paper-with-me

Papers

SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting

2019-08-10 · Junyu. Gao, Qi. Wang, Yuan Yuan

Recently, crowd counting is a hot topic in crowd analysis. Many CNN-based counting algorithms attain good performance. However, these methods only focus on the local appearance features of crowd scenes but ignore the large-range pixel-wise contextual and crowd attention information. To remedy the above problems, in this paper, we introduce the Spatial-/Channel-wise Attention Models into the traditional Regression CNN to estimate the density map, which is named as "SCAR". It consists of two modules, namely Spatial-wise Attention Model (SAM) and Channel-wise Attention Model (CAM). The former can encode the pixel-wise context of the entire image to more accurately predict density maps at the pixel level. The latter attempts to extract more discriminative features among different channels, which aids model to pay attention to the head region, the core of crowd scenes. Intuitively, CAM alleviates the mistaken estimation for background regions. Finally, two types of attention information and traditional CNN's feature maps are integrated by a concatenation operation. Furthermore, the extensive experiments are conducted on four popular datasets, Shanghai Tech Part A/B, GCC, and UCF_CC_50 Dataset. The results show that the proposed method achieves state-of-the-art results.

📄 PDF Abstract BibTeX arXiv:1908.03716

Code (0)

등록된 구현이 없습니다.

Tasks

Crowd Countingregression

Methods 이 논문이 사용한 방법론

CAM Class activation maps could be used to interpret the prediction decision made by the convolutional neural network (CNN). Image source: [Learning Deep Features for…

Similar Papers 제목 키워드 기반

Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information

2019-05-09 · CVPR 2019 6 · Kai Su, Dongdong Yu, Zhenqi Xu, Xin Geng 외

Multi-person pose estimation is an important but challenging problem in computer vision. Although current approaches have achieved significant progress by fusing the multi-scale feature maps, they pay little attention to…

Multi-Person Pose EstimationPose Estimation

Polarized Self-Attention: Towards High-quality Pixel-wise Regression

2021-07-02 · arXiv preprint 2021 7 · Huajun Liu, Fuqiang Liu, Xinyi Fan, Dong Huang

Pixel-wise regression is probably the most common problem in fine-grained computer vision tasks, such as estimating keypoint heatmaps and segmentation masks. These regression problems are very challenging particularly be…

2D Pose EstimationKeypoint DetectionPose Estimationregression+3

PDANet: Polarity-consistent Deep Attention Network for Fine-grained Visual Emotion Regression

2019-09-11 · Sicheng Zhao, Zizhou Jia, Hui Chen, Leida Li 외

Existing methods on visual emotion analysis mainly focus on coarse-grained emotion classification, i.e. assigning an image with a dominant discrete emotion category. However, these methods cannot well reflect the complex…

Deep AttentionEmotion ClassificationEmotion Recognitionregression

Locality-aware Channel-wise Dropout for Occluded Face Recognition

2021-07-20 · Mingjie He, Jie Zhang, Shiguang Shan, Xiao Liu 외

Face recognition remains a challenging task in unconstrained scenarios, especially when faces are partially occluded. To improve the robustness against occlusion, augmenting the training images with artificial occlusions…

Face Recognition

SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning

2016-11-17 · CVPR 2017 7 · Long Chen, Hanwang Zhang, Jun Xiao, Liqiang Nie 외

Visual attention has been successfully applied in structural prediction tasks such as visual captioning and question answering. Existing visual attention models are generally spatial, i.e., the attention is modeled as sp…

Image CaptioningSentence