Related papers: Gaze Estimation using Transformer
Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image…
Pain is a serious and costly issue globally, but to be treated, it must first be detected. Vision transformers are a top-performing architecture in computer vision, with little research on their use for pain detection. In this paper, we…
This paper introduces neck-mounted view gaze estimation, a new task that estimates user gaze from the neck-mounted camera perspective. Prior work on egocentric gaze estimation, which predicts device wearer's gaze location within the…
Transformers have become a default architecture in computer vision, but understanding what drives their predictions remains a challenging problem. Current explanation approaches rely on attention values or input gradients, but these provide…
Hybrid images is a technique to generate images with two interpretations that change as a function of viewing distance. It has been utilized to study multiscale processing of images by the human visual system. Using 63,000 hybrid images…
Predicting human gaze is important in Human-Computer Interaction (HCI). However, to practically serve HCI applications, gaze prediction models must be scalable, fast, and accurate in their spatial and temporal gaze predictions. Recent…
Visual segmentation seeks to partition images, video frames, or point clouds into multiple segments or groups. This technique has numerous real-world applications, such as autonomous driving, image editing, robot sensing, and medical…
This study explores human action recognition using a three-class subset of the COCO image corpus, benchmarking models from simple fully connected networks to transformer architectures. The binary Vision Transformer (ViT) achieved 90% mean…
Transformer has been applied in the field of computer vision due to its excellent performance in natural language processing, surpassing traditional convolutional neural networks and achieving new state-of-the-art. ViT divides an image into…
Vision Transformers (ViT) have marked a paradigm shift in computer vision, outperforming state-of-the-art models across diverse tasks. However, their practical deployment is hampered by high computational and memory demands. This study…
We explore the application of Vision Transformer (ViT) for handwritten text recognition. The limited availability of labeled data in this domain poses challenges for achieving high performance solely relying on ViT. Previous…
This study evaluates the trade-offs between convolutional and transformer-based architectures on both medical and general-purpose image classification benchmarks. We use ResNet-18 as our baseline and introduce a fine-tuning strategy applied…
Transformers have revolutionized deep learning based computer vision with improved performance as well as robustness to natural corruptions and adversarial attacks. Transformers are used predominantly for 2D vision tasks, including image…
Scene text recognition (STR) involves the task of reading text in cropped images of natural scenes. Conventional models in STR employ convolutional neural network (CNN) followed by recurrent neural network in an encoder-decoder framework.…
Monocular 3D human pose estimation technologies have the potential to greatly increase the availability of human movement data. The best-performing models for single-image 2D-3D lifting use graph convolutional networks (GCNs) that typically…
Change detection in remote sensing images is essential for tracking environmental changes on the Earth's surface. Despite the success of vision transformers (ViTs) as backbones in numerous computer vision applications, they remain…
Self-supervised learning (SSL) has become prevalent for learning representations in computer vision. Notably, SSL exploits contrastive learning to encourage visual representations to be invariant under various image transformations. The…
Human Action Recognition (HAR) encompasses the task of monitoring human activities across various domains, including but not limited to medical, educational, entertainment, visual surveillance, video retrieval, and the identification of…
In video action recognition, transformers consistently reach state-of-the-art accuracy. However, many models are too heavyweight for the average researcher with limited hardware resources. In this work, we explore the limitations of video…
Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions. Despite having…