Concerns with enabling computers to interpret and understand visual inputs, such as images and videos.
This academic paper focuses on the development of a deepfake detection technique that can distinguish between real and fake images. The authors propose a novel approach that utilizes Vision-Language Models…
Continue readingThis research paper introduces a new descriptor for human action recognition called the Distribution Action Movements Descriptor (DAM). The descriptor is based on the distribution of the movements of each…
Continue readingThe study focuses on the issue of automatic sign language recognition, specifically Argentinian Sign Language (LSA), using a technique called ProbSom. The complexity of this issue lies in its multidisciplinary…
Continue readingThe article introduces LSA64, a dataset of 64 signs from the Argentinian Sign Language (LSA) aimed at facilitating automatic sign language recognition. The dataset contains 3200 videos of 64 different…
Continue readingThe article discusses the vulnerability of deep neural networks, specifically in semantic segmentation tasks, to adversarial attacks – perturbations of the input that lead to incorrect predictions. The authors propose…
Continue readingThis research paper focuses on Automatic Sign Language Recognition (SLR), a complex, multidisciplinary field that combines video processing, machine learning, and linguistics. The authors present a model for sign classification…
Continue readingThis article presents OTMatch, a new method for semi-supervised learning that leverages the semantic relationships among classes using an optimal transport loss function. The paper highlights that current algorithms often…
Continue readingThis paper presents a new method for 3D object localization using only 2D labels and the physical laws of motion. No 3D labels or expensive hardware is needed. The model…
Continue readingThe academic article focuses on image-text matching, a problem that has gained attention in academia and industry. The authors identify a prevalent issue in this field, the noisy correspondence (NC),…
Continue readingThe study deals with the complex activity detection (CompAD) in videos, a field that extends the analysis of actions in a video to long-term activities. The researchers propose a hybrid…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
