Related papers: Batch DropBlock Network for Person Re-identificati…

Despite gait recognition and person re-identification researches have made a lot of progress, the accuracy of identification is not high enough in some specific situations, for example, people carrying bags or changing coats. In order to…

Convolution and self-attention are acting as two fundamental building blocks in deep neural networks, where the former extracts local image features in a linear way while the latter non-locally encodes high-order contextual relationships.…

Existing person re-identification (re-id) methods rely mostly on either localised or global feature representation alone. This ignores their joint benefit and mutual complementary effects. In this work, we show the advantages of jointly…

Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR). As a classic regression problem, SR exhibits a different behaviour as…

Person re-identification (Re-ID) is a critical technique in the video surveillance system, which has achieved significant success in the supervised setting. However, it is difficult to directly apply the supervised model to arbitrary unseen…

Batch Normalization (BN) has become an out-of-box technique to improve deep network training. However, its effectiveness is limited for micro-batch training, i.e., each GPU typically has only 1-2 images for training, which is inevitable for…

Compared to RGB semantic segmentation, RGBD semantic segmentation can achieve better performance by taking depth information into consideration. However, it is still problematic for contemporary segmenters to effectively exploit RGBD…

To reduce annotation labor associated with object detection, an increasing number of studies focus on transferring the learned knowledge from a labeled source domain to another unlabeled target domain. However, existing methods assume that…

The recent research for person re-identification has been focused on two trends. One is learning the part-based local features to form more informative feature descriptors. The other is designing effective metric learning loss functions…

Classical person re-identification approaches assume that a person of interest has appeared across different cameras and can be queried by one of the existing images. However, in real-world surveillance scenarios, frequently no visual…

Deep convolutional neural network (DCNN) based supervised learning is a widely practiced approach for large-scale image classification. However, retraining these large networks to accommodate new, previously unseen data demands high…

In this paper, we propose PointCubeNet, a novel multi-modal 3D understanding framework that achieves part-level reasoning without requiring any part annotations. PointCubeNet comprises global and local branches. The proposed local branch,…

This work presents a novel module, namely multi-branch concat (MBC), to process the input tensor and obtain the multi-scale feature map. The proposed MBC module brings new degrees of freedom (DoF) for the design of attention networks by…

A domain adaptation method for urban scene segmentation is proposed in this work. We develop a fully convolutional tri-branch network, where two branches assign pseudo labels to images in the unlabeled target domain while the third branch…

3D point cloud semantic and instance segmentation is crucial and fundamental for 3D scene understanding. Due to the complex structure, point sets are distributed off balance and diversely, which appears as both category imbalance and…

Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs) continually demonstrate stronger multi-scale representation ability, leading to…

We propose a novel architecture for object classification, called Self-Attention Capsule Networks (SACN). SACN is the first model that incorporates the Self-Attention mechanism as an integral layer within the Capsule Network (CapsNet).…

In this work, we address the problem of unsupervised domain adaptation for person re-ID where annotations are available for the source domain but not for target. Previous methods typically follow a two-stage optimization pipeline, where the…

Most recent gains in visual recognition have originated from the inclusion of attention mechanisms in deep convolutional networks (DCNs). Because these networks are optimized for object recognition, they learn where to attend using only a…

3D point cloud segmentation has a wide range of applications in areas such as autonomous driving, augmented reality, virtual reality and digital twins. The point cloud data collected in real scenes often contain small objects and categories…