Related papers: Geometry Attention Transformer with Position-aware…

Graph Neural Networks (GNNs) are deep learning methods which provide the current state of the art performance in node classification tasks. GNNs often assume homophily -- neighboring nodes having similar features and labels--, and therefore…

Self-attention networks have shown remarkable progress in computer vision tasks such as image classification. The main benefit of the self-attention mechanism is the ability to capture long-range feature interactions in attention-maps.…

The rapid growth of Internet services and mobile devices provides an excellent opportunity to satisfy the strong demand for the personalized item or product recommendation. However, with the tremendous increase of users and items,…

Graph Transformer (GT), as a special type of Graph Neural Networks (GNNs), utilizes multi-head attention to facilitate high-order message passing. However, this also imposes several limitations in node classification applications: 1) nodes…

Image generation has been successfully cast as an autoregressive sequence generation or transformation problem. Recent work has shown that self-attention is an effective way of modeling textual sequences. In this work, we generalize a…

Image captioning is the generation of natural language descriptions of images which have increased immense popularity in the recent past. With this different deep-learning techniques are devised for the development of factual and stylized…

Since the superiority of Transformer in learning long-term dependency, the sign language Transformer model achieves remarkable progress in Sign Language Recognition (SLR) and Translation (SLT). However, there are several issues with the…

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

Transformer models have achieved promising performances in point cloud segmentation. However, most existing attention schemes provide the same feature learning paradigm for all points equally and overlook the enormous difference in size…

Self-attention mechanisms have made striking state-of-the-art (SOTA) progress in various sequence learning tasks, standing on the multi-headed dot product attention by attending to all the global contexts at different locations. Through a…

Image captioning is the task of automatically generating sentences that describe an input image in the best way possible. The most successful techniques for automatically generating image captions have recently used attentive deep learning…

Image captioning has been recently gaining a lot of attention thanks to the impressive achievements shown by deep captioning architectures, which combine Convolutional Neural Networks to extract image representations, and Recurrent Neural…

Vision-Language Models (VLMs) excel at grounded reasoning but remain prone to object hallucination. Recent work treats self-generated captions as a uniformly positive resource, yet we find that naively embedding one can degrade rather than…

Single-cell spatial transcriptomics (ST) offers a unique approach to measuring gene expression profiles and spatial cell locations simultaneously. However, most existing ST methods assume that cells in closer spatial proximity exhibit more…

The Transformer architecture has recently gained considerable attention in the field of graph representation learning, as it naturally overcomes several limitations of Graph Neural Networks (GNNs) with customized attention mechanisms or…

Vision Transformers (ViTs) have been shown to enhance visual recognition through modeling long-range dependencies with multi-head self-attention (MHSA), which is typically formulated as Query-Key-Value computation. However, the attention…

Retinal image analysis is crucial for diagnosing and treating eye diseases, yet generating accurate medical reports from images remains challenging due to variability in image quality and pathology, especially with limited labeled data.…

Over the past decade, Deep Convolutional Neural Networks have been widely adopted for medical image segmentation and shown to achieve adequate performance. However, due to the inherent inductive biases present in the convolutional…

Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in graph-structured data,…

We tackle the task of synthesizing novel views of an object given a few input images and associated camera viewpoints. Our work is inspired by recent 'geometry-free' approaches where multi-view images are encoded as a (global) set-latent…