Accurate video prediction by deep neural networks, especially for dynamic regions, is a challenging task in computer vision for critical applications such as autonomous driving, remote working, and telemedicine. Due to inherent uncertainties, existing prediction models often struggle with the complexity of motion dynamics and occlusions. In this paper, we propose a novel stochastic long-term video prediction model that focuses on dynamic regions by employing a hybrid warping strategy. By integrating frames generated through forward and backward warpings, our approach effectively compensates for the weaknesses of each technique, improving the prediction accuracy and realism of moving regions in videos while also addressing uncertainty by making stochastic predictions that account for various motions. Furthermore, considering real-time predictions, we introduce a MobileNet-based lightweight architecture into our model. Our model, called SVPHW, achieves state-of-the-art performance on two benchmark datasets.
PowerBEV: A Powerful Yet Lightweight Framework for Instance Prediction in Bird's-Eye View
Mercedes-Benz AG(梅赛德斯-奔驰股份公司);University of Tübingen(图宾根大学);University of Bonn(波恩大学);Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔机器学习与人工智能研究所)
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
CUHK-SenseTime Joint Lab, The Chinese University of Hong Kong(香港中文大学-商汤科技联合实验室,香港中文大学)
FlowNet 2是用于光流估计的最先进的卷积神经网络(CNN),需要超过160 M的参数来实现准确的流量估计。在本文中,我们提出了一种替代网络,它在具有挑战性的Sintel final pass和KITTI基准测试中的性能优于FlowNet2,同时模型大小小30倍,运行速度快1.36倍。这是通过深入到当前框架中可能遗漏的架构细节来实现的:(1)我们通过轻量级级联网络在每个金字塔级别上提出了一种更有效的流推理方法。它不仅通过早期校正提高了流量估计的准确性,而且还允许在我们的网络中无缝地结合描述符匹配。(2)我们提出了一种新的流正则化层,通过使用特征驱动的局部卷积来改善异常值和模糊流边界的问题。(3)我们的网络拥有一个有效的金字塔特征提取的结构,并包括特征扭曲,而不是在FlowNet2中实践的图像扭曲。我们的代码和训练模型可以在www.example.com上找到。
FaceLiVTv2: An Improved Hybrid Architecture for Efficient Mobile Face Recognition
Department of Electro-Optics, National Formosa University(国立虎尾科技大学光电工程系);Department of Electrical Engineering, National Taipei University(国立台北大学电机工程系);College of Artificial Intelligence and Green Energy, National Yang Ming Chiao Tung University(国立阳明交通大学人工智能与绿色能源学院)
HDiffTG: A Lightweight Hybrid Diffusion-Transformer-GCN Architecture for 3D Human Pose Estimation
College of Information Science and Electronic Engineering, Zhejiang University(浙江大学信息科学与电子工程学院);Faculty of Science and Technology, University of Macau(澳门大学科学与技术学院);College of Mechatronics and Control Engineering, Shenzhen University(深圳大学机电与控制工程学院);School of AI and Advanced Computing, Xi’an Jiaotong-Liverpool University(西安交通大学利物浦大学人工智能与高级计算学院);School of Computing and Information Systems, Singapore Management University(新加坡管理学院计算机与信息系统学院)
Automated Plant Disease and Pest Detection System Using Hybrid Lightweight CNN-MobileViT Models for Diagnosis of Indigenous Crops
Department of Computer Science \& Engineering;Department of Information Technology Mekelle University - Mekelle Institute of Technology, Ethiopia Email
CamDirector: Towards Long-Term Coherent Video Trajectory Editing
McMaster University(麦克 master 大学);University of Toronto(多伦多大学);The University of Hong Kong(香港大学);McGill University(麦吉尔大学);Concordia University(Concordia 大学);MBZUAI