Related papers: ACNet: Attention Based Network to Exploit Compleme…

Monocular depth estimation and semantic segmentation are two fundamental goals of scene understanding. Due to the advantages of task interaction, many works study the joint task learning algorithm. However, most existing methods fail to…

Understanding indoor scenes is crucial for urban studies. Considering the dynamic nature of indoor environments, effective semantic segmentation requires both real-time operation and high accuracy.To address this, we propose AsymFormer, a…

We propose a novel CNN architecture called ACTNET for robust instance image retrieval from large-scale datasets. Our key innovation is a learnable activation layer designed to improve the signal-to-noise ratio (SNR) of deep convolutional…

Multi-view action recognition aims to identify actions in a given multi-view scene. Traditional studies initially extracted refined features from each view, followed by implemented paired interaction and integration, but they potentially…

Synthetic Aperture Radar (SAR) images have proven to be a valuable cue for multimodal Land Cover Classification (LCC) when combined with RGB images. Most existing studies on cross-modal fusion assume that consistent feature information is…

In this paper, we tackle the problem of RGB-D semantic segmentation of indoor images. We take advantage of deconvolutional networks which can predict pixel-wise class labels, and develop a new structure for deconvolution of multiple…

For object detection, how to address the contradictory requirement between feature map resolution and receptive field on high-resolution inputs still remains an open question. In this paper, to tackle this issue, we build a novel…

Visual explanation enables human to understand the decision making of Deep Convolutional Neural Network (CNN), but it is insufficient to contribute the performance improvement. In this paper, we focus on the attention map for visual…

Data-fusion networks have shown significant promise for RGB-thermal scene parsing. However, the majority of existing studies have relied on symmetric duplex encoders for heterogeneous feature extraction and fusion, paying inadequate…

Considering the spectral properties of images, we propose a new self-attention mechanism with highly reduced computational complexity, up to a linear rate. To better preserve edges while promoting similarity within objects, we propose…

We present an effective method to progressively integrate and refine the cross-modality complementarities for RGB-D salient object detection (SOD). The proposed network mainly solves two challenging issues: 1) how to effectively integrate…

The combination of the traditional convolutional network (i.e., an auto-encoder) and the graph convolutional network has attracted much attention in clustering, in which the auto-encoder extracts the node attribute feature and the graph…

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…

We propose a real-time general purpose semantic segmentation architecture, RGPNet, which achieves significant performance gain in complex environments. RGPNet consists of a light-weight asymmetric encoder-decoder and an adaptor. The adaptor…

Scene text recognition is a challenging task due to the complex backgrounds and diverse variations of text instances. In this paper, we propose a novel Semantic GAN and Balanced Attention Network (SGBANet) to recognize the texts in scene…

Medical ultrasound image segmentation presents a formidable challenge in the realm of computer vision. Traditional approaches rely on Convolutional Neural Networks (CNNs) and Transformer-based methods to address the intricacies of medical…

Semantic segmentation profits from deep learning and has shown its possibilities in handling the graphical data from the on-site inspection. As a result, visual damage in the facade images should be detected. Attention mechanism and…

Depth completion involves recovering a dense depth map from a sparse map and an RGB image. Recent approaches focus on utilizing color images as guidance images to recover depth at invalid pixels. However, color images alone are not enough…

Image classification remains a fundamental yet challenging task in computer vision, particularly when fine-grained feature extraction and background noise suppression are required simultaneously. Conventional convolutional neural networks,…

Real-time semantic segmentation has received considerable attention due to growing demands in many practical applications, such as autonomous vehicles, robotics, etc. Existing real-time segmentation approaches often utilize feature fusion…