it can achieve, skeleton-based action recognition has recently received the attention of the computer vision community. The recent Convolutional Neural Network (CNN)-based methods have shown…

Recent technological advancements have significantly expanded the potential of human action recognition through harnessing the power of 3D data. This data provides a richer understanding of actions, including depth information that enables…

Skeleton sequence representation learning has shown great advantages for action recognition due to its promising ability to model human joints and topology. However, the current methods usually require sufficient labeled data for training…

Medical vision foundation models remain limited in downstream tasks, particularly volumetric medical image segmentation. While fine-tuning on labeled target-domain data improves performance, existing approaches typically rely on randomly…

Person re-identification (Re-ID) via gait features within 3D skeleton sequences is a newly-emerging topic with several advantages. Existing solutions either rely on hand-crafted descriptors or supervised gait representation learning. This…

Image segmentation methods are usually trained with pixel-level annotations, which require significant human effort to collect. The most common solution to address this constraint is to implement weakly-supervised pipelines trained with…

Recently, mid-level features have shown promising performance in computer vision. Mid-level features learned by incorporating class-level information are potentially more discriminative than traditional low-level local features. In this…

Skeleton-based action recognition has recently made significant progress. However, data imbalance is still a great challenge in real-world scenarios. The performance of current action recognition algorithms declines sharply when training…

To integrate action recognition into autonomous robotic systems, it is essential to address challenges such as person occlusions-a common yet often overlooked scenario in existing self-supervised skeleton-based action recognition methods.…

We present SkeleTR, a new framework for skeleton-based action recognition. In contrast to prior work, which focuses mainly on controlled environments, we target more general scenarios that typically involve a variable number of people and…

Skeleton-based action recognition has made significant advancements recently, with models like InfoGCN showcasing remarkable accuracy. However, these models exhibit a key limitation: they necessitate complete action observation prior to…

Skeleton-based action recognition has recently received considerable attention. Current approaches to skeleton-based action recognition are typically formulated as one-hot classification tasks and do not fully exploit the semantic relations…

The increasingly wide usage of location aware sensors has made it possible to collect large volume of trajectory data in diverse application domains. Machine learning allows to study the activities or behaviours of moving objects (e.g.,…

This paper simultaneously addresses three limitations associated with conventional skeleton-based action recognition; skeleton detection and tracking errors, poor variety of the targeted actions, as well as person-wise and frame-wise action…

Semantic segmentation enables robots to perceive and reason about their environments beyond geometry. Most of such systems build upon deep learning approaches. As autonomous robots are commonly deployed in initially unknown environments,…

Human motion capture data has been widely used in data-driven character animation. In order to generate realistic, natural-looking motions, most data-driven approaches require considerable efforts of pre-processing, including motion…

Zero-shot skeleton-based action recognition aims to recognize unseen actions by transferring knowledge from seen categories through semantic descriptions. Most existing methods typically align skeleton features with textual embeddings…

Active learning (AL) aims to optimize model training and reduce annotation costs by selecting the most informative samples for labeling. Typically, AL methods rely on the empirical distribution of labeled data to define the decision…

Skeleton-based action recognition receives increasing attention because the skeleton representations reduce the amount of training data by eliminating visual information irrelevant to actions. To further improve the sample efficiency,…