Related papers: Recurrent Soft Attention Model for Common Object R…

The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model…

Triggered by the success of transformers in various visual tasks, the spatial self-attention mechanism has recently attracted more and more attention in the computer vision community. However, we empirically found that a typical vision…

Attention modules for Convolutional Neural Networks (CNNs) are an effective method to enhance performance on multiple computer-vision tasks. While existing methods appropriately model channel-, spatial- and self-attention, they primarily…

This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short term memory…

Deep learning-based medical image segmentation technology aims at automatic recognizing and annotating objects on the medical image. Non-local attention and feature learning by multi-scale methods are widely used to model network, which…

Encoder-decoder models have become an effective approach for sequence learning tasks like machine translation, image captioning and speech recognition, but have yet to show competitive results for handwritten text recognition. To this end,…

In this paper, we propose an end-to-end CNN-LSTM model for generating descriptions for sequential images with a local-object attention mechanism. To generate coherent descriptions, we capture global semantic context using a multi-layer…

Recent years have witnessed the great success of convolutional neural network (CNN) based models in the field of computer vision. CNN is able to learn hierarchically abstracted features from images in an end-to-end training manner. However,…

Mainstream visual object tracking frameworks predominantly rely on template matching paradigms. Their performance heavily depends on the quality of template features, which becomes increasingly challenging to maintain in complex scenarios…

Low-shot learning indicates the ability to recognize unseen objects based on very limited labeled training samples, which simulates human visual intelligence. According to this concept, we propose a multi-level similarity model (MLSM) to…

This paper introduces a convolutional recurrent network with attention for speech command recognition. Attention models are powerful tools to improve performance on natural language, image captioning and speech tasks. The proposed model…

Skeleton-based human action recognition has recently attracted increasing attention due to the popularity of 3D skeleton data. One main challenge lies in the large view variations in captured human actions. We propose a novel view…

Many natural language processing tasks solely rely on sparse dependencies between a few tokens in a sentence. Soft attention mechanisms show promising performance in modeling local/global dependencies by soft probabilities between every two…

Transformer-based encoder-decoder models have achieved remarkable success in image-to-image transfer tasks, particularly in image restoration. However, their high computational complexity-manifested in elevated FLOPs and parameter…

We examine how the saccade mechanism from biological vision can be used to make deep neural networks more efficient for classification and object detection problems. Our proposed approach is based on the ideas of attention-driven visual…

Class-agnostic object tracking is particularly difficult in cluttered environments as target specific discriminative models cannot be learned a priori. Inspired by how the human visual cortex employs spatial attention and separate "where"…

This paper addresses the challenges of mining latent patterns and modeling contextual dependencies in complex sequence data. A sequence pattern mining algorithm is proposed by integrating Bidirectional Long Short-Term Memory (BiLSTM) with a…

We consider the problem of visually explaining similarity models, i.e., explaining why a model predicts two images to be similar in addition to producing a scalar score. While much recent work in visual model interpretability has focused on…

Attention is fundamental to both biological and artificial intelligence, yet research on animal attention and AI self attention remains largely disconnected. We propose a Recurrent Vision Transformer (Recurrent ViT) that integrates…

A key human ability is to decompose a scene into distinct objects and use their relationships to understand the environment. Object-centric learning aims to mimic this process in an unsupervised manner. Recently, the slot attention-based…