Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence最新文献_第3页

Object Tracking Algorithm for Siamese Network Combined with Channel Attention Mechanism 结合通道关注机制的Siamese网络目标跟踪算法

Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence Pub Date : 2022-03-04 DOI: 10.1145/3529466.3529476

Xuehui Li, Yongjun Zhang, Yi Zhang, Dian-xi Shi, Huachi Xu

{"title":"Object Tracking Algorithm for Siamese Network Combined with Channel Attention Mechanism","authors":"Xuehui Li, Yongjun Zhang, Yi Zhang, Dian-xi Shi, Huachi Xu","doi":"10.1145/3529466.3529476","DOIUrl":"https://doi.org/10.1145/3529466.3529476","url":null,"abstract":"As an important branch in the field of computer vision, object tracking has been widely used in many fields such as intelligent video surveillance, human-computer interaction and autonomous driving. Although object tracking has imposing development in recent years, tracking in the complex environment is still a challenge. Due to problems such as occlusion, object deformation, and illumination change, tracking performance will be inaccurate and unstable. In this paper, an object tracking algorithm for Siamese network combined with channel attention mechanism is proposed. Firstly, the Siamese network is used to improve the ability to discriminate features; secondly, the channel attention mechanism is introduced to design a cross correlation module DCAM (Depth-wise Cross-correlation with Attention Mechanism, DCAM), which pays more attention to the features that are beneficial to the tracking results; finally, the stochastic weight averaging method is used to train the network to further improve the overall performance of the tracker. Experimental results on public data sets show that the proposed algorithm has higher accuracy and more stable tracking performance in complex tracking environment","PeriodicalId":375562,"journal":{"name":"Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126042941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Traffic Sign Detection in Complex Environment based on Multi-Scale Feature Enhancement and Group Attention 基于多尺度特征增强和群体注意的复杂环境下交通标志检测

Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence Pub Date : 2022-03-04 DOI: 10.1145/3529466.3529502

JinFei Fu, Yinghua Zhou

引用次数: 0

Atmospheric Correction for Polarimetric Images Based on Spectral Segregation 基于光谱分离的偏振图像大气校正

Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence Pub Date : 2022-03-04 DOI: 10.1145/3529466.3529479

Pu Xia, Xiaolai Chen, Zhaohuan Tang

{"title":"Atmospheric Correction for Polarimetric Images Based on Spectral Segregation","authors":"Pu Xia, Xiaolai Chen, Zhaohuan Tang","doi":"10.1145/3529466.3529479","DOIUrl":"https://doi.org/10.1145/3529466.3529479","url":null,"abstract":"In hazy weather, light's penetration power is wavelength related, the longer wavelength, the less attenuation. Although traditional polarimetric image-dehazing algorithms have demonstrated their ability in enhancing grayscale images, but their ignorance of the spectral difference will lead to serious color distortion when utilizing these algorithms for color images. To conquer that problem, we propose a new method base on spectral segregation. 15 spectral bands are selected and dehazed with the polarimetric dehazing algorithm separately to obtain the best dehazing effects. The blue, green and red channels of the dehazed image, which are acquired through image fusion of the spectral bands, are adjusted with different coefficients to correct the color distortion. 10 infrared bands are added to the short-wavelength channels to enhance the details of the objects especially the trees. Experiment and data analysis demonstrate the effectiveness of our method in increasing visibility and preserving color information. The amount of color distortion can be reduced by 89.6% compared with the polarimetric image-dehazing algorithm without spectral segregation.","PeriodicalId":375562,"journal":{"name":"Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124708271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-view Network with Transformer for Point Cloud Semantic Segmentation 基于Transformer的点云语义分割多视图网络

Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence Pub Date : 2022-03-04 DOI: 10.1145/3529466.3529504

Zhongwei Hua, Daming Du

引用次数: 0

Speech Emotion Recognition Exploiting ASR-based and Phonological Knowledge Representations 基于asr和语音知识表示的语音情感识别

Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence Pub Date : 2022-03-04 DOI: 10.1145/3529466.3529488

Shuang Liang, Xiang Xie, Qingran Zhan, Hao-bo Cheng

{"title":"Speech Emotion Recognition Exploiting ASR-based and Phonological Knowledge Representations","authors":"Shuang Liang, Xiang Xie, Qingran Zhan, Hao-bo Cheng","doi":"10.1145/3529466.3529488","DOIUrl":"https://doi.org/10.1145/3529466.3529488","url":null,"abstract":"Speech emotion recognition (SER) is a challenging problem due to the insufficient dataset. This paper deals with this problem from two aspects. First, we exploit two levels of speech representations for SER task, one for automatic speech recognition (ASR)-based representations and the other for phonological knowledge representations. Second, we use transfer learning, pre-train models and transfer knowledge from other large corpus for none-SER task. In our system, the whole model is divided into two parts: two-representation learning module and SER module. We fuse acoustic features with ASR-based and phonological knowledge representations which are both extracted from pre-trained models, and the fusion features are used in SER training. Then a novel multi-task learning approach is proposed where a shared encoder-multi decoder model is used for the phonological knowledge representation learning. The Conformer structure is introduced for the SER task, and our study indicates that Conformer is effective for SER. Finally, experimental results on IEMOCAP show that the proposed method can achieve 77.35 weighted accuracy and 77.99 unweighted accuracy respectively.","PeriodicalId":375562,"journal":{"name":"Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116839217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hard-Lite SLAM: A Hybrid Detector Based Real-Time SLAM System 硬- lite SLAM:一种基于混合检测器的实时SLAM系统

Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence Pub Date : 2022-03-04 DOI: 10.1145/3529466.3529473

Chengying Cai, Jichao Jiao, Wei Xu, Mingliang Pang, Jianye Dong

{"title":"Hard-Lite SLAM: A Hybrid Detector Based Real-Time SLAM System","authors":"Chengying Cai, Jichao Jiao, Wei Xu, Mingliang Pang, Jianye Dong","doi":"10.1145/3529466.3529473","DOIUrl":"https://doi.org/10.1145/3529466.3529473","url":null,"abstract":"Simultaneous Localization and Mapping (SLAM) system is essential for autonomous driving and mobile robots. The problem of data association between features becomes a bottleneck limiting the performance of traditional visual SLAM systems, especially in complex environments. Therefore, many studies combine the SLAM system with the Convolutional Neural Networks (CNN) to obtain a more robust data association. This paper shows that CNN-based local descriptors significantly improve the accuracy and robustness of the SLAM system. The CNN-based keypoints reduce the performance of the SLAM algorithm in many scenarios. We propose a SLAM system that combines hand-crafted keypoints with CNN local descriptors. The system is more robust in complex environments than traditional visual SLAM systems. The experimental results show that our system achieves higher localization accuracy than ORB-SLAM2 and VINS-Mono on the evaluated datasets. Meanwhile, the CNN local descriptors can be combined with any visual SLAM system and have good portability. Furthermore, with the assistant of the Nvidia TensorRT inference acceleration technology, the system can run in real-time on the Jetson AGX Xavier at 27 frames per second. CCS CONCEPTS • Computer systems organization • Embedded and cyber-physical systems • Robotics • Robotic autonomy","PeriodicalId":375562,"journal":{"name":"Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124552420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FPB-UNet++: Semantic Segmentation for Remote Sensing Images of reservoir area via Improved UNet++ with FPN fpb - un++:基于FPN改进un++的库区遥感图像语义分割

Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence Pub Date : 2022-03-04 DOI: 10.1145/3529466.3529483

Kaiyue Wang, Xiaoye Fan, Q. Wang

引用次数: 2

Event causality extraction based on Transformer sequence annotation model 基于Transformer序列标注模型的事件因果关系提取

Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence Pub Date : 2022-03-04 DOI: 10.1145/3529466.3529481

Zefeng Xie, Shengwu Xiong

引用次数: 0

A Graph Based Approach Towards Exploiting Reviews for Recommendation 利用评论进行推荐的基于图的方法

Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence Pub Date : 2022-03-04 DOI: 10.1145/3529466.3529499

Bo Kong, Caiyan Jia

{"title":"A Graph Based Approach Towards Exploiting Reviews for Recommendation","authors":"Bo Kong, Caiyan Jia","doi":"10.1145/3529466.3529499","DOIUrl":"https://doi.org/10.1145/3529466.3529499","url":null,"abstract":"Textual reviews, pervasive on many e-commerce websites, contain a lot of information. Many neural network models have been proposed to use the information of reviews to improve the performance of recommender systems. However, existing models usually use convolutional neural networks to learn the features of the reviews, often focus on the local interactions of words and lack the ability to capture long-distance and non-consecutive word interactions. Meanwhile, their ability should be strengthened on modelling the high-level interactions between users and items. Therefore, we propose a multi-view Graph based Approach towards exploiting Reviews for recommendation (GAR). It integrates the information of review content and user-item graph. In review view, we build an individual word co-occurrence graph for each review and use gated graph convolutional network to learn the features of reviews. In graph view, we use graph attention network to model high-order multi-aspect relations in the user-item graph. Both views use a graph based method. The representation of users and items learned from the two views are integrated to predict the final rating. Experiments on the benchmark datasets show that GAR achieves significantly better rating prediction accuracy compared to the state-of-the-art methods.","PeriodicalId":375562,"journal":{"name":"Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125331947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Accelerating federated learning based on grouping aggregation in heterogeneous edge computing

Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence Pub Date : 2022-03-04 DOI: 10.1145/3529466.3529505

Longbo Li, C. Li

{"title":"Accelerating federated learning based on grouping aggregation in heterogeneous edge computing","authors":"Longbo Li, C. Li","doi":"10.1145/3529466.3529505","DOIUrl":"https://doi.org/10.1145/3529466.3529505","url":null,"abstract":"Recently, edge devices such as mobile phones and smartwatches have become part of modern distributed systems, federated learning is an effectively distributed learning paradigm that can leverage these edge devices to collaboratively train models without sharing raw data. In federated learning, the device periodically downloads the model from the server, uses the local data for training, and uploads it to the server, while the servers aggregates params uploaded to update the global model. However, different devices are located in different network environments and have different communication and computation capability. Therefore, the model training speed depends on the slowest device, and the system between devices is heterogeneous. To effectively address these problems, we propose to group the devices, firstly use the synchronous method to aggregate model updates within a group, then aggregate updates between groups in an asynchronous way, and propose an algorithm based on weight update to aggregate models. We conduct extensive simulations on our proposed algorithms, and the results show that they can dramatically accelerate model training while achieving high accuracy.","PeriodicalId":375562,"journal":{"name":"Proceedings of the 2022 6th International Conference on Innovation in Artificial Intelligence","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125434086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0