Related papers: Contextual Transformer Networks for Visual Recogni…

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to…

While Transformers have shown remarkable success in natural language processing, their attention mechanism's large memory requirements have limited their ability to handle longer contexts. Prior approaches, such as recurrent memory or…

We present a novel attention mechanism: Causal Attention (CATT), to remove the ever-elusive confounding effect in existing attention-based vision-language models. This effect causes harmful bias that misleads the attention module to focus…

Self-attention (SA) has become the cornerstone of modern vision backbones for its powerful expressivity over traditional Convolutions (Conv). However, its quadratic complexity remains a critical bottleneck for practical applications. Given…

The segmentation-free research efforts for addressing handwritten text recognition can be divided into three categories: connectionist temporal classification (CTC), hidden Markov model and encoder-decoder methods. In this paper, inspired…

Pre-trained language models like BERT and its variants have recently achieved impressive performance in various natural language understanding tasks. However, BERT heavily relies on the global self-attention block and thus suffers large…

Humans can effectively find salient regions in complex scenes. Self-attention mechanisms were introduced into Computer Vision (CV) to achieve this. Attention Augmented Convolutional Network (AANet) is a mixture of convolution and…

Pre-training Transformer from large-scale raw texts and fine-tuning on the desired task have achieved state-of-the-art results on diverse NLP tasks. However, it is unclear what the learned attention captures. The attention computed by…

Although convolutional neural networks (CNNs) showed remarkable results in many vision tasks, they are still strained by simple yet challenging visual reasoning problems. Inspired by the recent success of the Transformer network in computer…

Recently proposed fine-grained 3D visual grounding is an essential and challenging task, whose goal is to identify the 3D object referred by a natural language sentence from other distractive objects of the same category. Existing works…

Transformer has achieved impressive successes for various computer vision tasks. However, most of existing studies require to pretrain the Transformer backbone on a large-scale labeled dataset (e.g., ImageNet) for achieving satisfactory…

Few-shot object detection is a challenging but realistic scenario, where only a few annotated training images are available for training detectors. A popular approach to handle this problem is transfer learning, i.e., fine-tuning a detector…

Transformers have emerged as the cornerstone of state-of-the-art natural language processing models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands posed by the self-attention…

We explore the task of language-guided video segmentation (LVS). Previous algorithms mostly adopt 3D CNNs to learn video representation, struggling to capture long-term context and easily suffering from visual-linguistic misalignment. In…

Incomplete-view computed tomography (CT) can shorten the data acquisition time and allow scanning of large objects, including sparse-view and limited-angle scenarios, each with various settings, such as different view numbers or angular…

The self-attention mechanism, a cornerstone of Transformer-based state-of-the-art deep learning architectures, is largely heuristic-driven and fundamentally challenging to interpret. Establishing a robust theoretical foundation to explain…

Generative adversarial models with convolutional neural network (CNN) backbones have recently been established as state-of-the-art in numerous medical image synthesis tasks. However, CNNs are designed to perform local processing with…

With the popularity of Transformer architectures in computer vision, the research focus has shifted towards developing computationally efficient designs. Window-based local attention is one of the major techniques being adopted in recent…

Attention based language models have become a critical component in state-of-the-art natural language processing systems. However, these models have significant computational requirements, due to long training times, dense operations and…

3D convolution is powerful for video classification but often computationally expensive, recent studies mainly focus on decomposing it on spatial-temporal and/or channel dimensions. Unfortunately, most approaches fail to achieve a…