检索结果-内蒙古大学图书馆

A Hybrid Transformer-LSTM Model With 3d separable convolution for Video Prediction

IEEE ACCESS 2024年 12卷 39589-39602页

作者： Mathai, Mareeta Liu, Ying Ling, Nam Santa Clara Univ Dept Comp Sci & Engn Santa Clara CA 95053 USA

Video prediction is an essential vision task due to its wide applications in real-world scenarios. However, it is indeed challenging due to the inherent uncertainty and complex spatiotemporal dynamics of video content. Several state-of-the-art deep learning methods have achieved superior video prediction accuracy at the expense of huge computational cost. Hence, they are not suitable for devices with limitations in memory and computational resource. In the light of Green Artificial Intelligence (AI), more environment friendly deep learning solutions are desired to tackle the problem of large models and computational cost. In this work, we propose a novel video prediction network 3dTransLSTM, which adopts a hybrid transformer-long short-term memory (LSTM) structure to inherit the merits of both self-attention and recurrence. Three-dimensional (3d) depthwise separable convolutions are used in this hybrid structure to extract spatiotemporal features, meanwhile enhancing model efficiency. We conducted experimental studies on four popular video prediction datasets. Compared to existing methods, our proposed 3dTransLSTM achieved competitive frame prediction accuracy with significantly reduced model size, trainable parameters, and computational complexity. Moreover, we demonstrate the generalization ability of the proposed model by testing the model on dataset completely unseen in the training data.

关键词： Three-dimensional displays deep learning convolutional neural networks Long short term memory Spatiotemporal phenomena Visualization Visual analytics Videos Predictive models Green design Artificial intelligence Training data Computational modeling data models Computational efficiency 3d separable convolution deep learning depthwise convolution LSTM pointwise convolution self-attention spatiotemporal modeling transformer visual communications video prediction

来源：评论

学校读者我要写书评

暂无评论

dynamic Gesture Recognition Based on 3d separable convolutional LSTM Networks 11

Dynamic Gesture Recognition Based on 3D Separable Convolutio...

引用

11th IEEE International Conference on Software Engineering and Service Science (IEEE ICSESS)

作者： Zhang, Xunlei Tie, Yun Qi, Lin Zhengzhou Univ Sch Informat Engn Zhengzhou Henan Peoples R China

ISBN: (纸本)9781728165790

dynamic gesture recognition, as an important component of human-computer interaction (HCI), has attracted the attention of many researchers. However, there are still many challenges in the actual gesture recognition task, such as the non-rigid properties of the hand, the acquisition of different semantic information through spatial and motion information at different locations, and the changes of light and background in the surrounding environment can ultimately affect the extraction of gesture features. Since the essence of dynamic gesture recognition is classification and recognition, how to extract the spatio-temporal features of dynamic gestures will have a significant impact on the final recognition and classification of gestures. In recent years, three-dimensional convolutional neural networks have achieved excellent performance in motion recognition, but traditional three-dimensional convolution is redundant in the feature extraction process. In order to reduce the resource consumption, this paper adopts 3d separable convolution as an alternative solution. To further extract semantic and action information of gestures, we combine attentional mechanisms and long- and short-term memory To further extract semantic and action information of gestures, we combine attentional mechanisms and long- and short-term memory (LSTM) networks for gesture recognition in this paper. We conducted experiments on the ChaLearn Large-Scale Gesture Recognition dataset (IsoGd), and the experimental results validate the effectiveness of our method.

关键词： 3d separable convolution LSTM dynamic Gesture Recognition Attention Mechanism

来源：评论

学校读者我要写书评

暂无评论

A Fast Lightweight 3d separable convolutional Neural Network With Multi-Input Multi-Output for Moving Object detection

引用

IEEE ACCESS 2021年 9卷 148433-148448页

作者： Hou, Bingxin Liu, Ying Ling, Nam Liu, Lingzhi Ren, Yongxiong Santa Clara Univ Dept Comp Sci & Engn Santa Clara CA 95053 USA Kwai Inc Palo Alto CA 94306 USA

Advances in moving object detection have been driven by the active application of deep learning methods. However, many existing models render superior detection accuracy at the cost of high computational complexity and slow inference speed. This fact has hindered the development of such models in mobile and embedded vision tasks, which need to be carried out in a timely fashion on a computationally limited platform. In this paper, we propose a super-fast (inference speed-154 fps) and lightweight (model size-1.45 MB) end-to-end 3d separable convolutional neural network with a multi-input multi-output (MIMO) strategy named "3dS_MM" for moving object detection. To improve detection accuracy, the proposed model adopts 3d convolution which is more suitable to extract both spatial and temporal information in video data than 2d convolution. To reduce model size and computational complexity, the standard 3d convolution is decomposed into depthwise and pointwise convolutions. Besides, we proposed a MIMO strategy to increase inference speed, which can take multiple frames as the network input and output multiple frames of detection results. Further, we conducted the scene dependent evaluation (SdE) and scene independent evaluation (SIE) on the benchmark Cdnet2014 and dAVIS2016 datasets. Compared to state-of-the-art approaches, our proposed method significantly increases the inference speed, reduces the model size, meanwhile achieving the highest detection accuracy in the SdE setup and maintaining a competitive detection accuracy in the SIE setup.

关键词： Three-dimensional displays convolution Computational modeling Solid modeling Object detection MIMO communication Task analysis convolutional neural network depthwise convolution moving object detection multi-input multi-output pointwise convolution scene independent evaluation 3d separable convolution unseen videos video analytics video surveillance

来源：评论

学校读者我要写书评

暂无评论

Anomaly Behavior detection in Crowd via Lightweight 3d convolution 20th

Anomaly Behavior Detection in Crowd via Lightweight 3D Convo...

引用

20th International Conference on Intelligent Computing (ICIC)

作者： Wang, Jinfeng Xie, Xiongshen South China Agr Univ Coll Math & Informat Guangzhou 510642 Peoples R China

ISBN: (纸本)9789819756148;9789819756155

detecting abnormal behaviors in large crowds is a highly challenging problem. In practical scenarios, there are two problems. One of the problems is the imbalance in the number of training samples collected through monitoring always results in overfitting, which is mainly reflected in the lack of samples of specific abnormal behavior for training. The other problem is that edge computing devices in practical scenarios cannot load models with many parameters, while most deep learning methods need excessive parameters to obtain good performance. In this article, a lightweight model is proposed to detect anomalous behaviors, which combines memory singular value decomposition and attention mechanism in 3d convolution. Truncated singular value decomposition is adopted to prevent overfitting, in which a cross-entropy loss is introduced into the loss function. The integrated 3d separable convolution decomposes 3d convolutions into 2d and 1d channels, which can effectively reduce the number of parameters. Compared to traditional deep learning models, experimental results have shown the proposed model is superior to others in performance on several benchmark datasets.

关键词： 3d separable convolution Lightweight Overfitting Memory Singular Value decomposition

来源：评论

学校读者我要写书评

暂无评论

F3dsCNN: A Fast Two-Branch 3d separable CNN for Moving Object detection

F3DsCNN: A Fast Two-Branch 3D Separable CNN for Moving Objec...

引用

IEEE International Conference on Visual Communications and Image Processing (VCIP) - Visual Communications in the Era of AI and Limited Resources

作者： Hou, Bingxin Liu, Ying Ling, Nam Liu, Lingzhi Ren, Yongxiong Hsu, Ming Kai Santa Clara Univ Dept Comp Sci & Engn Santa Clara CA 95053 USA Kwai Inc Palo Alto CA USA

ISBN: (纸本)9781728185514

deep learning methods have been actively applied in moving object detection and achieved great performance. However, many existing models render superior detection accuracy at the cost of high computational complexity and slow inference speed, which hindered the application on mobile and embedded devices with limited computing resources. In this paper, we propose a two-branch 3d separable convolutional neural network named "F3dsCNN" for moving object detection. The network extracts both high-level global features and low-level detailed features. It achieves a fast inference speed of 120 frames per second, suitable for tasks that need to be carried out in a timely manner on a computationally limited platform with high accuracy.

关键词： computer vision convolutional neural network depthwise convolution inverted residual linear bottleneck moving object detection pointwise convolution 3d convolution 3d separable convolution two-branch network unseen videos video analytics video surveillance

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Model with separable CNN and LSTM for Video Prediction

A Lightweight Model with Separable CNN and LSTM for Video Pr...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Mathai, Mareeta Liu, Ying Ling, Nam Santa Clara Univ Dept Comp Sci & Engn Santa Clara CA 95053 USA

ISBN: (纸本)9781665484855

Future frame prediction is an emerging, yet challenging task in the deep learning field due to its inherent uncertainty and complex spatiotemporal dynamics. The state-of-the-art methods achieve significant accuracy at the expense of complex, computationally intensive deep neural networks, which makes it difficult to deploy in mobile devices. In the light of recent wide popularity of Green AI which aims for efficient environment friendly solutions alongside accuracy, we propose a lightweight model using 3d separable convolutions, which can predict future video frames with reduced model size and reasonable accuracy-complexity tradeoffs as compared to the state-of-the-art methods.

关键词： autoencoder convolutional neural network deep learning depthwise convolution spatiotemporal LSTM video prediction 3d convolution 3d separable convolution

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：