Related papers: ConViViT -- A Deep Neural Network Combining Convol…
Human action or activity recognition in videos is a fundamental task in computer vision with applications in surveillance and monitoring, self-driving cars, sports analytics, human-robot interaction and many more. Traditional supervised…
Understanding the relationship between different parts of an image is crucial in a variety of applications, including object recognition, scene understanding, and image classification. Despite the fact that Convolutional Neural Networks…
There has been huge progress on video action recognition in recent years. However, many works focus on tweaking existing 2D backbones due to the reliance of ImageNet pretraining, which restrains the models from achieving higher efficiency…
The synergy of long-range dependencies from transformers and local representations of image content from convolutional neural networks (CNNs) has led to advanced architectures and increased performance for various medical image analysis…
Vision Transformer (ViT) has demonstrated significant potential in various vision tasks due to its strong ability in modelling long-range dependencies. However, such success is largely fueled by training on massive samples. In real…
Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving state-of-the-art results on recognition, detection, segmentation and retrieval. In this work we propose and evaluate several deep…
To efficiently extract spatiotemporal features of video for action recognition, most state-of-the-art methods integrate 1D temporal convolution into a conventional 2D CNN backbone. However, they all exploit 1D temporal convolution of fixed…
Convolutional neural networks (CNNs) and vision transformers (ViTs) have become essential in computer vision for local and global feature extraction. However, aggregating these architectures in existing methods often results in…
Since their emergence, Convolutional Neural Networks (CNNs) have made significant strides in medical image analysis. However, the local nature of the convolution operator may pose a limitation for capturing global and long-range…
Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-of-the-art accuracy on certain benchmarks. The reason for their limited use include their need for larger training datasets and…
Convolutional architectures have proven extremely successful for vision tasks. Their hard inductive biases enable sample-efficient learning, but come at the cost of a potentially lower performance ceiling. Vision Transformers (ViTs) rely on…
Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…
The task of object segmentation in videos is usually accomplished by processing appearance and motion information separately using standard 2D convolutional networks, followed by a learned fusion of the two sources of information. On the…
Although convolutional neural networks (CNNs) showed remarkable results in many vision tasks, they are still strained by simple yet challenging visual reasoning problems. Inspired by the recent success of the Transformer network in computer…
Motivated by the success of data-driven convolutional neural networks (CNNs) in object recognition on static images, researchers are working hard towards developing CNN equivalents for learning video features. However, learning video…
The extension of convolutional neural networks (CNNs) to non-Euclidean geometries has led to multiple frameworks for studying manifolds. Many of those methods have shown design limitations resulting in poor modelling of long-range…
Despite the steady progress in video analysis led by the adoption of convolutional neural networks (CNNs), the relative improvement has been less drastic as that in 2D static image classification. Three main challenges exist including…
The hybrid architecture of convolution neural networks (CNN) and Transformer has been the most popular method for medical image segmentation. However, the existing networks based on the hybrid architecture suffer from two problems. First,…
In this work we present a new efficient approach to Human Action Recognition called Video Transformer Network (VTN). It leverages the latest advances in Computer Vision and Natural Language Processing and applies them to video…
Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transformer architectures have been proposed and they show promising…