A5021268896- Topic Modeling
- Advanced Sensor and Control Systems
- Information Retrieval and Search Behavior
- Sentiment Analysis and Opinion Mining
- Recommender Systems and Techniques
- Web Data Mining and Analysis
- Advanced Graph Neural Networks
- Image Retrieval and Classification Techniques
- Data Management and Algorithms
- Advanced Computational Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Text and Document Classification Technologies
- Spam and Phishing Detection
- Complex Network Analysis Techniques
- Face and Expression Recognition
- Misinformation and Its Impacts
- Sparse and Compressive Sensing Techniques
- Simulation and Modeling Applications
- Advanced Text Analysis Techniques
- Rough Sets and Fuzzy Logic
- Engineering and Test Systems
- Advanced Algorithms and Applications
- Safety and Risk Management
- Advanced Fiber Optic Sensors
- Mobile Crowdsensing and Crowdsourcing
Chongqing University of Technology
2007-2024
Harbin University of Science and Technology
2008-2023
Shandong University
2023
Air Force Medical University
2021-2022
Beijing Aerospace Flight Control Center
2017-2020
Nanjing University of Posts and Telecommunications
2020
Xi'an High Tech University
2005-2018
PLA Rocket Force University of Engineering
2008-2018
L3S Research Center
2013-2016
Leibniz University Hannover
2014-2016
The research field of Information Retrieval (IR) has evolved significantly, expanding beyond traditional search to meet diverse user information needs. Recently, Large Language Models (LLMs) have demonstrated exceptional capabilities in text understanding, generation, and knowledge inference, opening up exciting avenues for IR research. LLMs not only facilitate generative retrieval but also offer improved solutions model evaluation, user-system interactions. More importantly, the synergistic...
Publicly available social media archives facilitate research in the sciences and provide corpora for training testing a wide range of machine learning natural language processing methods. With respect to recent outbreak Coronavirus disease 2019 (COVID-19), online discourse on Twitter reflects public opinion perception related pandemic itself as well mitigating measures their societal impact. Understanding such discourse, its evolution, interdependencies with real-world events or...
In this paper, a real-time scheduling problem of dual-resource flexible job shop with robots is studied. Multiple independent and their supervised machine sets form own work cells. First, mixed integer programming model established, which considers the problems jobs machines in cells, between based on process plan flexibility. Second, order to make decisions, framework multi-task multi-agent reinforcement learning centralized training decentralized execution proposed. Each agent interacts...
Query similarity calculation is an important problem and has a wide range of applications in IR, including query recommendation, expansion, even advertisement matching. Existing work on aims to provide single measure without considering the fact that queries are ambiguous usually have multiple search intents. In this paper, we argue should be defined upon intents, so-called intent-aware similarity. By introducing intents into similarity, can obtain more accurate also informative measures...
Ranking is an important problem in various applications, such as Information Retrieval (IR), natural language processing, computational biology, and social sciences. Many ranking approaches have been proposed to rank objects according their degrees of relevance or importance. Beyond these two goals, diversity has also recognized a crucial criterion ranking. Top ranked results are expected convey little redundant information possible, cover many aspects possible. However, existing either take...
Query recommendation has been considered as an effective way to help search users in their information seeking activities. Traditional approaches mainly focused on recommending alternative queries with close intent the original query. However, only take relevance into account may generate redundant recommendations users. It is better provide diverse well relevant query recommendations, so that we can cover multiple potential intents of and minimize risk will not be satisfied. Besides,...
Social tags are known to be a valuable source of information for image retrieval and organization. However, contrary the conventional document retrieval, rich tag frequency in social sharing systems, such as Flickr, is not available, thus we cannot directly use (analogous term document) represent relevance tags. Many heuristic approaches have been proposed address this problem, among which well-known neighbor voting based most effective methods. The basic assumption these methods that...
Query recommendation plays a critical role in helping users' search. Most existing approaches on query aim to recommend relevant queries. However, the ultimate goal of is assist users reformulate queries so that they can accomplish their search task successfully and quickly. Only considering relevance apparently not directly toward this goal. In paper, we argue it more important with high utility, i.e., better satisfy information needs. For purpose, propose novel generative model, referred...
Using crowdsourcing for gathering labels can be beneficial supervised machine learning, if done in the right way. Crowdsourcing is more cost-effective and faster than employing experts labeling items needed as training examples. Unfortunately, crowd produced are not always of a comparable quality. Therefore, different methods could employed order to assure label One them redundancy, by one per item, from assessors. In this paper we introduce novel method aggregating multiple crowdsourced...
Image segmentation is a challenging task in the field of image processing and computer vision. In order to obtain an accurate performance, user interaction always used practical image-segmentation applications. However, good method should not rely on much prior information. this paper, efficient superpixel-guided interactive algorithm based graph theory proposed. algorithm, we first perform initial by using MeanShift then built taking pre-segmented regions (superpixels) as nodes, maximum...