Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence最新文献

Scale adaptive and lightweight super-resolution with a selective hierarchical residual network 具有选择性分层残差网络的规模自适应轻量级超分辨率

Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence Pub Date : 2021-03-05 DOI: 10.1145/3461353.3461376

Jiawang Dan, Zhaowei Qu, Xiaoru Wang, Fu Li, Jiahang Gu, Bing Ma

引用次数: 0

Foggy Image Detection Based on DehazeNet with improved SSD 基于改进SSD的DehazeNet雾图像检测

Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence Pub Date : 2021-03-05 DOI: 10.1145/3461353.3461363

Yahong Ma, Jinfan Cai, Jiaxin Tao, Qin Yang, Yujie Gao, Xiaojiao Fan

引用次数: 1

Multiple Biases-incorporated Latent Factorization of Tensors for Dynamic Network Link Prediction 基于多偏差的张量潜在分解的动态网络链路预测

Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence Pub Date : 2021-03-05 DOI: 10.1145/3461353.3461356

Xuke Wu, Juan Wang, Hao Wu

引用次数: 1

Learning Navigation Policies for Mobile Robots in Deep Reinforcement Learning with Random Network Distillation 基于随机网络蒸馏深度强化学习的移动机器人导航策略学习

Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence Pub Date : 2021-03-05 DOI: 10.1145/3461353.3461365

Lifan Pan, Anyi Li, Jun Ma, Jianmin Ji

{"title":"Learning Navigation Policies for Mobile Robots in Deep Reinforcement Learning with Random Network Distillation","authors":"Lifan Pan, Anyi Li, Jun Ma, Jianmin Ji","doi":"10.1145/3461353.3461365","DOIUrl":"https://doi.org/10.1145/3461353.3461365","url":null,"abstract":"Learning navigation policies considers the task of training a model that can find collision-free paths for mobile robots, where various Deep Reinforcement Learning (DRL) methods have been applied with promising results. However, the natural reward function for the task is usually sparse, i.e., obtaining a penalty for the collision and a positive reward for arriving the target position, which makes it difficult to learn. In particular, for some complex navigation environments, it is hard to search a collision-free path by the random exploration, which leads to a rather slow learning speed and solutions with poor performance. In this paper, we propose a DRL based approach to train an end-to-end navigation planner, i.e, the policy neural network, that directly translates the local grid map and the relative goal of the robot into its moving actions. To handle the sparse reward problem, we augment the normal extrinsic reward from the environment with intrinsic reward signals measured by random network distillation (RND). In specific, the intrinsic reward is calculated by two different networks from RND, which encourages the agent to explore a state that has not been seen before. The experimental results show that by augmenting the reward function with intrinsic reward signals by RND, solutions with better performance can be learned more efficiently and more stably in our approach. We also deploy the trained model to a real robot, which can perform collision avoidance in navigation tasks without any parameter tuning. A video of our experiments can be found at https://youtu.be/b1GJrWfO8pw.","PeriodicalId":114871,"journal":{"name":"Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133201732","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: 3

A Speed Planning Method Based on Time Domain of Unmanned Ground Vehicle 基于时域的无人地面车辆速度规划方法

Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence Pub Date : 2021-03-05 DOI: 10.1145/3461353.3461379

Shenmin Zhang, Shaobin Wu, Derun Li

{"title":"A Speed Planning Method Based on Time Domain of Unmanned Ground Vehicle","authors":"Shenmin Zhang, Shaobin Wu, Derun Li","doi":"10.1145/3461353.3461379","DOIUrl":"https://doi.org/10.1145/3461353.3461379","url":null,"abstract":"Speed planning ensures safety and ride comfort, and gives a reasonable driving speed for unmanned ground vehicles. Most velocity planning methods based on arc-length of a given local path are inconvenient when considering comfort constraints such as jerk and safe constraints such as lateral acceleration. In this paper, an innovative method is proposed to establish a speed curve model of multiple segment quadratic curves with respect to time domain, and the adjustment method which is dividing quadratic curves units and preinstalling jerk of local velocity curves under the constraint of different velocity correlation variables is described. In practice, the velocity profile satisfying the constraint is obtained through three steps. The first is multiple iterations which are necessary to change the speed profile. The second is jerk boundary adjustment including safety and comfort. The third step is assigning the velocity value to each point of the local path. Furthermore, Simulation result of unmanned vehicle road entrance ramp merging scenario shows the effectiveness of the proposed method through presetting driving conditions and constraints.","PeriodicalId":114871,"journal":{"name":"Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125649828","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

Street-level Air Quality Inference Based on Geographically Context-aware Random Forest Using Opportunistic Mobile Sensor Network 基于地理环境感知随机森林的街道级空气质量推断利用机会移动传感器网络

Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence Pub Date : 2021-03-05 DOI: 10.1145/3461353.3461370

Xuening Qin, T. Do, J. Hofman, Esther Rodrigo, Valerio La Manna Panzica, N. Deligiannis, Wilfried Philips

{"title":"Street-level Air Quality Inference Based on Geographically Context-aware Random Forest Using Opportunistic Mobile Sensor Network","authors":"Xuening Qin, T. Do, J. Hofman, Esther Rodrigo, Valerio La Manna Panzica, N. Deligiannis, Wilfried Philips","doi":"10.1145/3461353.3461370","DOIUrl":"https://doi.org/10.1145/3461353.3461370","url":null,"abstract":"The spatial heterogeneity and temporal variability of air pollution in urban environments make air quality inference for fine-grained air pollution monitoring extremely challenging. Most of the existing work estimates the air quality using sparse measurements collected from a limited number of fixed monitoring stations or make use of computationally demanding physicochemical models simulating the source and fate of pollutants across multiple spatial scales. In this work, we propose a geographically context-aware random forest model for street-level air quality inference using high spatial resolution data collected by an opportunistic mobile sensor network. Compared with a traditional random forest model, the proposed method builds a local model for each location by considering the neighbors in both geographical and feature space. The model is evaluated on our real air quality dataset collected from mobile sensors in Antwerp, Belgium. The experimental results show that the proposed method outperforms a series of commonly used methods including Ordinary Kriging (OK), Inverse Distance Weighting (IDW) and Random forest (RF).","PeriodicalId":114871,"journal":{"name":"Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127822530","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: 2

Parallel Attention with Weighted Efficient Network for Video-Based Person Re-Identification 基于加权高效网络的并行关注视频人物再识别

Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence Pub Date : 2021-03-05 DOI: 10.1145/3461353.3461357

Junting Yang, Z. Yang, Jing Zhou, Yong Zhao, Qifei Dai, Fuchi Li

{"title":"Parallel Attention with Weighted Efficient Network for Video-Based Person Re-Identification","authors":"Junting Yang, Z. Yang, Jing Zhou, Yong Zhao, Qifei Dai, Fuchi Li","doi":"10.1145/3461353.3461357","DOIUrl":"https://doi.org/10.1145/3461353.3461357","url":null,"abstract":"In this paper, we propose a new way to solve the problems of temporal and spatial independence, shallow feature extraction, and large computation which are not solved by traditional video-based Re-ID methods. Insufficient ability to extract features based on traditional networks can cause problems with bad ripple effect later, therefore we design an attention network named Parallel Spatio-Temporal Attention (PSTA) to fuse spatio-temporal features. After extracting deep features, existed methods need stack convolutional operation to model large receptive fields, so we use Non-local operation to capture long-range dependencies directly. For Non-local method, we propose an Attention-Like Similarity (ALS) to learn the weights of similarity matrix adaptively, then filter out redundant similarities. To solve the high complexity brought by Non-local method and maintain accuracy, we perform Spatial Pyramid Pooling (SPP) in Non-local structure to reduce complexity and combine multi-scale features. Extensive experiments with ablation analysis show the effectiveness of our methods, and state-of-the-art results are achieved on large-scale video datasets.","PeriodicalId":114871,"journal":{"name":"Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123320563","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

Acquisition of Cooperative Behavior in a Soccer Task Using Reward Shaping 基于奖励塑造的足球任务合作行为习得

Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence Pub Date : 2021-03-05 DOI: 10.1145/3461353.3461360

Takashi Abe, R. Orihara, Y. Sei, Yasuyuki Tahara, Akihiko Ohsuga

引用次数: 1

Few-Shot Text Classification with External Knowledge Expansion 基于外部知识扩展的小样本文本分类

Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence Pub Date : 2021-03-05 DOI: 10.1145/3461353.3461389

Jian Guan, Rui Xu, Jing Ya, Qiu Tang, Jidong Xue, Ni Zhang

{"title":"Few-Shot Text Classification with External Knowledge Expansion","authors":"Jian Guan, Rui Xu, Jing Ya, Qiu Tang, Jidong Xue, Ni Zhang","doi":"10.1145/3461353.3461389","DOIUrl":"https://doi.org/10.1145/3461353.3461389","url":null,"abstract":"The performance of most current models for text classification drops dramatically when annotated data is scarce. In such challenging scenarios, the existing models for few-shot text classification are not accurate or robust enough due to limited capture of semantic knowledge. In this paper, we propose a method of few-shot text classification based on external knowledge expansion and two strategies of expansion to supervise richer information during training and prediction, by leveraging WordNet and pre-trained model BERT. We split texts into sentences, develop techniques to select terms to semantically expand sentences based on knowledge and measure the text instance representation after knowledge expansion. In this way, we find the method is capable of improving the performance on the task of few-shot text classification. We evaluate our method on two English text classification datasets - IMDB and ASRS across a range of training set sizes. Experiment results show that by knowledge expansion, our method is robust and yields better or comparable performance to the state-of-the-art methods on both datasets, which achieves 2.7% relative improvement compared with previous method on the ASRS test set with the training set size of 380.","PeriodicalId":114871,"journal":{"name":"Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132437454","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

Target detection algorithm based on CNN and its FPGA implementation 基于CNN的目标检测算法及其FPGA实现

Proceedings of the 2021 5th International Conference on Innovation in Artificial Intelligence Pub Date : 2021-03-05 DOI: 10.1145/3461353.3461385

Yan Yan, Yonghui Zhang, Jian Zhang, Ruonan Liu

引用次数: 1