Crowd management is of paramount importance when it comes to preventing stampedes and saving lives, especially in a countries like China and India where the combined population is a third of the global population. Millions of people convene annually all around the nation to celebrate a myriad of events and crowd count estimation is the linchpin of the crowd management system that could prevent stampedes and save lives. We present a network for crowd counting which reports state of the art results on crowd counting benchmarks. Our contributions are, first, a U-Net inspired model which affords us to report state of the art results. Second, we propose an independent decoding Reinforcement branch which helps the network converge much earlier and also enables the network to estimate density maps with high Structural Similarity Index (SSIM). Third, we discuss the drawbacks of the contemporary architectures and empirically show that even though our architecture achieves state of the art results, the merit may be due to the encoder-decoder pipeline instead. Finally, we report the error analysis which shows that the contemporary line of work is at saturation and leaves certain prominent problems unsolved.
Reinforced Axial Refinement Network for Monocular 3D Object Detection
Tsinghua University(清华大学);State Key Lab of Intelligent Technologies and Systems(智能技术与系统国家重点实验室);Beijing National Research Center for Information Science and Technology(北京信息科学与技术国家研究中心);Huawei Inc.(华为公司)
An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning
University of New South Wales(新南威尔士大学);University of Technology Sydney(悉尼科技大学);University of California San Diego(加州大学圣迭戈分校);RMIT University(皇家墨尔本理工大学)
Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization
School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院);School of Cyber Science and Technology, Sun Yat-sen University(中山大学网络空间科学与技术学院);Peng Cheng Laboratory(鹏城实验室);Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University(深圳广东省智能信息处理重点实验室)
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所模式识别国家重点实验室);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Horizon Robotics(地平线机器人);Huazhong University of Science and Technology(华中科技大学)
Intra-Variable Handwriting Inspection Reinforced with Idiosyncrasy Analysis
JIS Institute of Advanced Studies and Research, JIS University(JIS大学JIS高等研究学院);University of Technology Sydney(悉尼科技大学);Techno India University(Techno印度大学);Indian Statistical Institute(印度统计研究所)
Learning Reinforced Attentional Representation for End-to-End Visual Tracking
Harbin Institute of Technology(哈尔滨工业大学);Ho Chi Minh City University of Technology (HUTECH)(胡志明市理工大学(HUTECH));Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI)(安达卢西亚数据科学与计算智能研究所(DaSCI));University of Granada(格拉纳达大学);Iwate Prefectural University(岩手县立大学)
Self-Reinforced Deep Priors for Reparameterized Full Waveform Inversion
University of Science and Technology of China(中国科学技术大学);Shanghai Jiao Tong University(上海交通大学);Geological Exploration Technology Institute of Anhui Province(安徽省地质勘查技术院)
Reinforced Wasserstein Training for Severity-Aware Semantic Segmentation in Autonomous Driving
Harvard University(哈佛大学);Columbia University(哥伦比亚大学);China University of Mining and Technology(中国矿业大学);University of California Berkeley(加州大学伯克利分校);Carnegie Mellon University(卡内基梅隆大学);The Hong Kong Polytechnic University(香港理工大学)