检索结果-内蒙古大学图书馆

CPED: A Large-Scale Chinese Personalized and Emotional Dialogue dataset for Conversational AI

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： Chen, Yirong Fan, Weiquan Xing, Xiaofen Pang, Jianxin Huang, Minlie Han, Wenjing Tie, Qianfeng Xu, Xiangmin The UBTECH-SCUT Joint Research Lab Engineering Research Center Ministry of Education on Human Body Data Perception School of Electronic and Information Engineering South China University of Technology Guangzhou510641 China UBTECH Robotics Corp Shenzhen518000 China CoAI Group State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

Human language expression is based on the subjective construal of the situation instead of the objective truth conditions, which means that speakers’ personalities and emotions after cognitive processing have an important influence on conversation. However, most existing datasets for conversational AI ignore human personalities and emotions, or only consider part of them. It’s difficult for dialogue systems to understand speakers’ personalities and emotions although large-scale pre-training language models have been widely used. In order to consider both personalities and emotions in the process of conversation generation, we propose CPED, a large-scale Chinese personalized and emotional dialogue dataset, which consists of multi-source knowledge related to empathy and personal characteristic. These knowledge covers gender, Big Five personality traits, 13 emotions, 19 dialogue acts and 10 scenes. CPED contains more than 12K dialogues of 392 speakers from 40 TV shows. We release the textual dataset with audio features and video features according to the copyright claims, privacy issues, terms of service of video platforms. We provide detailed description of the CPED construction process and introduce three tasks for conversational AI, including personality recognition, emotion recognition in conversations as well as personalized and emotional conversation generation. Finally, we provide baseline systems for these tasks and consider the function of speakers’ personalities and emotions on conversation. Our motivation is to propose a dataset to be widely adopted by the NLP community as a new open benchmark for conversational AI research. The full dataset is available1 © 2022, CC BY-NC-SA.

关键词： Emotion Recognition

Itg-Yolov7-Based Temperature Extraction Method for Group-Raised Pigs from Thermal Images

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Liu, Xiaowen Zeng, Xueting Chu, Mengyuan Li, Qian Liu, Gang Li, Tao Ding, Xiangdong Mi, Yang Key Lab of Smart Agriculture Systems Ministry of Education China Agricultural University Beijing100083 China Key Laboratory of Agricultural Information Acquisition Technology Ministry of Agriculture and Rural Affairs of China China Agricultural University Beijing100083 China Henan Fengyuan Hepu Agricultural and Animal Husbandry Co. Ltd Xinyang464000 China College of Animal Science and Technology China Agricultural University Beijing100193 China National Engineering Laboratory for Animal Breeding Laboratory of Animal Genetics Breeding and Reproduction Ministry of Agriculture and Rural Affairs Beijing100193 China Key Laboratory of Agricultural Machinery Monitoring and Big Data Applications Ministry of Agriculture and Rural Affairs Beijing100083 China College of Information and Electrical Engineering China Agricultural University China

Body temperature detection in pigs is vital for effective pig breeding, particularly in large-scale farming where traditional infrared thermal imaging methods typically measure only one pig at a time, leading to inefficient monitoring. This study introduces a novel approach for detecting the body temperature of group-raised pigs by leveraging an image super-resolution (SR) algorithm alongside an instantaneous posture recognition technique. The Porcine-ESRGAN was employed to preprocess thermal infrared images, addressing issues related to low resolution and improving the characterization of target areas. Additionally, an improved You Only Look Once v7 (YOLOv7) based on pig posture classification was proposed and named ITG-YOLOv7. ITG-YOLOv7 was developed to identify the instantaneous posture of pigs and measure their ear root or eye temperature. This approach effectively resolves the challenge of obtaining the temperatures of pigs in a lying position. The ITG-YOLOv7 model integrates multi-scale features through the Scale Sequence Feature Fusion (SSFF) module and optimizes parameters with the Generalized Efficient Layer Aggregation Network (GELAN). The incorporation of Shape-IoU as the anchor box loss function enhances bounding box regression accuracy, thus improving detection precision. Performance assessment of Porcine-ESRGAN using thermal infrared images before and after preprocessing. The processed images significantly improve the detection precision (P), recall (R), and mean average precision (mAP) for lying pigs by 3.1%, 11.5%, and 6.9%, indicating that the method is effective in enhancing the temperature detection accuracy for lying pigs. The proposed ITG-YOLOv7 model achieves an accuracy of 93.2%, a R of 95.4%, and an mAP of 97.5% with a model size of 61.9 MB when used in conjunction with the Porcine-ESRGAN model. By correlating maximum head temperatures with ear root and eye temperatures, the maximum head temperature was identified as the body temperature ind

关键词： Thermography (imaging)

FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Shao, Shuo Yang, Wenyuan Gu, Hanlin Qin, Zhan Fan, Lixin Yang, Qiang Ren, Kui The State Key Laboratory of Blockchain and Data Security Zhejiang University China The School of Cyber Science and Technology Sun Yat-sen University China The Webank AI Lab China The Computer Science and Engineering Department Hong Kong University of Science and Technology Hong Kong

Federated learning (FL) is a distributed machine learning paradigm allowing multiple clients to collaboratively train a global model without sharing their local data. However, FL entails exposing the model to various participants. This poses a risk of unauthorized model distribution or resale by the malicious client, compromising the intellectual property rights of the FL group. To deter such misbehavior, it is essential to establish a mechanism for verifying the ownership of the model and as well tracing its origin to the leaker among the FL participants. In this paper, we present FedTracker, the first FL model protection framework that provides both ownership verification and traceability. FedTracker adopts a bi-level protection scheme consisting of global watermark mechanism and local fingerprint mechanism. The former authenticates the ownership of the global model, while the latter identifies which client the model is derived from. FedTracker leverages Continual Learning (CL) principles to embed the watermark in a way that preserves the utility of the FL model on both primitive task and watermark task. FedTracker also devises a novel metric to better discriminate different fingerprints. Experimental results show FedTracker is effective in ownership verification, traceability, and maintains good fidelity and robustness against various watermark removal attacks. © 2022, CC BY.

关键词： Learning systems

CPED: A Large-Scale Chinese Personalized and Emotional Dialogue dataset for Conversational AI

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Yirong Fan, Weiquan Xing, Xiaofen Pang, Jianxin Huang, Minlie Han, Wenjing Tie, Qianfeng Xu, Xiangmin The UBTECH-SCUT Joint Research Lab Engineering Research Center of Ministry of Education on Human Body Data Perception School of Electronic and Information Engineering South China University of Technology Guangzhou510641 China UBTECH Robotics Corp Shenzhen518000 China CoAI Group State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

Human language expression is based on the subjective construal of the situation instead of the objective truth conditions, which means that speakers' personalities and emotions after cognitive processing have an important influence on conversation. However, most existing datasets for conversational AI ignore human personalities and emotions, or only consider part of them. It's difficult for dialogue systems to understand speakers' personalities and emotions although large-scale pre-training language models have been widely used. In order to consider both personalities and emotions in the process of conversation generation, we propose CPED, a large-scale Chinese personalized and emotional dialogue dataset, which consists of multi-source knowledge related to empathy and personal characteristic. These knowledge covers gender, Big Five personality traits, 13 emotions, 19 dialogue acts and 10 scenes. CPED contains more than 12K dialogues of 392 speakers from 40 TV shows. We release the textual dataset with audio features and video features according to the copyright claims, privacy issues, terms of service of video platforms. We provide detailed description of the CPED construction process and introduce three tasks for conversational AI, including personality recognition, emotion recognition in conversations as well as personalized and emotional conversation generation. Finally, we provide baseline systems for these tasks and consider the function of speakers' personalities and emotions on conversation. Our motivation is to propose a dataset to be widely adopted by the NLP community as a new open benchmark for conversational AI research. The full dataset is available. © 2022, CC BY-NC-ND.

关键词： Speech processing

Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Ziyi Chen, Weikai Cheng, Hui Li, Zhen Li, Siyuan Lin, Liang Li, Guanbin National Key Laboratory of Novel Software Technology Nanjing University Nanjing China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Tencent America United States The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China AI Lab School of Engineering Westlake University Hangzhou China

We investigate a practical domain adaptation task, called source-free unsupervised domain adaptation (SFUDA), where the source pretrained model is adapted to the target domain without access to the source data. Existing techniques mainly leverage self-supervised pseudo-labeling to achieve class-wise global alignment [24] or rely on local structure extraction that encourages the feature consistency among neighborhoods [48]. While impressive progress has been made, both lines of methods have their own drawbacks – the "global" approach is sensitive to noisy labels while the "local" counterpart suffers from the source bias. In this paper, we present Divide and Contrast (DaC), a new paradigm for SFUDA that strives to connect the good ends of both worlds while bypassing their limitations. Based on the prediction confidence of the source model, DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals under an adaptive contrastive learning framework. Specifically, the source-like samples are utilized for learning global class clustering thanks to their relatively clean labels. The more noisy target-specific data are harnessed at the instance level for learning the intrinsic local structures. We further align the source-like domain with the target-specific samples using a memory-based maximum mean discrepancy (MMD) loss to reduce the distribution mismatch. Extensive experiments on VisDA, Office-Home, and the more challenging DomainNet have verified the superior performance of DaC over current state-of-the-art approaches. The code is available at https://***/ZyeZhang/***. Copyright © 2022, The Authors. All rights reserved.

关键词：

Semantics-Guided Contrastive Network for Zero-Shot Object Detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yan, Caixia Chang, Xiaojun Luo, Minnan Liu, Huan Zhang, Xiaoqin Zheng, Qinghua The Ministry of Education Key Lab of Intelligent Networks and Network Security National Engineering Lab for Big Data Analytics School of Electronic and Information Engineering Xi'an Jiaotong University Shaanxi710049 China The ReLER Lab AAAI Faculty of Engineering and Information Technology University of Technology Sydney Australia The College of Computer Science and Artificial Intelligence Wenzhou University China

Zero-shot object detection (ZSD), the task that extends conventional detection models to detecting objects from unseen categories, has emerged as a new challenge in computer vision. Most existing approaches tackle the ZSD task with a strict mapping-transfer strategy that may lead to suboptimal ZSD results: 1) the learning process of these models neglects the available semantic information on unseen classes, which can easily bias towards the seen categories;2) the original visual feature space is not well-structured for the ZSD task due to the lack of discriminative information. To address these issues, we develop a novel Semantics-Guided Contrastive Network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection. Particularly, ContrastZSD incorporates two semantics-guided contrastive learning subnets that contrast between region-category and region-region pairs respectively. The pairwise contrastive tasks take advantage of supervision signals derived from both the ground truth label and class similarity information. By performing supervised contrastive learning over those explicit semantic supervision, the model can learn more knowledge about unseen categories to avoid the bias problem to seen concepts, while optimizing the visual data structure to be more discriminative for better visual-semantic alignment. Extensive experiments are conducted on two popular benchmarks for ZSD, i.e., PASCAL VOC and MS COCO. Results show that our method outperforms the previous state-of-the-art on both ZSD and generalized ZSD tasks. © 2021, CC BY.

关键词： Object detection

Research on the Loading Method of Logistics Vehicle and Cargo Based on IPSO Algorithm

学校读者我要写书评

暂无评论

Research on the Loading Method of Logistics Vehicle and Carg...

第42届中国控制会议

作者： Zewei Zhao Huqing Wang Zhe Sun Lei Xu Guangfu Gong Xiangpeng Xie Zhixin Sun Post Industry Technology Research and Development Center of the State Posts Bureau (Internet of Things Technology) Nanjing University of Posts and Telecommunications Post Big Data Technology and Application Engineering Research Center of Jiangsu Province Nanjing University of Posts and Telecommunications Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of EducationNanjing University of Posts and Telecommunications

Logistics vehicle and cargo matching problem is a typical combination optimization problem,which has important theoretical and application value in the field of logistics *** proved particle swarm optimization(PSO) algorithm is one of the most extensive optimization methods studied in recent years,with excellent global search ability and convergence *** on the IPSO algorithm,this paper proposes an effective IPSO algorithm model for the matching problem of logistics vehicles and goods,and conducts the corresponding comparative *** final experimental results show that the algorithm has good results in practical application and can provide a feasible optimization method for solving the problem of logistics vehicles and goods.

关键词：

MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Duan, Yue Zhao, Zhen Qi, Lei Wang, Lei Zhou, Luping Shi, Yinghuan Gao, Yang The National Key Laboratory for Novel Software Technology The National Institute of Healthcare Data Science Nanjing University Nanjing210023 China The School of Electrical and Information Engineering The University of Sydney SydneyNSW2006 Australia The School of Computer Science and Engineering The Key Lab of Computer Network and Information Integration Ministry of Education Southeast University Nanjing211189 China The School of Computing and Information Technology University of Wollongong WollongongNSW2522 Australia

The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore the usage of low-confidence samples. In this paper, we aim to utilize low-confidence samples in a novel way with our proposed mutex-based consistency regularization, namely MutexMatch. Specifically, the high-confidence samples are required to exactly predict "what it is" by conventional True-Positive Classifier, while low-confidence samples are employed to achieve a simpler goal — to predict with ease "what it is not" by True-Negative Classifier. In this sense, we not only mitigate the pseudo-labeling errors but also make full use of the low-confidence unlabeled data by consistency of dissimilarity degree. MutexMatch achieves superior performance on multiple benchmark datasets, i.e., CIFAR-10, CIFAR-100, SVHN, STL-10, mini-ImageNet and Tiny-ImageNet. More importantly, our method further shows superiority when the amount of labeled data is scarce, e.g., 92.23% accuracy with only 20 labeled data on CIFAR-10. Our code and model weights have been released at https://***/NJUyued/MutexMatch4SSL. Copyright © 2022, The Authors. All rights reserved.

关键词： Benchmarking

Large Language Models for Generative Information Extraction: A Survey

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xu, Derong Chen, Wei Peng, Wenjun Zhang, Chao Xu, Tong Zhao, Xiangyu Wu, Xian Zheng, Yefeng Wang, Yang Chen, Enhong State Key Laboratory of Cognitive Intelligence University of Science and Technology of China Hefei230000 China Department of Data Science City University of Hong Kong Hongkong999077 Hong Kong Jarvis Research Center Tencent YouTu Lab Beijing100029 China Anhui Conch Information Technology Engineering Co. Ltd. Wuhu241000 China

Information extraction (IE) aims to extract structural knowledge from plain natural language texts. Recently, generative Large Language Models (LLMs) have demonstrated remarkable capabilities in text understanding and generation. As a result, numerous works have been proposed to integrate LLMs for IE tasks based on a generative paradigm. To conduct a comprehensive systematic review and exploration of LLM efforts for IE tasks, in this study, we survey the most recent advancements in this field. We first present an extensive overview by categorizing these works in terms of various IE subtasks and techniques, and then we empirically analyze the most advanced methods and discover the emerging trend of IE tasks with LLMs. Based on a thorough review conducted, we identify several insights in technique and promising research directions that deserve further exploration in future studies. We maintain a public repository and consistently update related works and resources on GitHub (LLM4IE repository). Copyright © 2023, The Authors. All rights reserved.

关键词： Information retrieval