4,124 Hits in 6.5 sec

Learning from Relevance Feedback Sessions using a K-Nearest-Neighbor-Based Semantic Repository

Matthew Ro, Ran Chang, Xiaojun Qi
2007 Multimedia and Expo, 2007 IEEE International Conference on  
A semantic repository is constructed offline by applying the k-nearest-neighborbased relevance learning on both positive and negative session-term feedback.  ...  Index Terms -Content-based image retrieval, semantic repository, k-nearest-neighbor-based relevance learning  ...  To this end, we offline construct a semantic repository (SR) by applying the k-nearest-neighbor-based (k-nn) relevance learning on the session-term feedback, which contains the accumulated collection of  ... 
doi:10.1109/icme.2007.4285070 dblp:conf/icmcs/RoyalCQ07 fatcat:dmf6zfenp5fcplj5wc4ghpnphu

Generic Intent Representation in Web Search

Hongfei Zhang, Xia Song, Chenyan Xiong, Corby Rosset, Paul N. Bennett, Nick Craswell, Saurabh Tiwary
2019 Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR'19  
We also demonstrate that GEN Encoder alleviates the sparsity of tail search traffic and cuts down half of the unseen queries by using an efficient approximate nearest neighbor search to effectively identify  ...  Ablation studies reveal the crucial role of learning from implicit user feedback in representing user intent and the contributions of multi-task learning in representation generality.  ...  We also thank Guoqing Zheng and Susan Dumais for providing valuable feedback for this paper.  ... 
doi:10.1145/3331184.3331198 dblp:conf/sigir/ZhangSXRBCT19 fatcat:kfftn26uo5daxdv3mdzck4g6qm

Graph-Enhanced Multi-Task Learning of Multi-Level Transition Dynamics for Session-based Recommendation [article]

Chao Huang, Jiahui Chen, Lianghao Xia, Yong Xu, Peng Dai, Yanqing Chen, Liefeng Bo, Jiashu Zhao, Jimmy Xiangji Huang
2021 arXiv   pre-print
Towards this end, we first develop a position-aware attention mechanism to learn item transitional regularities within individual session.  ...  In this paper, we propose a multi-task learning framework with Multi-level Transition Dynamics (MTD), which enables the jointly learning of intra- and inter-session item transition dynamics in automatic  ...  Acknowledgments We thank the anonymous reviewers for their constructive feedback and comments.  ... 
arXiv:2110.03996v1 fatcat:qp5o3osmofgttnnas7r6b6lowu

A session-based song recommendation approach involving user characterization along the play power-law distribution [article]

Diego Sánchez-Moreno, Vivian F. López Batista, M. Dolores Muñoz Vicente, Ana B. Gil González, María N. Moreno-García
2020 arXiv   pre-print
In this work, the referred shortcomings are addressed by means of a recommendation approach based on the users' streaming sessions.  ...  This enormous availability means that recommendation mechanisms that help users to select the music they like need to be incorporated.  ...  Incorporating UPC to user-based CF In user-based collaborative filtering, active users receive recommendations of items liked by their nearest neighbors.  ... 
arXiv:2004.13007v1 fatcat:634zwha5bjavdlb45adzm2wqea

A personal news agent that talks, learns and explains

Daniel Billsus, Michael J. Pazzani
1999 Proceedings of the third annual conference on Autonomous Agents - AGENTS '99  
Based on voice feedback from the user, the system automatically adapts to the user's preferences and interests.  ...  Second, we investigate the use of "concept feedback", a novel form of user feedback that is based on our agent' s capability to construct explanations for the reasons that have led to a specific classification  ...  In order to classify a new, unlabeled instance, the algorithm compares it to all stored instances given some defined similarity measure, and determines the "nearest neighbor" or the k nearest neighbors  ... 
doi:10.1145/301136.301208 dblp:conf/agents/BillsusP99 fatcat:mos6tf3jknb53bli3h2nywa4hm

Manifold-Ranking-Based Keyword Propagation for Image Retrieval

Hanghang Tong, Jingrui He, Mingjing Li, Wei-Ying Ma, Hong-Jiang Zhang, Changshui Zhang
2006 EURASIP Journal on Advances in Signal Processing  
In relevance feedback, the feedback information can be naturally incorporated to refine the retrieval result by additional propagation processes.  ...  In order to speed up the convergence of the query concept, we adopt two active learning schemes to select images during relevance feedback.  ...  . ♦ The weighted graph in step 1 is constructed as: calculate the K nearest neighbors for each point; connect two points with an edge if they are neighbors.  ... 
doi:10.1155/asp/2006/79412 fatcat:ygiq42upzzh2bmtahqssox3ozu

A Radial Basis Function and Semantic Learning Space Based Composite Learning Approach to Image Retrieval

Konstantin Shkurko, Xiaojun Qi
2007 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07  
The proposed system combines the radial basis function (RBF) based lowlevel learning and the semantic learning space (SLS) based high-level learning to retrieve the desired images with fewer than 3 feedback  ...  User's relevance feedback is utilized for updating both low-level and high-level features of the query image.  ...  Both query reweighing and query shifting apply a nearest-neighbor sampling approach to refine query concept.  ... 
doi:10.1109/icassp.2007.366065 dblp:conf/icassp/ShkurkoQ07 fatcat:4pyxsnuicbcytiyx4x5su7iyfa

Quality of experience evaluation of voice communication: an affect-based approach

Abhishek Bhattacharya, Wanmin Wu, Zhenyu Yang
2012 Human-Centric Computing and Information Sciences  
Neighbor (kNN).  ...  Effective quality evaluation methodologies are important for system development and refinement, particularly by adopting user feedback based measurement.  ...  The presented views are those of authors and do not represent the position of NSF.  ... 
doi:10.1186/2192-1962-2-7 fatcat:7dfh4qc2gzc65ns2lgw42saj34

Location Regularization-Based POI Recommendation in Location-Based Social Networks

Lei Guo, Haoran Jiang, Xinhua Wang
2018 Information  
To exploit the geographical characteristics from a location perspective, we then constrain the ranking loss by using a regularization term derived from locations, and assume nearest neighboring POIs are  ...  In fact, in most location-based social networks, the user's negative preferences are not explicitly observable.  ...  Due to the fact that users always share similar preferences on nearest neighboring POIs, nearby places are inclined to be visited by similar users.  ... 
doi:10.3390/info9040085 fatcat:s2yel2kdsvf33blmwnxvmb7ehy

Estimation of Learning Affects Experienced by Learners: An Approach Using Relational Reasoning and Adaptive Mapping

Anil Audumbar Pise, Hima Vadapalli, Ian Sanders, Kalidoss Rajakani
2022 Wireless Communications and Mobile Computing  
Thus, it is crucial to integrate modules into an existing e-learning platform to effectively estimate learners' learning affect (LLA), provide appropriate feedback to both learner and lecturers, and potentially  ...  The presence of certain facial expressions has shown to indicate a learner's levels of concentration in both traditional and e-learning environments.  ...  It is recommended that future research in the e-learning system provide feedback to learners based on the estimated learning affect and also incorporate multi-model pattern analysis techniques such as  ... 
doi:10.1155/2022/8808283 fatcat:yhcire7h6nasvj4aghgxxcikly

Hidden annotation for image retrieval with long-term relevance feedback learning

Wei Jiang, Guihua Er, Qionghai Dai, Jinwei Gu
2005 Pattern Recognition  
We propose to incorporate long-term relevance feedback (LRF) with HA to increase both efficiency and retrieval accuracy of CBIR systems.  ...  HA with these concepts alleviates the burden of manual annotation and avoids the ambiguity problem of keyword-based annotation. (2) For each learned concept, semi-supervised learning is incorporated to  ...  Specifically, the K-nearest neighbor (KNN) classifier is adopted as the feature selection classifier. We empirically set MINERR = 0.01 and MAXDIM = 50.  ... 
doi:10.1016/j.patcog.2005.03.007 fatcat:fn6unad5ozgr7fqpwwtlnqfgb4

Data Mining Session-Based Patient Reported Outcomes (PROs) in a Mental Health Setting: Toward Data-Driven Clinical Decision Support and Personalized Treatment

Casey Bennett, Thomas Doub, April Bragg, Jason Luellen, Christina Van Regenmorter, Jennifer Lockman, Randall Reiserer
2011 2011 IEEE First International Conference on Healthcare Informatics, Imaging and Systems Biology  
The CDOI outcome measure - a patient-reported outcome (PRO) instrument utilizing direct client feedback - was implemented in a large, real-world behavioral healthcare setting in order to evaluate previous  ...  The results showed that the CDOI does contain significant capacity to predict outcome delta over time based on baseline and early change scores in a large, real-world clinical setting, as suggested in  ...  Of note, decay was set to true for MP Neural Networks, max_parents was set to 3 for Bayesian Network-K2, and number of nearest neighbors was set to 3 for K-Nearest Neighbors.  ... 
doi:10.1109/hisb.2011.20 dblp:conf/hisb/BennettDBLRLR11 fatcat:dreg2sue55dmxc4uby7icqgq4q

SDM: Sequential Deep Matching Model for Online Large-scale Recommender System [article]

Fuyu Lv, Taiwei Jin, Changlong Yu, Fei Sun, Quan Lin, Keping Yang, Wilfred Ng
2019 arXiv   pre-print
We propose to encode behavior sequences with two corresponding components: multi-head self-attention module to capture multiple types of interests and long-short term gated fusion module to incorporate  ...  Currently, item-based Collaborative Filtering (CF) methods are common matching approaches in industry. However, they are not effective to model dynamic and evolving preferences of users.  ...  The prediction is made as equivalent to search the nearest neighbors of users' vectors among all the items. Besides, Zhu et al.  ... 
arXiv:1909.00385v2 fatcat:dyrojo7dvzbqjfp2bmfxfwmplu

Click-boosted graph ranking for image retrieval

Jun Wu, Yu He, Xiaohong Qin, Na Zhao, Yingpeng Sang
2017 Computer Science and Information Systems  
To bridge this gap, one of the current trends is to leverage the click-through data associated with images to facilitate the graph-based image ranking.  ...  Concretely, the first one is a click predictor based on matrix factorization with visual regularization, in order to alleviate the sparseness of the click-through data.  ...  The authors would like to thank the anonymous reviewers for their constructive suggestions.  ... 
doi:10.2298/csis170212020j fatcat:ja4vi6bhqjg3fftoauvbrmg2ja

Socially-Driven Collective Path Planning for Robot Missions

Juan Camilo Gamboa Higuera, Anqi Xu, Florian Shkurti, Gregory Dudek
2012 2012 Ninth Conference on Computer and Robot Vision  
We address the problem of path planning for robot missions based on waypoints suggested by multiple human users.  ...  These users may be operating under distinct mission objectives and hence suggest different locations for the robot to visit.  ...  ACKNOWLEDGMENTS We would like to thank Professor David Avis for contributing to our NP-hardness proof, and also to all the participants of our user study.  ... 
doi:10.1109/crv.2012.62 dblp:conf/crv/HigueraXSD12 fatcat:ayx4miualfagrizcwdezvt6iki
« Previous Showing results 1 — 15 out of 4,124 results