SC2Net: Scale-aware Crowd Counting Network with Pyramid Dilated Convolution

Article Computer Science, Artificial Intelligence

SGCNet: Scale-aware and global contextual network for crowd counting

Qi Liu et al.

Summary: In this paper, we propose a novel scale-aware and global contextual network (SGCNet) that employs multi-scale attention mechanisms to selectively strengthen features with different network scales, achieving better counting performance.

APPLIED INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Crowd density estimation based on multi scale features fusion network with reverse attention mechanism

Yong-Chao Li et al.

Summary: This paper proposes a multi-scale feature fusion network based on the reverse attention mechanism to overcome the challenges of perspective distortion and complex background in crowd counting. Experimental results show that the algorithm achieves lower errors on multiple datasets.

APPLIED INTELLIGENCE (2022)

添加到收藏夹

Article Automation & Control Systems

Hierarchical pyramid attentive network with spatial separable convolution for crowd counting

Shihui Zhang et al.

Summary: This paper introduces a novel method based on HPANet to address the challenging issue of scale variation in crowd counting tasks, improving counting accuracy. By designing SPA blocks and an HFF module, HPANet provides a powerful scale-aware feature representation and demonstrates effective performance on public benchmark datasets.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2022)

添加到收藏夹

Article Geochemistry & Geophysics

Multiple Instance Graph Learning for Weakly Supervised Remote Sensing Object Detection

Binglu Wang et al.

Summary: This study proposes a multiple instance graph (MIG) learning framework for weakly supervised object detection (WSOD) in remote sensing images (RSIs). The framework utilizes spatial and appearance graphs to detect high-quality objects and mine possible instances with the same class.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Group-Wise Learning for Weakly Supervised Semantic Segmentation

Tianfei Zhou et al.

Summary: This work proposes a novel group-wise learning framework for weakly supervised semantic segmentation. The framework explicitly encodes semantic dependencies and discovers rich semantic context within a group of images. The proposed model achieves state-of-the-art performance in various benchmarks and demonstrates strong generalizability in weakly supervised object localization tasks.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Context-aware pyramid attention network for crowd counting

Lingyu Gu et al.

Summary: This study proposes an innovative Context-Aware Pyramid Attention Network for accurate crowd counting, which extracts rich contextual features and deals with dependencies on space and channels. Experimental results on multiple challenging datasets demonstrate significant improvement in counting accuracy with CAPAN, validating its effectiveness.

APPLIED INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Pyramid-dilated deep convolutional neural network for crowd counting

Weixing Wang et al.

Summary: This paper proposes an automatic crowd counting method based on pyramid-dilated deep convolutional neural network, achieving high-quality density map estimation and good counting performance through capturing multiscale features and using structural similarity loss.

APPLIED INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

MGSNet: A multi-scale and gated spatial attention network for crowd counting

Ying Shi et al.

Summary: This paper proposes a multi-scale and gated spatial attention network (MGSNet) for crowd counting, which aims to address the challenges of large-scale variation and complex background noise. Experimental results demonstrate its effectiveness over state-of-the-art approaches on multiple datasets.

APPLIED INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Background-Click Supervision for Temporal Action Localization

Le Yang et al.

Summary: This study proposes a novel method called BackTAL, which converts action-click supervision to background-click supervision, and trains a stronger action localizer on background video frames. BackTAL implements two-fold modeling on the background frames and dynamically attends to informative neighbors during temporal convolution. Extensive experiments demonstrate the high performance of BackTAL and the rationality of the proposed background-click supervision.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Hierarchical Human Semantic Parsing With Comprehensive Part-Relation Modeling

Wenguan Wang et al.

Summary: This study examines three types of inference processes in human parsing, proposes a compositional neural information fusion framework, and develops a part-relation-aware human parser. The results demonstrate superior performance of the new methods in human parsing tasks.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Weakly Supervised Visual Saliency Prediction

Qiuxia Lai et al.

Summary: This paper introduces a weakly supervised visual saliency model based on cognitive theories. The model incorporates components motivated from biological vision and proposes novel loss functions to utilize supervision cues. Experimental results show promising performance in reducing annotation budget and providing a more comprehensive understanding of the visual attention mechanism.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Crowd counting method based on the self-attention residual network

Yan-Bo Liu et al.

Summary: The crowd counting method proposed in this study utilizes multiscale convolution and self-attention residual modules to effectively address the issues of occlusion and scale changes in crowd estimation, ultimately improving the accuracy of crowd counting.

APPLIED INTELLIGENCE (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization

Qi Wang et al.

Summary: In the past decade, crowd counting and localization have gained much attention from researchers due to their wide range of applications. The NWPU-Crowd dataset is constructed to address the issue of small-scale datasets, containing a large number of annotated heads with points and boxes. A benchmark website is developed for impartial evaluation of different methods, providing researchers with a platform to submit test results and analyze new challenges in the field.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Multi-Resolution Fusion and Multi-scale Input Priors Based Crowd Counting

Usman Sajid et al.

Summary: The paper proposes a new end-to-end crowd counting network based on multi-resolution fusion, with three deep-layered columns/branches catering to different crowd-density scales. It introduces three input priors as an alternative to the PRM module, and strategically places three auxiliary crowd estimation regression heads in the network to enhance overall performance. Comprehensive experiments show that the proposed approach outperforms state-of-the-art models in terms of RMSE evaluation metric and generalizes well in cross-dataset experiments.

2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Embedding Perspective Analysis Into Multi-Column Convolutional Neural Network for Crowd Counting

Yifan Yang et al.

Summary: The study presents a simple yet effective multi-column network that integrates perspective analysis method with counting network, enabling efficient analysis of crowd quantities in scenes of various scales. By sharing parameters and introducing strategies like transform dilated convolution, the evaluation accuracy is improved, achieving state-of-the-art performance on multiple datasets.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

添加到收藏夹

Article Computer Science, Information Systems

Multi-scale dilated convolution of convolutional neural network for crowd counting

Yanjie Wang et al.

MULTIMEDIA TOOLS AND APPLICATIONS (2020)

添加到收藏夹

Article Engineering, Multidisciplinary

GPR B scan image analysis with deep learning methods

Umut Ozkaya et al.

MEASUREMENT (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

PCC Net: Perspective Crowd Counting via Spatial Convolutional Network

Junyu Gao et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images

Usman Sajid et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

SCLNet: Spatial context learning network for congested crowd counting

Shunzhou Wang et al.

NEUROCOMPUTING (2020)

添加到收藏夹

Article Computer Science, Information Systems

HAGN: Hierarchical Attention Guided Network for Crowd Counting

Zuodong Duan et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

MATNet: Motion-Attentive Transition Network for Zero-Shot Video Object Segmentation

Tianfei Zhou et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

HA-CCN: Hierarchical Attention-Based Crowd Counting Network

Vishwanath A. Sindagi et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Atrous convolutions spatial pyramid network for crowd counting and density estimation

Junjie Ma et al.

NEUROCOMPUTING (2019)

添加到收藏夹

Article Computer Science, Artificial Intelligence

SCAR: Spatial-/channel-wise attention regression networks for crowd counting

Junyu Gao et al.

NEUROCOMPUTING (2019)

添加到收藏夹

Article Computer Science, Information Systems

An Automatic Scale-Adaptive Approach With Attention Mechchanism-Based Crowd Spatial Information for Crowd Counting

Weihang Kong et al.

IEEE ACCESS (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Attentional Neural Fields for Crowd Counting

Anran Zhang et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Relational Attention Network for Crowd Counting

Anran Zhang et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks

Xiaolong Jiang et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding

Ning Liu et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Interdisciplinary Applications

DADNet: Dilated-Attention-Deformable ConvNet for Crowd Counting

Dan Guo et al.

PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19) (2019)

添加到收藏夹

Article Computer Science, Information Systems

CASA-Crowd: A Context-Aware Scale Aggregation CNN-Based Crowd Counting Technique

Naveed Ilyas et al.

IEEE ACCESS (2019)

添加到收藏夹

Proceedings Paper Computer Science, Software Engineering

CROWD COUNTING VIA MULTI-VIEW SCALE AGGREGATION NETWORKS

Zhilin Qiu et al.

2019 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME) (2019)

添加到收藏夹

Article Computer Science, Information Systems

Crowd Counting in Low-Resolution Crowded Scenes Using Region-Based Deep Convolutional Neural Networks

Muhammad Saqib et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Engineering, Electrical & Electronic

Crowd Counting via Weighted VLAD on a Dense Attribute Feature Map

Biyun Sheng et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2018)

添加到收藏夹

SC2Net: Scale-aware Crowd Counting Network with Pyramid Dilated Convolution

相关参考文献

导出引文

分享论文