相关论文: STEAM: Squeeze and Transform Enhanced Attention Mo…

In deep CNN based models for semantic segmentation, high accuracy relies on rich spatial context (large receptive fields) and fine spatial details (high resolution), both of which incur high computational costs. In this paper, we propose a…

Channel State Information (CSI) Feedback plays a crucial role in achieving higher gains through beamforming. However, for a massive MIMO system, this feedback overhead is huge and grows linearly with the number of antennas. To reduce the…

Contextual information has been shown to be powerful for semantic segmentation. This work proposes a novel Context-based Tandem Network (CTNet) by interactively exploring the spatial contextual information and the channel contextual…

Skip connection engineering is primarily employed to address the semantic gap between the encoder and decoder, while also integrating global dependencies to understand the relationships among complex anatomical structures in medical image…

Speech enhancement is a demanding task in automated speech processing pipelines, focusing on separating clean speech from noisy channels. Transformer based models have recently bested RNN and CNN models in speech enhancement, however at the…

Simulating physics using Graph Neural Networks (GNNs) is predominantly driven by message-passing architectures, which face challenges in scaling and efficiency, particularly in handling large, complex meshes. These architectures have…

In this paper, a self-supervised model that simultaneously predicts a sequence of future frames from video-input with a novel spatial-temporal attention (ST) network is proposed. The ST transformer network allows constraining both temporal…

Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set,…

The rapid development of spatial transcriptomics (ST) offers new opportunities to explore the gene expression patterns within the spatial microenvironment. Current research integrates pathological images to infer gene expression, addressing…

Session-based recommendation systems suggest relevant items to users by modeling user behavior and preferences using short-term anonymous sessions. Existing methods leverage Graph Neural Networks (GNNs) that propagate and aggregate…

Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatiotemporal features and another flow stream to learn motion…

Recently, window-based attention methods have shown great potential for computer vision tasks, particularly in Single Image Super-Resolution (SISR). However, it may fall short in capturing long-range dependencies and relationships between…

Event cameras unlock new frontiers that were previously unthinkable with standard frame-based cameras. One notable example is low-latency motion estimation (optical flow), which is critical for many real-time applications. In such…

While self-attention has been instrumental in the success of Transformers, it can lead to over-concentration on a few tokens during training, resulting in suboptimal information flow. Enforcing doubly-stochastic constraints in attention…

Semantic segmentation is a fundamental task in multimedia processing, which can be used for analyzing, understanding, editing contents of images and videos, among others. To accelerate the analysis of multimedia data, existing segmentation…

High level understanding of sequential visual input is important for safe and stable autonomy, especially in localization and object detection. While traditional object classification and tracking approaches are specifically designed to…

In this paper, we study the effect of introducing channel and spatial attention mechanisms, namely SEN-Net, ECA-Net, and CBAM, to existing CNN vision-based models such as VGGNet, ResNet, and ResNetV2 to perform the Facial Emotion…

Multi-modality image fusion enhances scene perception by combining complementary information. Unified models aim to share parameters across modalities for multi-modality image fusion, but large modality differences often cause gradient…

In this work, we propose a generally applicable transformation unit for visual recognition with deep convolutional neural networks. This transformation explicitly models channel relationships with explainable control variables. These…

Accurately modelling human attention is essential for numerous computer vision applications, particularly in the domain of automotive safety. Existing methods typically collapse gaze into saliency maps or scanpaths, treating gaze dynamics…