Related papers: GiT: Graph Interactive Transformer for Vehicle Re-…
Transformer-based approaches have achieved superior performance in image restoration, since they can model long-term dependencies well. However, the limitation in capturing local information restricts their capacity to remove degradations.…
In recent years, Transformer-based architectures have become the dominant method for Computer Vision applications. While Transformers are explainable and scale well with dataset size, they lack the inductive biases of Convolutional Neural…
We present a new approach for learning unsupervised node representations in community graphs. We significantly extend the Interferometric Graph Transform (IGT) to community labeling: this non-linear operator iteratively extracts features…
Collaborative recommendation fundamentally involves learning high-quality user and item representations from interaction data. Recently, graph convolution networks (GCNs) have advanced the field by utilizing high-order connectivity patterns…
Graph Transformers (GTs) have demonstrated their advantages across a wide range of tasks. However, the self-attention mechanism in GTs overlooks the graph's inductive biases, particularly biases related to structure, which are crucial for…
Vision transformers (ViTs) encoding an image as a sequence of patches bring new paradigms for semantic segmentation.We present an efficient framework of representation separation in local-patch level and global-region level for semantic…
Recently, AutoRegressive (AR) models for the whole image generation empowered by transformers have achieved comparable or even better performance to Generative Adversarial Networks (GANs). Unfortunately, directly applying such AR models to…
Existing Graph Neural Networks (GNNs) are limited to process graphs each of whose vertices is represented by a vector or a single value, limited their representing capability to describe complex objects. In this paper, we propose the first…
Multi-grained features extracted from convolutional neural networks (CNNs) have demonstrated their strong discrimination ability in supervised person re-identification (Re-ID) tasks. Inspired by them, this work investigates the way of…
In this paper, we propose a graph correspondence transfer (GCT) approach for person re-identification. Unlike existing methods, the GCT model formulates person re-identification as an off-line graph matching and on-line correspondence…
Dynamic graph learning plays a pivotal role in modeling evolving relationships over time, especially for temporal link prediction tasks in domains such as traffic systems, social networks, and recommendation platforms. While…
We present the Group Propagation Vision Transformer (GPViT): a novel nonhierarchical (i.e. non-pyramidal) transformer model designed for general visual recognition with high-resolution features. High-resolution features (or tokens) are a…
Learning representation on graph plays a crucial role in numerous tasks of pattern recognition. Different from grid-shaped images/videos, on which local convolution kernels can be lattices, however, graphs are fully coordinate-free on…
Vision Transformers (ViT) have made many breakthroughs in computer vision tasks. However, considerable redundancy arises in the spatial dimension of an input image, leading to massive computational costs. Therefore, We propose a…
Nature is infinitely resolution-free. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To overcome this…
Traffic sign detection is a vital task in the visual system of self-driving cars and the automated driving system. Recently, novel Transformer-based models have achieved encouraging results for various computer vision tasks. We still…
Vision Transformer(ViT) is one of the most widely used models in the computer vision field with its great performance on various tasks. In order to fully utilize the ViT-based architecture in various applications, proper visualization…
We propose a method for image categorization and retrieval that leverages graphs and a graph attention network (GAT)-based autoencoder. Our approach is representative-centric, that is, we execute the categorization and retrieval process via…
Transformer-based architectures have become the shared backbone of natural language processing and computer vision. However, understanding how these models operate remains challenging, particularly in vision settings, where images are…
Message Passing Neural Networks have recently become the most popular approach to graph machine learning tasks; however, their receptive field is limited by the number of message passing layers. To increase the receptive field, Graph…