Filters








39,411 Hits in 10.4 sec

Effects of Usage-Based Feedback on Video Retrieval

David Vallet, Frank Hopfgartner, Joemon M. Jose, Pablo Castells
2011 ACM Transactions on Information Systems  
We propose a graph-based model for all types of implicit and explicit feedback, in which the relevant usage information is represented.  ...  An evaluation strategy is proposed based on simulated user actions, which enables the evaluation of our recommendation strategies over a usage information pool obtained from 24 users performing four different  ...  to evaluate each recommendation strategy.  ... 
doi:10.1145/1961209.1961214 fatcat:lshdfvddxvac7mjcnymjsby7dq

Adaptive multiple feedback strategies for interactive video search

Huanbo Luan, Yantao Zheng, Shi-Yong Neo, Yongdong Zhang, Shouxun Lin, Tat-Seng Chua
2008 Proceedings of the 2008 international conference on Content-based image and video retrieval - CIVR '08  
In this paper, we propose adaptive multiple feedback strategies for interactive video retrieval.  ...  To cater to the large number of novice users (non-expert users), an adaptive option is built-in to learn the expert user behavior so as to provide recommendations on the next feedback strategy, leading  ...  In general, it is not enough to utilize only one single feedback technique to tackle different types of queries and for different video domains.  ... 
doi:10.1145/1386352.1386411 dblp:conf/civr/LuanZNZLC08 fatcat:vs45pml57nc7lk2aufxpywcbyu

Search trails using user feedback to improve video search

Frank Hopfgartner, David Vallet, Martin Halvey, Joemon Jose
2008 Proceeding of the 16th ACM international conference on Multimedia - MM '08  
This feedback is the basis for providing recommendations to users of our video retrieval system.  ...  We use community based feedback mined from the interactions of previous users of our video search system to aid users in their search tasks.  ...  In particular, these techniques could be extended with other types of querying, e.g. query by example, to provide even more improved query results for users.  ... 
doi:10.1145/1459359.1459405 dblp:conf/mm/HopfgartnerVHJ08 fatcat:qzc64vui5fa33flxt2hw5ssi3y

Adaptive website recommendations with AWESOME

Andreas Thor, Nick Golovin, Erhard Rahm
2005 The VLDB journal  
In particular, we investigate two-step selection approaches that first determine the most promising recommenders and then apply their recommendations for the current situation.  ...  Furthermore, we propose and evaluate several rule-based schemes for dynamically selecting the most promising recommendations.  ...  Acknowledgements We thank Robert Lokaiczyk for his help with the implementation.  ... 
doi:10.1007/s00778-005-0160-x fatcat:u4eaiirmfvautow2ug3sncsobm

Community based feedback techniques to improve video search

David Vallet, Frank Hopfgartner, Martin Halvey, Joemon M. Jose
2008 Signal, Image and Video Processing  
We use a graph based model based on implicit feedback mined from the interactions of previous users of our video search system to provide recommendations to aid users in their search tasks.  ...  In particular we wish to make the challenging task of video search much easier for users.  ...  As part of this work a number of different weighting schemes were evaluated in order to determine which weighting scheme was the most effective for implicit feedback for interactive video search.  ... 
doi:10.1007/s11760-008-0087-y fatcat:ydlqun6mjvhdrebeetmijwglku

Preference based feedback for collaborative image retrieval

Martin Halvey
2011 Proceedings of the 3rd international workshop on Collaborative information retrieval - CIR '11  
We describe initial implementations of this approach and some evaluations of this paradigm for image search.  ...  There are a many of image related search tasks that can be collaborative in nature and require input from more than one person e.g. organisation of photographs or videos from multiple views, students working  ...  In an attempt to address this issue the comparison-based recommendation work of McGinty and Smyth [12] propose a number of query revision strategies that are designed to revise the current query/recommendation  ... 
doi:10.1145/2064075.2064082 fatcat:4bq7ilukvffndompa724ob4y5q

EGO: A personalized multimedia management and retrieval tool

Jana Urban, Joemon M. Jose
2006 International Journal of Intelligent Systems  
The recommendation algorithm is described, which is based on relevance feedback techniques.  ...  In this article, we sketch the development of CBIR interfaces and introduce our view on how to solve some of the problems these interfaces present.  ...  It allows for different views of the results based on the features supported.  ... 
doi:10.1002/int.20157 fatcat:3delftfrufhsjkdszfmbfuyw64

A Large-Scale Rich Context Query and Recommendation Dataset in Online Knowledge-Sharing [article]

Bin Hao, Min Zhang, Weizhi Ma, Shaoyun Shi, Xinxing Yu, Houzhi Shan, Yiqun Liu, Shaoping Ma
2021 arXiv   pre-print
To the best of our knowledge, this is the largest real-world interaction dataset for personalized recommendation.  ...  Multiple experiments show the dataset can be used to evaluate algorithms in general top-N recommendation, sequential recommendation, and context-aware recommendation.  ...  content and user interactions. • CC-CC [26] : This method uses the adaptive "Feature Sampling" strategy for the recommendation.  ... 
arXiv:2106.06467v1 fatcat:km3z66zbcrcmhppc4yjfuihiha

Which to View

Beidou Wang, Martin Ester, Jiajun Bu, Yu Zhu, Ziyu Guan, Deng Cai
2016 Proceedings of the 25th International Conference on World Wide Web - WWW '16  
In this paper, we propose the first framework for broadcast email prioritization by designing a novel active learning model that considers the collaborative filtering, implicit feedback and time sensitive  ...  Despite lots of previous effort on this topic, broadcast email, an important type of email, is overlooked in previous literature.  ...  Since different active learning algorithms query different sets of users for feedback, to make fair comparisons, the performance is evaluated on the same set of users, which is the intersection of the  ... 
doi:10.1145/2872427.2883049 dblp:conf/www/WangEBZGC16 fatcat:u6wkij7vrbfqde4viuqoocl4a4

Improving recommender systems with adaptive conversational strategies

Tariq Mahmood, Francesco Ricci
2009 Proceedings of the 20th ACM conference on Hypertext and hypermedia - HT '09  
This strategy is optimal for the given model of the interaction and it is adapted to the users' behaviors.  ...  We show that the optimal strategy is different from the fixed one, and supports more effective and efficient interaction sessions.  ...  Users specify their preferences by providing during the interaction various types of information or feedbacks, which are used to update the user model, and hence inform future recommendations.  ... 
doi:10.1145/1557914.1557930 dblp:conf/ht/MahmoodR09 fatcat:exxkiok2xne2zcs73ngoio3hli

A Unified Relevance Feedback Framework for Web Image Retrieval

En Cheng, Feng Jing, Lei Zhang
2009 IEEE Transactions on Image Processing  
To seamlessly combine textual feature-based RF and visual feature-based RF, a query concept-dependent fusion strategy is automatically learned.  ...  In this paper, we propose a unified relevance feedback framework for Web image retrieval. Our framework shows advantage over traditional RF mechanisms in the following three aspects.  ...  This property of the parameter results in a query concept-dependent fusion strategy for relevance feedback in both textual and visual space. III.  ... 
doi:10.1109/tip.2009.2017128 pmid:19362910 fatcat:ygpc546pj5ftnbrgzsuxcillga

An implicit feedback approach for interactive information retrieval

Ryen W. White, Joemon M. Jose, Ian Ruthven
2006 Information Processing & Management  
One reason for this is that they may have difficulty devising queries to express their information needs.  ...  The approach chooses terms to better represent information needs by monitoring searcher interaction with different representations of top-ranked documents.  ...  the subject groups in the type and amount of interaction).  ... 
doi:10.1016/j.ipm.2004.08.010 fatcat:4l7q3ycjqbfzzakfzzg4evzsw4

Toward the exploitation of social access patterns for recommendation

Jill Freyne, Rosta Farzan, Maurice Coyle
2007 Proceedings of the 2007 ACM conference on Recommender systems - RecSys '07  
ASSIST exploits multiple forms of social implicit feedback in order to generate well-informed user recommendations in the online information retrieval domain.  ...  The online information retrieval process across different repositories shares similarities with content access facilities and user behaviors even when containing inherently different content types.  ...  In this work we will refer to examples using a multimedia platform for serving up videos, YouTube (www.youtube.com) to illustrate how our recommendation strategies could be implemented in an alternative  ... 
doi:10.1145/1297231.1297266 dblp:conf/recsys/FreyneFC07 fatcat:36vqyaac6zeatojkhhxvwt5mru

Advances and Challenges in Conversational Recommender Systems: A Survey [article]

Chongming Gao, Wenqiang Lei, Xiangnan He, Maarten de Rijke, Tat-Seng Chua
2021 arXiv   pre-print
Existing models, technologies, and evaluation methods for CRSs are far from mature. In this paper, we provide a systematic review of the techniques used in current CRSs.  ...  Recommender systems exploit interaction history to estimate user preference, having been heavily used in a wide range of industry applications.  ...  an explicit strategy to deal with different feedback.  ... 
arXiv:2101.09459v6 fatcat:j7djzhrv6fazpogmnj7r4e4f2y

TRECVID 2009 of MCG-ICT-CAS

Juan Cao, Yong-Dong Zhang, Bai-Lan Feng, Lei Bao, Ling Pang, Jin-Tao Li, Ke Gao, Xiao Wu, Hon-Ttao Xie, Wei Zhang, Zhen-Dong Mao
2009 TREC Video Retrieval Evaluation  
This paper describes the highlights of our interactive search system VideoMap for TRECVID 2009.  ...  Meanwhile, the system has powerful multiple modality feedback strategies, including the visual-based feedback, concept-based feedback and community-based feedback.  ...  Figure 8 The performance for 24 topics of automatic multi-strategies feedback (run1) Experiments and Analysis We submitted 10 type A runs for interactive search task.  ... 
dblp:conf/trecvid/CaoZFBPLGWXZM09 fatcat:dupkc3rutvgcpasjzpxwcfqui4
« Previous Showing results 1 — 15 out of 39,411 results