Jiaying Zou, Xuechen Zhao, Feng Xie, Bin Zhou, Zhong Zhang, Lei Tian
{"title":"Zero-Shot Stance Detection via Sentiment-Stance Contrastive Learning","authors":"Jiaying Zou, Xuechen Zhao, Feng Xie, Bin Zhou, Zhong Zhang, Lei Tian","doi":"10.1109/ICTAI56018.2022.00044","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00044","url":null,"abstract":"Zero-shot stance detection (ZSSD) is an important research problem that requires algorithms to have good stance detection capability even for unseen targets. In general, stance features can be grouped into two types: target-invariant and target-specific. Target-invariant features express the same stance regardless of the targets they are associated with, and such features are general and transferable. On the contrary, target-specific features will only be directly associated with specific targets. Therefore, it is crucial to effectively mine target-invariant features in texts in ZSSD. In this paper, we develop a method based on contrastive learning to mine certain transferable target-invariant expression features in texts from two dimensions of sentiment and stance and then generalize them to unseen targets. Specifically, we first grouped all texts into several types in terms of two orthogonal dimensions: sentiment polarity and stance polarity. Then we devise a supervised contrastive learning-based strategy to capture each type's common and transferable expressive features. Finally, we fuse the above-mentioned expressive features with the semantic features of the original texts about specific targets to deal with the stance detection for unseen targets. Extensive experiments on three benchmark datasets show that our proposed model achieves the state-of-the-art performance on most datasets. Code and other resources are available on GitHub11https://github.com/zoujiaying1995/sscl-project.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132200191","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}
{"title":"Explicit History Selection for Conversational Question Answering","authors":"Zhiyuan Zhang, Qiaoqiao Feng, Yujie Wang","doi":"10.1109/ICTAI56018.2022.00212","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00212","url":null,"abstract":"Topic shift is very common in multi-turn dialogues, making it a great challenge in the filed of conversational question answering. Existing methods usually select the most adjacent turns as history information, however, it is useless or even harmful in case of topic shift. This paper proposes two explicit history selection models: SHSM and DHSM, to address this issue. The former is a simple history selection model, which only selects $boldsymbol{k}$ previous history turns; and the latter is a dependent history selection model, which selects the most relevant $boldsymbol{k}$ history turns through a turn-dependent graph. The two models are then trained in a consistency framework. Experimental results on QuAC show that our model can cope with topic shift problem, and it outperforms existing state-of-the-art methods by 0.8 on $boldsymbol{F}_{mathbf{1}}$ score, 0.7 on HEQ-Q score, and 1.4 on HEQ-D score.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114560076","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}
{"title":"MoGoCo-@Net: Discrete Multi-Objective Grey Wolf Optimization for Discovering Community Structures in Attributed Networks","authors":"Mehdi Azaouzi, L. Romdhane","doi":"10.1109/ICTAI56018.2022.00174","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00174","url":null,"abstract":"In this paper, we deal with the problem of community detection in attributed networks. The multi-objective grey wolf optimizer is adopted in order to discover the optimal partition with multiple objectives for the first time. This paper presents MoGoCo-@Net, a novel multiQbjective discrete grey wolf optimizatlon algorithm to solve the community detection-problem in the @ttributed networks. To fully exploit the topology structure and node attribute of vertices at each time step, we introduce two new criteria and maximize them simultaneously. Moreover, MoGoCo-@Net used opposition-based learning and improved label propagation technique by combining the node's attributes with the network topology for fast and effective initialization. Then, MoGoCo-@Net redefined the social hierarchy and the hunting behavior of grey wolves in discretization. Next, a multi-individual mutation operation is adopted as an evolutionary operation. In our experiments, various benchmark attributed networks are used to compare with some state-of-the-art methods. The experimental results show that the proposed algorithm performs favorably against the compared methods.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117181131","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}
Ji Wang, Ziyue Hou, Long Zhang, Wei Li, Zhongxue Gan
{"title":"Imitation Learning-Based Drone Motion Planning in Dense Obstacle Scenarios","authors":"Ji Wang, Ziyue Hou, Long Zhang, Wei Li, Zhongxue Gan","doi":"10.1109/ICTAI56018.2022.00126","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00126","url":null,"abstract":"For the drone motion planning problem in dense obstacle scenarios, we introduce a trajectory generation method based on imitation learning that does not require the establish-ment of a local map, which greatly increases the planning speed. This method utilizes only onboard sensors and depth camera perception. We specially made the Imitation Learning Planning-Drones (ILP-Drones) dataset for training. The kinodynamic and smoothness of the generated trajectory are improved with local nonlinear optimization. The uniform B-Spline parameterization is adopted to allocate a reasonable time interval for the generated trajectory. Ultimately, our method is able to plan high quality trajectories with excellent collision avoidance ability within mil-liseconds. This is demonstrated by comparative experiments with various advanced algorithms. At the same time, the flexibility and adaptability of our method are demonstrated by ablation experiments with different number of predicted points and different simulation environments.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117230129","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}
Min Yang, Yaochen Li, Su Wang, Shaohan Yang, Hujun Liu
{"title":"RITNet: A Rotation Invariant Transformer based Network for Point Cloud Registration","authors":"Min Yang, Yaochen Li, Su Wang, Shaohan Yang, Hujun Liu","doi":"10.1109/ICTAI56018.2022.00096","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00096","url":null,"abstract":"Conventional point cloud registration methods usually employ an encoder-decoder architecture, where mid-level features are locally aggregated to extract geometric information. However, the over-reliance on local features may raise the boundary points cannot be adequately matched for two point clouds. To address this issue, we argue that the boundary features can be further enhanced by the rotation information, and propose a rotation invariant representation to replace common 3D Cartesian coordinates as the network inputs that enhances generalization to arbitrary orientations. Based on this technique, we propose rotation invariant Transformer for point cloud registration, which utilizes insensitivity to arrangement and quantity of data in the Transformer module to capture global structural knowledge within local parts for overall comprehension of each point clouds. Extensive quantitative and qualitative experimental on ModelNet40 evaluations show the effectiveness of the proposed method.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125787302","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}
{"title":"In-air Handwriting System Based on Improved YOLOv5 algorithm and Monocular Camera","authors":"Minghong Ye, Xiwen Qu, Jun Huang, Xuangou Wu","doi":"10.1109/ICTAI56018.2022.00145","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00145","url":null,"abstract":"In-air handwriting is a new and more humanized human-computer interaction way. The existing in-air handwriting systems are mainly based on three-dimensional sensors, which are expensive, too large and not conducive for integration and application promotion. To solve this problem, this paper proposes a new in-air handwriting system using cheap and portable monocular camera which allows users writing freely in the air. Additionally we develop an end-to-end fingertip detection algorithm based on improved YOLOv5 algorithm to form in-air handwritten characters. Concretely, we first build a fingertip images dataset. After preprocessing and fingertip labeling, we use the dataset to train the improved YOLOv5 model, and then use the trained model to detect the coordinates of the fingertip in each video frame. After that, we connect the coordinates of the fingertip of each frame to form the character, and finally utilize the classifiers to recognize characters. The experimental results show that proposed in-air handwriting system allows user write freely in the air, and can obtain over 92 % in fingertip detection and character recognition.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128700555","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}
Qianhui Wang, Xinzhi Wang, Mingke Gao, Xiangfeng Luo, Y. Li, Han Zhang
{"title":"Fully Parameterized Dueling Mixing Distributional Q-Leaning for Multi-Agent Cooperation","authors":"Qianhui Wang, Xinzhi Wang, Mingke Gao, Xiangfeng Luo, Y. Li, Han Zhang","doi":"10.1109/ICTAI56018.2022.00175","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00175","url":null,"abstract":"Multi-agent reinforcement learning (MARL) has been applied to many multi-agent team tasks, such as multi-robot swarm control. Distributional Value Function Factorization (DFAC) follows the Distributional-Individual-Global-Max (DIGM) principle, which forces the individual's optimal action to be in accordance with the optimal joint action at all times. However, this principle leads to grade inflation, which limits agents to exploring better strategies than before. We focus on this issue and propose a novel MARL method named dueling mixing distributional Q-learning with fully parameters (FDMIX). Firstly, a parametric individual value network generates an individual distribution function and a utility value function, while the fractions are obtained through a fraction proposal network. Secondly, the conversion mixing network obeys a new advantage-based DIGM principle to generate a joint distribution action value based on the global state. Finally, we incorporate an N-step return-based loss function to achieve stable and efficient training. Our extensive tests on the multiple-particle environment and StarCraft II show that our method performs better than state-of-the-art algorithms noticeably.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127281409","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}
{"title":"Half Title Page","authors":"","doi":"10.1109/ictai56018.2022.00001","DOIUrl":"https://doi.org/10.1109/ictai56018.2022.00001","url":null,"abstract":"","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122350389","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}
{"title":"A Novel Multi-Frequency Coordinated Module for SAR Ship Detection","authors":"Chenchen Qiao, Fei Shen, Xuejun Wang, Ruixin Wang, Fang Cao, Sixian Zhao, Chang Li","doi":"10.1109/ICTAI56018.2022.00124","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00124","url":null,"abstract":"Synthetic aperture radar (SAR) ships have rich multi-frequency information, however, existing SAR ship detection methods mostly only consider high-frequency information, ignoring other frequency features and structured relationships. For that, a novel plug-and-play Multi-Frequency Coordinated (MFC) module is developed for SAR ship detection. Specifically, the proposed MFC consists of the two key submodules, i.e., Multi-Frequency Aggregate (MFA) and Frequency Response (FR). First, MFA is used to refine the different frequency feature maps along the channel dimension and Discrete Cosine Transform (DCT) bases to solve the problem of dense multi-target SAR ship detection. Then, FR is introduced to select the one with a better response from multi-frequency and boost the significant features of ship targets and suppress interference of surroundings. Lastly, we develop a YOLOv5s-MFC by embedding the MFC for ship detection. Extensive experiments on three large-scale ship datasets (SSDD, HRSID, and LS-SSDD-v1.0) demonstrate that the proposed YOLOv5s-MFC is superior to state-of-the-art ship detection approaches.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130713367","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}
{"title":"EMAS: Efficient Meta Architecture Search for Few-Shot Learning","authors":"Dongkai Liu, Jiaxing Li, Honglong Chen, Baodi Liu, Xiaoping Lu, Weifeng Liu","doi":"10.1109/ICTAI56018.2022.00099","DOIUrl":"https://doi.org/10.1109/ICTAI56018.2022.00099","url":null,"abstract":"With the progress of few-shot learning, it has been scaled to many domains in the real world which have few labeled data, such as image classification and object detection. Many efforts for data embedding and feature combination have been made by designing a fixed neural architecture that can also be extended to variable and adaptive neural architectures for better performance. Recent works leverage neural architecture search technique to automatically design networks for few-shot learning but it requires vast computation costs and GPU memory requirements. This work introduces EMAS, an efficient method to speed up the searching process for few-shot learning. Specifically, we build a supernet to combine all candidate operations and then adopt gradient-based methods to search. Instead of training the whole supernet, we adopt Gumbel reparameterization technique to sample and activate a small subset of operations. EMAS handles a single path in a novel task adapted with just a few steps and time. A novel task only needs to learn fewer parameters and compute less content. During meta-testing, the task can well adapt to the network architecture although only with a few iterations. Empirical results show that EMAS yields a fair improvement in accuracy on the standard few-shot classification benchmark and is five times smaller in time.","PeriodicalId":354314,"journal":{"name":"2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130225584","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}