Related papers: Interpreting Attention Models with Human Visual At…

Deep neural networks are able to solve tasks across a variety of domains and modalities of data. Despite many empirical successes, we lack the ability to clearly understand and interpret the learned internal mechanisms that contribute to…

Machine comprehension of text is an important problem in natural language processing. A recently released dataset, the Stanford Question Answering Dataset (SQuAD), offers a large number of real questions and their answers created by humans…

Transformers with linear attention allow for efficient parallel training but can simultaneously be formulated as an RNN with 2D (matrix-valued) hidden states, thus enjoying linear-time inference complexity. However, linear attention…

Attention mechanisms in deep neural networks have achieved excellent performance on sequence-prediction tasks. Here, we show that these recently-proposed attention-based mechanisms---in particular, the Transformer with its parallelizable…

Human action recognition has become an important research focus in computer vision due to the wide range of applications where it is used. 3D Resnet-based CNN models, particularly MC3, R3D, and R(2+1)D, have different convolutional filters…

Deep learning has achieved outstanding performance for face recognition benchmarks, but performance reduces significantly for low resolution (LR) images. We propose an attention similarity knowledge distillation approach, which transfers…

Visual reasoning is a long-term goal of vision research. In the last decade, several works have attempted to apply deep neural networks (DNNs) to the task of learning visual relations from images, with modest results in terms of the…

Understanding connections between artificial and biological intelligent systems can reveal fundamental principles of general intelligence. While many artificial intelligence models have a neuroscience counterpart, such connections are…

While attention mechanisms have been proven to be effective in many NLP tasks, majority of them are data-driven. We propose a novel knowledge-attention encoder which incorporates prior knowledge from external lexical resources into deep…

The early outcome prediction of ongoing or completed processes confers competitive advantage to organizations. The performance of classic machine learning and, more recently, deep learning techniques such as Long Short-Term Memory (LSTM) on…

Convolutional Neural Networks (CNNs) have been the standard for image classification tasks for a long time, but more recently attention-based mechanisms have gained traction. This project aims to compare traditional CNNs with…

The computational principles underlying attention allocation in complex goal-directed tasks remain elusive. Goal-directed reading, i.e., reading a passage to answer a question in mind, is a common real-world task that strongly engages…

Attention mechanisms represent a fundamental paradigm shift in neural network architectures, enabling models to selectively focus on relevant portions of input sequences through learned weighting functions. This monograph provides a…

Visual attention modeling has recently gained momentum in developing visual hierarchies provided by Convolutional Neural Networks. Despite recent successes of feedforward processing on the abstraction of concepts form raw images, the…

Fine-grained visual recognition typically depends on modeling subtle difference from object parts. However, these parts often exhibit dramatic visual variations such as occlusions, viewpoints, and spatial transformations, making it hard to…

Computational human attention modeling in free-viewing and task-specific settings is often studied separately, with limited exploration of whether a common representation exists between them. This work investigates this question and…

Most feedforward convolutional neural networks spend roughly the same efforts for each pixel. Yet human visual recognition is an interaction between eye movements and spatial attention, which we will have several glimpses of an object in…

Attention-based graph neural networks have made great progress in feature matching learning. However, insight of how attention mechanism works for feature matching is lacked in the literature. In this paper, we rethink cross- and…

Transformers have been successfully used in various fields and are becoming the standard tools in computer vision. However, self-attention, a core component of transformers, has a quadratic complexity problem, which limits the use of…

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…