Related papers: Graphical Models with Attention for Context-Specif…

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Attention-based transformers have achieved tremendous success across a variety of disciplines including natural languages. To deepen our understanding of their sequential modeling capabilities, there is a growing interest in using Markov…

The paradigm of Transformers using the self-attention mechanism has manifested its advantage in learning graph-structured data. Yet, Graph Transformers are capable of modeling full range dependencies but are often deficient in extracting…

Several approaches to graphically representing context-specific relations among jointly distributed categorical variables have been proposed, along with structure learning algorithms. While existing optimization-based methods have limited…

Multi-view action recognition (MVAR) leverages complementary temporal information from different views to improve the learning performance. Obtaining informative view-specific representation plays an essential role in MVAR. Attention has…

Motivated by problems from neuroimaging in which existing approaches make use of "mass univariate" analysis which neglects spatial structure entirely, but the full joint modelling of all quantities of interest is computationally infeasible,…

Open set recognition (OSR) requires the model to classify samples that belong to closed sets while rejecting unknown samples during test. Currently, generative models often perform better than discriminative models in OSR, but recent…

Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the…

The study presents an exploratory graphical modeling approach for evaluating local item dependency within cognitively diagnostic classification models (DCMs). Current approaches to modeling local dependence require known item structure and…

Exponential random graph models, or ERGMs, are a flexible and general class of models for modeling dependent data. While the early literature has shown them to be powerful in capturing many network features of interest, recent work…

We present an attention-based modular neural framework for computer vision. The framework uses a soft attention mechanism allowing models to be trained with gradient descent. It consists of three modules: a recurrent attention module…

While linear attention architectures offer efficient inference, compressing unbounded history into a fixed-size memory inherently limits expressivity and causes information loss. To address this limitation, we introduce Random Access Memory…

Efficient operation of intelligent machines in the real world requires methods that allow them to understand and predict the uncertainties presented by the unstructured environments with good accuracy, scalability and generalization,…

In recent years, single image super-resolution (SR) methods based on deep convolutional neural networks (CNNs) have made significant progress. However, due to the non-adaptive nature of the convolution operation, they cannot adapt to…

Multivariate time series modeling and prediction problems are abundant in many machine learning application domains. Accurate interpretation of such prediction outcomes from a machine learning model that explicitly captures temporal…

Recent works have shown that exploiting multi-scale representations deeply learned via convolutional neural networks (CNN) is of tremendous importance for accurate contour detection. This paper presents a novel approach for predicting…

In recent years, powered by the learned discriminative representation via graph neural network (GNN) models, deep graph matching methods have made great progresses in the task of matching semantic features. However, these methods usually…

In controllable image synthesis, generating coherent and consistent images from multiple references with spatial layout awareness remains an open challenge. We present LAMIC, a Layout-Aware Multi-Image Composition framework that, for the…

Fine-grained image recognition is central to many multimedia tasks such as search, retrieval and captioning. Unfortunately, these tasks are still challenging since the appearance of samples of the same class can be more different than those…

Functional data play a pivotal role across science and engineering, yet their infinite-dimensional nature makes representation learning challenging. Conventional statistical models depend on pre-chosen basis expansions or kernels, limiting…