检索结果-内蒙古大学图书馆

One chatbot per person: Creating personalized chatbots based on implicit user profiles

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ma, Zhengyi Dou, Zhicheng Zhu, Yutao Zhong, Hanxun Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China School of Information Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods Key Laboratory of Data Engineering and Knowledge Engineering MOE Université de Montréal MontréalQC Canada

Personalized chatbots focus on endowing chatbots with a consistent personality to behave like real users, give more informative responses, and further act as personal assistants. Existing personalized approaches tried to incorporate several text descriptions as explicit user profiles. However, the acquisition of such explicit profiles is expensive and time-consuming, thus being impractical for large-scale real-world applications. Moreover, the restricted predefined profile neglects the language behavior of a real user and cannot be automatically updated together with the change of user interests. In this paper, we propose to learn implicit user profiles automatically from large-scale user dialogue history for building personalized chatbots. Specifically, leveraging the benefits of Transformer on language understanding, we train a personalized language model to construct a general user profile from the user's historical responses. To highlight the relevant historical responses to the input post, we further establish a key-value memory network of historical post-response pairs, and build a dynamic post-aware user profile. The dynamic profile mainly describes what and howthe user has responded to similar posts in history. To explicitly utilize users' frequently used words, we design a personalized decoder to fuse two decoding strategies, including generating a word from the generic vocabulary and copying one word from the user's personalized vocabulary. Experiments on two real-world datasets show the significant improvement of our model compared with existing methods. Our code is available at https://***/zhengyima/DHAP. Copyright © 2021, The Authors. All rights reserved.

关键词： User profile

Cross-Domain Animal Pose Estimation with Skeleton Anomaly-Aware Learning

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Han, Le Chen, Kaixuan Zhao, Lei Jiang, Yangbo Wang, Pengfei Zheng, Nenggan Zhejiang Hangzhou310007 China Zhejiang University College of Computer Science and Technology Zhejiang Hangzhou310007 China Zhejiang University State Key Laboratory of Blockchain and Data Security Zhejiang Hangzhou310007 China Institute of Blockchain and Data Security. China Zhejiang University School of Software Technology Ningbo China Zhejiang University State Key Lab of Brain-Machine Intelligence Hangzhou310007 China Zhejiang Provincial Government ZJU Collaborative Innovation Center for Artificial Intelligence by MOE Hangzhou310007 China Bengbu University School of Computer and Information Engineering Bengbu233030 China

Animal pose estimation is often constrained by the scarcity of annotations and the diversity of scenarios and species. The pseudo-label generation based unsupervised domain adaptation paradigm, which discriminates the predicted keypoints of unlabeled data based on the skeleton position consistency, has demonstrated effectiveness for such problems. However, existing methods generate pseudo-labels with massive false positives, because they cannot effectively distinguish sample pairs with the same errors. In this study, we propose a cross-domain animal pose estimation model from a novel perspective of skeleton anomaly learning. We construct a graph contrastive learning mechanism to acquire the skeleton anomaly-aware knowledge, which enables the generation of accurate pseudo-labels for target domain and imposes graph constraint on unlabeled data. And a skeleton anomaly-feedback based domain adaptation framework is designed to facilitate implicit alignment of object-specific features and joint training of cross-domain. Besides, we propose a novel rat pose dataset named UDARP-9.4K to address the gap of small-sized animal pose datasets encompassing diverse experimental scenarios. The related datasets are reviewed and evaluated in detail. Extensive experiments are conducted on UDARP-9.4K and two public datasets to demonstrate the superiority of the proposed model in cross-scenarios and cross-species animal pose estimation tasks. Further analysis reveals the effectiveness of the proposed model for skeleton structure feature learning. The UDARP-9.4K dataset is available here. © 1991-2012 IEEE.

关键词： Invertebrates

A Universal data-Driven Spatial Interpolation Framework for the Measurements of Environmental Sites

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Cheng, Zhen Guo, Yuzhe Xue, Wenbo Du, Qinyi Shanghai Environmental Protection Key Lab of Environmental Big Data and Intelligent Decision-making School of Environmental Science and Engineering Shanghai Jiao Tong University Shanghai China Center of Air Quality Simulation and System Analysis Chinese Academy of Environmental Planning Beijing100043 China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China

The accurate spatial distribution of environmental pollutant metrics is crucial for evaluating human exposure and managing the environment. Spatial interpolation, which relies on the measurements of limited environmental sites, is often necessary. However, commonly used geostatistical methods often introduce significant prediction biases, leading to misleading assessments and decision-making processes. Reported machine learning studies usually required intensive spatial datasets and sites’ measurements, as well as special complex algorithm for target pollutant. In this study, we propose and validate a simple and universal data-driven spatial interpolation framework for environmental sites’ measurements. We employ a conditional generative adversarial network (cGAN) as the data-driven algorithm to leverage spatial dataset. We demonstrate the implementation and validation of the framework using two representative ambient pollutants, namely ozone and PM2.5. The results reveal a relative mean absolute error of only 9% for ozone and 13% for PM2.5. Compared to the traditional inverse distance weight method and ordinary kriging method, the proposed framework reduces errors by 70% and 79% respectively. Furthermore, the R-squared values between independent measurements from additional geographic locations and the corresponding predicted results using the proposed method reach 0.96 for ozone and 0.97 for PM2.5, showcasing its excellent and consistent performance. The unique input dataset and universal algorithm architecture illustrate the distinct advantages compared to previous machine learning studies. With the rapid increase of remote sensing and numerical modeling datasets in the environmental field, we anticipate that data-driven methods will replace traditional mathematical approaches. This study provides a simple yet universal interpolation framework and is expected to accelerate the adoption of these advancements. © 2023, The Authors. All rights reserved.

关键词： Spatial distribution

RPR-Net: A Point Cloud-based Rotation-aware Large Scale Place Recognition Network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fan, Zhaoxin Song, Zhenbo Zhang, Wenping Liu, Hongyan He, Jun Du, Xiaoyong Key Laboratory of Data Engineering and Knowledge Engineering of MOE School of Information Renmin University of China Beijing100872 China Department of Management Science and Engineering Tsinghua University Beijing100084 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

Point cloud-based large scale place recognition is an important but challenging task for many applications such as Simultaneous Localization and Mapping (SLAM). Taking the task as a point cloud retrieval problem, previous methods have made delightful achievements. However, how to deal with catastrophic collapse caused by rotation problems is still under-explored. In this paper, to tackle the issue, we propose a novel Point Cloud-based Rotation-aware Large Scale Place Recognition Network (RPR-Net). In particular, to solve the problem, we propose to learn rotation-invariant features in three steps. First, we design three kinds of novel Rotation-Invariant Features (RIFs), which are low-level features that can hold the rotation-invariant property. Second, using these RIFs, we design an attentive module to learn rotation-invariant kernels. Third, we apply these kernels to previous point cloud features to generate new features, which is the well-known SO(3) mapping process. By doing so, high-level scene-specific rotation-invariant features can be learned. We call the above process an Attentive Rotation-Invariant Convolution (ARIConv). To achieve the place recognition goal, we build RPR-Net, which takes ARIConv as a basic unit to construct a dense network architecture. Then, powerful global descriptors used for retrieval-based place recognition can be sufficiently extracted from RPR-Net. Experimental results on prevalent datasets show that our method achieves comparable results to existing state-of-the-art place recognition models and significantly outperforms other rotation-invariant baseline models when solving rotation problems. Copyright © 2021, The Authors. All rights reserved.

关键词： Network architecture

Article Reranking by Memory-Enhanced key Sentence Matching for Detecting Previously Fact-Checked Claims

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sheng, Qiang Cao, Juan Zhang, Xueyao Li, Xirong Zhong, Lei Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China China

False claims that have been previously fact-checked can still spread on social media. To mitigate their continual spread, detecting previously fact-checked claims is indispensable. Given a claim, existing works retrieve fact-checking articles (FC-articles) for detection and focus on reranking candidate articles in the typical two-stage retrieval framework. However, their performance may be limited as they ignore the following characteristics of FC-articles: (1) claims are often quoted to describe the checked events, providing lexical information besides semantics;and (2) sentence templates to introduce or debunk claims are common across articles, providing pattern information. In this paper, we propose a novel reranker, MTM (Memoryenhanced Transformers for Matching), to rank FC-articles using key sentences selected using event (lexical and semantic) and pattern information. For event information, we propose to finetune the Transformer with regression of ROUGE. For pattern information, we generate pattern vectors as a memory bank to match with the parts containing patterns. By fusing event and pattern information, we select key sentences to represent an article and then predict if the article fact-checks the given claim using the claim, key sentences, and patterns. Experiments on two real-world datasets show that MTM outperforms existing methods. Human evaluation proves that MTM can capture key sentences for explanations. The code and the dataset are at https://***/ICTMCG/MTM. © 2021, CC BY-SA.

关键词： Semantics

USED: Universal Speaker Extraction and Diarization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ao, Junyi Yıldırım, Mehmet Sinan Tao, Ruijie Ge, Meng Wang, Shuai Qian, Yanmin Li, Haizhou Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen518172 China Department of Electrical and Computer Engineering National University of Singapore Singapore119077 Singapore Saw Swee Hock School of Public Health National University of Singapore Singapore117549 Singapore Shenzhen Research Institute of Big Data Shenzhen518172 China Auditory Cognition and Computational Acoustics Lab Department of Computer Science and Engineering China MoE Key Laboratory of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China

Speaker extraction and diarization are two enabling techniques for real-world speech applications. Speaker extraction aims to extract a target speaker’s voice from a speech mixture, while speaker diarization demarcates speech segments by speaker, annotating ‘who spoke when’. Previous studies have typically treated the two tasks independently. In practical applications, it is more meaningful to have knowledge about ‘who spoke what and when’, which is captured by the two tasks. The two tasks share a similar objective of disentangling speakers. Speaker extraction operates in the frequency domain, whereas diarization is in the temporal domain. It is logical to believe that speaker activities obtained from speaker diarization can benefit speaker extraction, while the extracted speech offers more accurate speaker activity detection than the speech mixture. In this paper, we propose a unified model called Universal Speaker Extraction and Diarization (USED) to address output inconsistency and scenario mismatch issues. It is designed to manage speech mixtures with varying overlap ratios and variable number of speakers. We show that the USED model significantly outperforms the competitive baselines for speaker extraction and diarization tasks on LibriMix and SparseLibriMix datasets. We further validate the diarization performance on CALLHOME, a dataset based on real recordings, and experimental results indicate that our model surpasses recently proposed approaches. Copyright © 2023, The Authors. All rights reserved.

关键词： Frequency domain analysis

SOLVING CONTINUAL OFFLINE RL THROUGH SELECTIVE WEIGHTS ACTIVATION ON ALIGNED SPACES

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hu, Jifeng Huang, Sili Shen, Li Yang, Zhejian Hu, Shengchao Tang, Shisong Chen, Hechang Chang, Yi Tao, Dacheng Sun, Lichao School of Artificial Intelligence Jilin University China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University China MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China Shenzhen International Graduate School Tsinghua University China College of Computing and Data Science Nanyang Technological University Singapore Computer Science and Engineering Lehigh University United States

Continual offline reinforcement learning (CORL) has shown impressive ability in diffusion-based lifelong learning systems by modeling the joint distributions of trajectories. However, most research only focuses on limited continual task settings where the tasks have the same observation and action space, which deviates from the realistic demands of training agents in various environments. In view of this, we propose Vector-Quantized Continual Diffuser, named VQ-CD, to break the barrier of different spaces between various tasks. Specifically, our method contains two complementary sections, where the quantization spaces alignment provides a unified basis for the selective weights activation. In the quantized spaces alignment, we leverage vector quantization to align the different state and action spaces of various tasks, facilitating continual training in the same space. Then, we propose to leverage a unified diffusion model attached by the inverse dynamic model to master all tasks by selectively activating different weights according to the task-related sparse masks. Finally, we conduct extensive experiments on 15 continual learning (CL) tasks, including conventional CL task settings (identical state and action spaces) and general CL task settings (various state and action spaces). Compared with 16 baselines, our method reaches the SOTA performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Vector quantization

Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Dong, Jianfeng Wang, Yabing Chen, Xianke Qu, Xiaoye Li, Xirong He, Yuan Wang, Xun The College of Computer and Information Engineering Zhejiang Gongshang University Hangzhou310035 China The State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China The School of Electronic Information and Communications Huazhong University of Science and Technology Hubei430074 China The Key Lab of Data Engineering and Knowledge Engineering Renmin University of China The AIMC Lab. School of Information Renmin University of China Beijing100872 China The Alibaba Group Beijing100102 China

This paper aims for the task of text-to-video retrieval, where given a query in the form of a natural-language sentence, it is asked to retrieve videos which are semantically relevant to the given query, from a great number of unlabeled videos. The success of this task depends on cross-modal representation learning that projects both videos and sentences into common spaces for semantic similarity computation. In this work, we concentrate on video representation learning, an essential component for text-to-video retrieval. Inspired by the reading strategy of humans, we propose a Reading-strategy Inspired Visual Representation Learning (RIVRL) to represent videos, which consists of two branches: a previewing branch and an intensive-reading branch. The previewing branch is designed to briefly capture the overview information of videos, while the intensive-reading branch is designed to obtain more in-depth information. Moreover, the intensive-reading branch is aware of the video overview captured by the previewing branch. Such holistic information is found to be useful for the intensive-reading branch to extract more fine-grained features. Extensive experiments on three datasets are conducted, where our model RIVRL achieves a new state-of-the-art on TGIF and VATEX. Moreover, on MSR-VTT, our model using two video features shows comparable performance to the state-of-the-art using seven video features and even outperforms models pre-trained on the large-scale HowTo100M dataset. Code is available at https://***/LiJiaBei-7/rivrl. © 2022, CC BY.

关键词： Video recording

Disentangled Noisy Correspondence Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dang, Zhuohang Luo, Minnan Wang, Jihong Jia, Chengyou Han, Haochen Wan, Herun Dai, Guang Chang, Xiaojun Wang, Jingdong The School of Computer Science and Technology The Ministry of Education Key Laboratory of Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi'An710049 China SGIT AI Lab State Grid Shaanxi Electric Power Company Limited State Grid Corporation of China Shaanxi China The School of Information Science and Technology University of Science and Technology China United Arab Emirates The Baidu Inc China

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of MII and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal input for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL's efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning