检索结果-内蒙古大学图书馆

Interspeech Conference

作者： Li, Guangyao Xu, Yixin Hu, Di Renmin Uniivers China Gaoling Sch Artificial Intelligence Beijing Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China

Audio question answering (AQA), acting as a widely used proxy task to explore scene understanding, has got more attention. The AQA is challenging for it requires comprehensive temporal reasoning from different scales' events of an audio scene. However, existing methods mostly extend the structures of visual question answering task to audio ones in a simple pattern but may not perform well when perceiving a fine-grained audio scene. To this end, we present a Multi-scale Window Attention Fusion Model (MWAFM) consisting of an asynchronous hybrid attention module and a multi-scale window attention module. The former is designed to aggregate unimodal and cross-modal temporal contexts, while the latter captures sound events of varying lengths and their temporal dependencies for a more comprehensive understanding. Extensive experiments are conducted to demonstrate that the proposed MWAFM can effectively explore temporal information to facilitate AQA in the fine-grained scene. (1)

关键词： Audio Question Answering Multi-scale Attention Temporal reasoning

来源：评论

学校读者我要写书评

暂无评论

Fair Scratch Tickets: Finding Fair Sparse Networks without Weight Training

Fair Scratch Tickets: Finding Fair Sparse Networks without W...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Tang, Pengwei Yao, Wei Li, Zhicong Liu, Yong Renmin Univ China Gaoling Sch Artificial Intelligence Beijing Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China

ISBN: (纸本)9798350301298

Recent studies suggest that computer vision models come at the risk of compromising fairness. There are extensive works to alleviate unfairness in computer vision using pre-processing, in-processing, and post-processing methods. In this paper, we lead a novel fairness-aware learning paradigm for in-processing methods through the lens of the lottery ticket hypothesis (LTH) in the context of computer vision fairness. We randomly initialize a dense neural network and find appropriate binary masks for the weights to obtain fair sparse subnetworks without any weight training. Interestingly, to the best of our knowledge, we are the first to discover that such sparse subnetworks with inborn fairness exist in randomly initialized networks, achieving an accuracy-fairness trade-off comparable to that of dense neural networks trained with existing fairness-aware in-processing approaches. We term these fair subnetworks as Fair Scratch Tickets (FSTs). We also theoretically provide fairness and accuracy guarantees for them. In our experiments, we investigate the existence of FSTs on various datasets, target attributes, random initialization methods, sparsity patterns, and fairness surrogates. We also find that FSTs can transfer across datasets and investigate other properties of FSTs.

关键词： accountability ethics in vision fairness privacy Transparency

来源：评论

学校读者我要写书评

暂无评论

PSGAN: A Minimax Game for Personalized Search with Limited and Noisy Click data 19

PSGAN: A Minimax Game for Personalized Search with Limited a...

引用

42nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

作者： Lu, Shuqi Dou, Zhicheng Xu, Jun Nie, Jian-Yun Wen, Ji-Rong Renmin Univ China Sch Informat Beijing Peoples R China Univ Montreal DIRO Montreal PQ Canada Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China MOE Key Lab Data Engn & Knowledge Engn Beijing Peoples R China

ISBN: (纸本)9781450361729

Personalized search aims to adapt document ranking to user's personal interests. Traditionally, this is done by extracting click and topical features from historical data in order to construct a user profile. In recent years, deep learning has been successfully used in personalized search due to its ability of automatic feature learning. However, the small amount of noisy personal data poses challenges to deep learning models to learn the personalized classification boundary between relevant and irrelevant results. In this paper, we propose PSGAN, a Generative Adversarial Network (GAN) framework for personalized search. By means of adversarial training, we enforce the model to pay more attention to training data that are difficult to distinguish. We use the discriminator to evaluate personalized relevance of documents and use the generator to learn the distribution of relevant documents. Two alternative ways to construct the generator in the framework are tested: based on the current query or based on a set of generated queries. Experiments on data from a commercial search engine show that our models can yield significant improvements over state-of-the-art models.

关键词： personalized web search generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

TEXT2POSTER: LAYING OUT STYLIZED TEXTS ON RETRIEVED IMAGES 47

TEXT2POSTER: LAYING OUT STYLIZED TEXTS ON RETRIEVED IMAGES

引用

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Jin, Chuhao Xu, Hongteng Song, Ruihua Lu, Zhiwu Renmin Univ China Gaoling Sch Artificial Intelligence Beijing 100872 Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China

ISBN: (纸本)9781665405409

Poster generation is a significant task for a wide range of applications, which is often time-consuming and requires lots of manual editing and artistic experience. In this paper, we propose a novel data-driven framework, called Text2Poster, to automatically generate visually-effective posters from textual information. Imitating the process of manual poster editing, our framework leverages a large-scale pretrained visualtextual model to retrieve background images from given texts, lays out the texts on the images iteratively by cascaded autoencoders, and finally, stylizes the texts by a matching-based method. We learn the modules of the framework by weakly- and self-supervised learning strategies, mitigating the demand for labeled data. Both objective and subjective experiments demonstrate that our Text2Poster outperforms state-of-the-art methods, including academic research and commercial software, on the quality of generated posters.

关键词： Poster Generation Image-Text Retrieval Layout Prediction Weakly- and Self-Supervised Learning

来源：评论

学校读者我要写书评

暂无评论

A Thorough Examination on Zero-shot Dense Retrieval

A Thorough Examination on Zero-shot Dense Retrieval

引用

Conference on Empirical methods in Natural Language Processing (EMNLP)

作者： Ren, Ruiyang Qu, Yingqi Liu, Jing Zhao, Wayne Xin Wu, Qifei Ding, Yuchen Wu, Hua Wang, Haifeng Wen, Ji-Rong Renmin Univ China Gaoling Sch Artificial Intelligence Beijing Peoples R China Baidu Inc Beijing Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China

ISBN: (纸本)9798891760615

Recent years have witnessed the significant advance in dense retrieval (DR) based on powerful pre-trained language models (PLM). DR models have achieved excellent performance in several benchmark datasets, while they are shown to be not as competitive as traditional sparse retrieval models (e.g., BM25) in a zero-shot retrieval setting. However, in the related literature, there still lacks a detailed and comprehensive study on zero-shot retrieval. In this paper, we present the first thorough examination of the zero-shot capability of DR models. We aim to identify the key factors and analyze how they affect zero-shot retrieval performance. In particular, we discuss the effect of several key factors related to source training set, analyze the potential bias from the target dataset, and review and compare existing zero-shot DR models. Our findings provide important evidence to better understand and develop zero-shot DR models.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Segmentation with Selectively Propagated Constraints 23rd

Segmentation with Selectively Propagated Constraints

引用

23rd International Conference on Neural Information Processing (ICONIP)

作者： Han, Peng Liu, Guangzhen Huang, Songfang Yuan, Wenwu Lu, Zhiwu Renmin Univ China Sch Informat Beijing Key Lab Big Data Management & Anal Method Beijing 100872 Peoples R China IBM China Res Lab Beijing Peoples R China

ISBN: (纸本)9783319466729;9783319466712

This paper presents a novel selective constraint propagation method for constrained image segmentation. In the literature, many pairwise constraint propagation methods have been developed to exploit pairwise constraints for cluster analysis. However, since these methods mostly have a polynomial time complexity, they are not much suitable for segmentation of images even with a moderate size, which is equal to cluster analysis with a large data size. In this paper, we thus choose to perform pair-wise constraint propagation only over a selected subset of pixels, but not over the whole image. Such a selective constraint propagation problem is then solved by an efficient graph-based learning algorithm. Finally, the selectively propagated constraints are exploited based on L-1-minimization for normalized cuts over the whole image. The experimental results show the promising performance of the proposed method.

关键词： Constrained image segmentation Pairwise constraint propagation Graph-based learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing power consumption of mobile devices for video streaming over 4G LTE networks

引用

PEER-TO-PEER NETWORKING AND APPLICATIONS 2018年第5期11卷 1101-1114页

作者： Zhang, Jingyu Wang, Zhi-Jie Quan, Zhe Yin, Jian Chen, Yuanyi Guo, Minyi Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai Peoples R China Sun Yat Sen Univ Sch Data & Comp Sci Guangdong Key Lab Big Data Anal & Proc Guangzhou Guangdong Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China Hunan Univ Coll Comp Sci & Elect Engn Changsha Hunan Peoples R China

While the video streaming technique and 4G LTE networks are developing rapidly, the advancement of the battery technology, however, is relatively slow. Existing works have paid much attention to understanding the power consumption in general 4G LTE networks, while few attention has been paid to reducing the power consumption for online video streaming in 4G LTE networks. Our previous work based on the real experimental platform showed that, the saving room in the network part is large, the transmission pattern and the number of RRC tails could be promising for optimizing the power consumption. In this paper, we attempt to develop efficient optimization strategies to save the energy cost of mobile devices for online video streaming over 4G LTE networks. This problem is clearly important and also interesting, while it is challenging, due to various reasons such as the uncertainty of users' behavior modes. To alleviate the challenges, we suggest a self-adaptive method that can allow us to adjust various parameters dynamically and efficiently, so as to achieve a relatively small energy consumption. We give the rigorous theoretical analysis for the proposed method, and conduct extensive experiments to validate its effectiveness. The experimental results show that the proposed method consistently outperforms the classical method as well as other competitors adapted from existing methods.

关键词： Power efficiency Online video streaming User behavior 4G LTE networks Mobile devices

来源：评论

学校读者我要写书评

暂无评论

ReBoost: a retrieval-boosted sequence-to-sequence model for neural response generation

引用

INFORMATION RETRIEVAL JOURNAL 2020年第1期23卷 27-48页

作者： Zhu, Yutao Dou, Zhicheng Nie, Jian-Yun Wen, Ji-Rong Renmin Univ China Sch Informat Beijing Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China Univ Montreal DIRO CP 6128Succ Ctr Ville Montreal PQ Canada

Human-computer conversation is an active research topic in natural language processing. One of the representative methods to build conversation systems uses the sequence-to-sequence (Seq2seq) model through neural networks. However, with limited input information, the Seq2seq model tends to generate meaningless and trivial responses. It can be greatly enhanced if more supplementary information is provided in the generation process. In this work, we propose to utilize retrieved responses to boost the Seq2seq model for generating more informative replies. Our method, called ReBoost, incorporates retrieved results in the Seq2seq model by a hierarchical structure. The input message and retrieved results can influence the generation process jointly. Experiments on two benchmark datasets demonstrate that our model is able to generate more informative responses in both automatic and human evaluations and outperforms the state-of-the-art response generation models.

关键词： Retrieved results Seq2seq model Response generation

来源：评论

学校读者我要写书评

暂无评论

A Category-aware Multi-interest Model for Personalized Product Search 22

A Category-aware Multi-interest Model for Personalized Produ...

引用

31st ACM Web Conference (WWW)

作者： Liu, Jiongnan Dou, Zhicheng Zhu, Qiannan Wen, Ji-Rong Renmin Univ China Gaoling Sch Artificial Intelligence Beijing Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China MOE Key Lab Data Engn & Knowledge Engn Beijing Peoples R China

ISBN: (纸本)9781450390965

Product search has been an important way for people to find products on online shopping platforms. Existing approaches in personalized product search mainly embed user preferences into one single vector. However, this simple strategy easily results in sub-optimal representations, failing to model and disentangle user's multiple preferences. To overcome this problem, we proposed a category-aware multi-interest model to encode users as multiple preference embeddings to represent user-specific interests. Specifically, we also capture the category indications for each preference to indicate the distribution of categories it focuses on, which is derived from rich relations between users, products, and attributes. Based on these category indications, we develop a category attention mechanism to aggregate these various preference embeddings considering current queries and items as the user's comprehensive representation. By this means, we can use this representation to calculate matching scores of retrieved items to determine whether they meet the user's search intent. Besides, we introduce a homogenization regularization term to avoid the redundancy between user interests. Experimental results show that the proposed method significantly outperforms existing approaches.

关键词： personalized product search multi-interest knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Improving Session Search by Modeling Multi-Granularity Historical Query Change 22

Improving Session Search by Modeling Multi-Granularity Histo...

引用

15th ACM International Conference on Web Search and data Mining (WSDM)

作者： Zuo, Xiaochen Dou, Zhicheng Wen, Ji-Rong Renmin Univ China Gaoling Sch Artificial Intelligence Beijing Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China Key Lab Data Engn & Knowledge Engn MOE Beijing Peoples R China

ISBN: (纸本)9781450391320

In session search, it's important to utilize historical interactions between users and the search engines to improve document retrieval. However, not all historical information contributes to document ranking. Users often express their preferences in the process of modifying the previous query, which can help us catch useful information in the historical interactions. Inspired by it, we propose to model historical query change to improve document ranking performance. Especially, we characterize multi-granularity query change between each pair of adjacent queries at both term level and semantic level. For term level query change, we calculate three types of term weights, including the retained term weights, added term weights and removed term weights. Then we perform term-based interaction between the candidate document and historical queries based on the term weights. For semantic level query change, we calculate an overall representation of user intent by integrating the representations of each historical query obtained by different types of term weights. Then we adopt representation-based matching between this representation and the candidate document. To improve the effect of query change modeling, we introduce query change classification as an auxiliary task. Experimental results on AOL and TianGong-ST search logs show that our model outperforms most existing models for session search.

关键词： Session Search Query Change Document Ranking

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：