Related papers: Relational Self-Attention: What's Missing in Atten…

An important development direction in the Single-Image Super-Resolution (SISR) algorithms is to improve the efficiency of the algorithms. Recently, efficient Super-Resolution (SR) research focuses on reducing model complexity and improving…

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…

Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However, many existing vision transformer (ViT) works simply inherent…

Spatio-temporal information is key to resolve occlusion and depth ambiguity in 3D pose estimation. Previous methods have focused on either temporal contexts or local-to-global architectures that embed fixed-length spatio-temporal…

Visual attention has been successfully applied in structural prediction tasks such as visual captioning and question answering. Existing visual attention models are generally spatial, i.e., the attention is modeled as spatial probabilities…

Vision Transformer (ViT) has gained increasing attention in the computer vision community in recent years. However, the core component of ViT, Self-Attention, lacks explicit spatial priors and bears a quadratic computational complexity,…

Recent advances on Vision Transformer (ViT) and its improved variants have shown that self-attention-based networks surpass traditional Convolutional Neural Networks (CNNs) in most vision tasks. However, existing ViTs focus on the standard…

Human action recognition is one of the challenging tasks in computer vision. The current action recognition methods use computationally expensive models for learning spatio-temporal dependencies of the action. Models utilizing RGB channels…

Inspired by recent trends in vision and language learning, we explore applications of attention mechanisms for visio-lingual fusion within an application to story-based video understanding. Like other video-based QA tasks, video story…

Video summarization is among challenging tasks in computer vision, which aims at identifying highlight frames or shots over a lengthy video input. In this paper, we propose an novel attention-based framework for video summarization with…

Over the past few years, a significant progress has been made in deep convolutional neural networks (CNNs)-based image recognition. This is mainly due to the strong ability of such networks in mining discriminative object pose and parts…

Temporal relational reasoning, the ability to link meaningful transformations of objects or entities over time, is a fundamental property of intelligent species. In this paper, we introduce an effective and interpretable network module, the…

Recently, substantial research effort has focused on how to apply CNNs or RNNs to better extract temporal patterns from videos, so as to improve the accuracy of video classification. In this paper, however, we show that temporal…

Convolutional Neural Networks (CNNs) are important for many machine learning tasks. They are built with different types of layers: convolutional layers that detect features, dropout layers that help to avoid over-reliance on any single…

Human pose estimation is an essential yet challenging task in computer vision. One of the reasons for this difficulty is that there are many redundant regions in the images. In this work, we proposed a convolutional network architecture…

Attention models have recently emerged as a powerful approach, demonstrating significant progress in various fields. Visualization techniques, such as class activation mapping, provide visual insights into the reasoning of convolutional…

In video transformers, the time dimension is often treated in the same way as the two spatial dimensions. However, in a scene where objects or the camera may move, a physical point imaged at one location in frame $t$ may be entirely…

Vision Transformers (ViT) have recently emerged as a powerful alternative to convolutional networks (CNNs). Although hybrid models attempt to bridge the gap between these two architectures, the self-attention layers they rely on induce a…

The goal of video-based person re-identification is to match two input videos, so that the distance of the two videos is small if two videos contain the same person. A common approach for person re-identification is to first extract image…

Self-supervised learning holds promise to revolutionize molecule property prediction - a central task to drug discovery and many more industries - by enabling data efficient learning from scarce experimental data. Despite significant…