Search Results

Video neural networks are computationally expensive. For real-time applications they require significant compute resources that are lacking on edge devices. Various methods were proposed to reduce the computational load of neural networks. Among ...

Egocentric actions typically exhibit Human-Object Interactions (HOIs), involving the transformation of objects (e.g., “cutting” an “onion”) using various tools and utensils (e.g., “knife” and “chopping board”). Recognising these actions requires networks ...

Vision-language models (VLMs) have demonstrated remarkable performance across various visual tasks, leveraging joint learning of visual and textual representations. While these models excel in zero-shot image tasks, their application to zero-shot ...

In this work, we tackle the problem of domain-generalized action recognition, i.e. we train a model on a source domain and then test the model on other unseen target domains with different data distributions. Generalizing across different domains ...

Recognition of human actions from videos is a valuable application for building management, security systems, accident prevention, accident intervention and several other applications. This study provides a framework for joint-based action ...

Pre-training video transformers generally requires a large amount of data, presenting significant challenges in terms of data collection costs and concerns related to privacy, licensing, and inherent biases. Synthesizing data is one of the ...

We address a novel cross-domain few-shot learning task (CD-FSL) with multimodal input and unlabeled target data for egocentric action recognition. This paper simultaneously tackles two critical challenges associated with egocentric action ...

While datasets on everyday actions, sports, and cooking are abundant, there’s a significant scarcity in datasets focused on industrial domain activities, especially for distinguishing between proper and improper actions. This shortage poses a ...

The current decline in bird species and protected natural areas highlights the importance of providing solutions to improve the understanding of bird biodiversity and its interaction with its environment. This study focuses on the development and ...

In sports training, accurate identification of athletes' movements is helpful to judge whether athletes' actions are standard or not, thus providing precise movement data for training and improving athletes' levels. The convolutional neural network VGG ...

Graph Convolutional Networks (GCNs) have succeeded remarkably in skeleton-based action recognition tasks. However, the existing GCN-based methods, where the interframe edges of the graph connect only the same joints and ignore the correlations ...

Now, it is still an open issue to automatically detect whether the worker’s manual operations are compliant with the standard in industrial assembly. In this paper, we first present a spatio-temporal Transformer network (STTN) to recognize each ...

This paper aims to study various approaches using deep learning methods to perform human action recognition (HAR). More specifically, a subset of HAR focused on recognising exercises and counting repetitions using deep learning. The paper ...

This paper propose a novel dance action dataset – YNU-Dance. To preserve and inherit ethnic dances, we have collected and constructed a dataset of ethnic dance actions. The dataset encompasses unique dances from 10 different ethnic groups, including ...

In the realm of online learning and distance education, the issue of inadequate supervision looms large, posing a significant obstacle. This paper delves into the challenges posed by the lack of supervision in online learning environments and ...

Classifying player actions from soccer videos is a challenging problem, which has become increasingly important in sports analytics over the years. Most state-of-the-art methods employ highly complex offline networks, which makes it difficult to ...

To interact with humans, a robot has to know actions done by each agent presents in the environment, robotic or not. Robots are not omniscient and can’t perceive every actions made but, as humans do, we can equip the robot with the ability to ...

This paper presents a novel approach to gesture-based sign language recognition, utilizing a two-step process involving keypoint detection and Long Short-Term Memory (LSTM) networks. Sign language recognition, a crucial technology for enhancing ...

The usage of large-scale vision-language pre-training models plays an important role in reducing computational consumption and improving the accuracy of the video action recognition task. However, pre-training models trained by image data may ...

This article introduces our methods and experimental results in the submission to Action Recognition and Action Anticipation tasks (Track 1) in the Trauma THOMPSON Challenge. This article introduces our methods and experimental results in the ...