Related papers: Neuron: Learning Context-Aware Evolving Representa…

Skeleton-aware sign language recognition (SLR) has gained popularity due to its ability to remain unaffected by background information and its lower computational requirements. Current methods utilize spatial graph modules and temporal…

In real-world scenarios, human actions often fall outside the distribution of training data, making it crucial for models to recognize known actions and reject unknown ones. However, using pure skeleton data in such open-set conditions…

Human action recognition from skeletal data is a hot research topic and important in many open domain applications of computer vision, thanks to recently introduced 3D sensors. In the literature, naive methods simply transfer off-the-shelf…

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…

With the development of robotics, skeleton-based action recognition has become increasingly important, as human-robot interaction requires understanding the actions of humans and humanoid robots. Due to different sources of human skeletons…

Skeleton-based human activity recognition has achieved strong empirical performance, yet most existing models remain black boxes and difficult to interpret. In this work, we introduce a neurosymbolic formulation of skeleton-based HAR that…

Zero-shot skeleton-based action recognition (ZSAR) aims to recognize action classes without any training skeletons from those classes, relying instead on auxiliary semantics from text. Existing approaches frequently depend on explicit…

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…

Spatiotemporal learning is challenging due to the intricate interplay between spatial and temporal dependencies, the high dimensionality of the data, and scalability constraints. These challenges are further amplified in scientific domains,…

Human motion prediction aims to generate future motions based on the observed human motions. Witnessing the success of Recurrent Neural Networks (RNN) in modeling the sequential data, recent works utilize RNN to model human-skeleton motion…

Autonomous robotic systems require spatio-temporal understanding of dynamic environments to ensure reliable navigation and interaction. While Vision-Language Models (VLMs) provide open-world semantic priors, they lack grounding in 3D…

Skeleton-based human action recognition has attracted great interest thanks to the easy accessibility of the human skeleton data. Recently, there is a trend of using very deep feedforward neural networks to model the 3D coordinates of…

We present Neural Congealing -- a zero-shot self-supervised framework for detecting and jointly aligning semantically-common content across a given set of images. Our approach harnesses the power of pre-trained DINO-ViT features to learn:…

Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power…

Zero-shot learning aims to recognize instances of unseen classes, for which no visual instance is available during training, by learning multimodal relations between samples from seen classes and corresponding class semantic…

How humans understand and recognize the actions of others is a complex neuroscientific problem that involves a combination of cognitive mechanisms and neural networks. Research has shown that humans have brain areas that recognize actions…

Recently, skeleton based action recognition gains more popularity due to cost-effective depth sensors coupled with real-time skeleton estimation algorithms. Traditional approaches based on handcrafted features are limited to represent the…

We introduce SynSE, a novel syntactically guided generative approach for Zero-Shot Learning (ZSL). Our end-to-end approach learns progressively refined generative embedding spaces constrained within and across the involved modalities…

Skeleton data is of low dimension. However, there is a trend of using very deep and complicated feedforward neural networks to model the skeleton sequence without considering the complexity in recent year. In this paper, a simple yet…

Zero-shot instance segmentation aims to detect and precisely segment objects of unseen categories without any training samples. Since the model is trained on seen categories, there is a strong bias that the model tends to classify all the…