Filters








1,810 Hits in 2.1 sec

Video search re-ranking via multi-graph propagation

Jingjing Liu, Wei Lai, Xian-Sheng Hua, Yalou Huang, Shipeng Li
2007 Proceedings of the 15th international conference on Multimedia - MULTIMEDIA '07  
This paper 1 is concerned with the problem of multimodal fusion in video search.  ...  First, we employ an object-sensitive approach to query analysis to improve the baseline result of text-based video search.  ...  Therefore, in most multimodal fusion systems for video search, different fusion models are constructed for different query classes [4] [5] [6] [12] [13] , with the involvement of human knowledge.  ... 
doi:10.1145/1291233.1291279 dblp:conf/mm/LiuLHHL07 fatcat:sp47lkrnmzegzpcfxootw7whxm

CompositeMap

Bingjun Zhang, Qiaoliang Xiang, Ye Wang, Jialie Shen
2009 Proceedings of the seventeen ACM international conference on Multimedia - MM '09  
In addition, an incremental Locality Sensitive Hashing algorithm is developed to support more efficient search processes.  ...  This paper demonstrates a novel multimodal and adaptive music similarity measure (CompositeMap) with its application in a personalized multimodal music search system.  ...  As shown in Fig. 1 , it consists of the following components: CompositeMap which constructs music signatures of multiple music dimensions for both multimodal music queries and music items in the database  ... 
doi:10.1145/1631272.1631474 dblp:conf/mm/ZhangXWS09 fatcat:m6sl5qh2yrhh3eeaw6u5l47mje

Object-Sensitive Query Analysis for Video Search

Jingjing Liu, Xian-Sheng Hua, Shipeng Li
2007 2007 IEEE 9th Workshop on Multimedia Signal Processing  
This paper is concerned with the problem of Recently, many studies on video content analysis are improving the performance of text search baseline in video focused on the fusion of multimodalities for  ...  the video retrieval, specifically for the search tasks in TRECVID.  ...  f deoisearc, we is terms will be assigned with a higher weight in the search object-centric BM25 algorithm for video search, which is stage, as will be explained in the next section. incrementally add  ... 
doi:10.1109/mmsp.2007.4412891 dblp:conf/mmsp/LiuHL07 fatcat:hfssdwyspnewlmcgzeg6xmhp7e

Web video recommendation and long tail discovering

Xiao Wu, Yongdong Zhang, Junbo Guo, Jintao Li
2008 2008 IEEE International Conference on Multimedia and Expo  
In this paper, to facilitate user's browsing we propose relevant and exploratory recommendation algorithms utilizing multimodal similarity and contextual network to organize web videos of various topics  ...  Given countless web videos available online, one problem is how to help users find videos to their taste in an efficient way.  ...  Incremental construction of the network The first objective is utilizing explicit links on video pages (as in 5 th layer of Fig.1 ) to initialize the structure of network.  ... 
doi:10.1109/icme.2008.4607448 dblp:conf/icmcs/WuZGL08 fatcat:5dczcoe4zvdmzpoqxfzp2j47sq

A Survey on Multimodal Video Representation for Semantic Retrieval

J. Calic, N. Campbell, S. Dasiopoulou, Y. Kompatsiaris
2005 EUROCON 2005 - The International Conference on "Computer as a Tool"  
This paper surveys the approaches to video representation, focusing on semantic analysis for content-based indexing and retrieval.  ...  Furthermore, the concept of video multimodality is reevaluated and redefined in order to introduce modalities such as editing technique or affect to the audience.  ...  For more information please visit www.cost292.org.  ... 
doi:10.1109/eurcon.2005.1629877 fatcat:e25kjkfqx5fplht6rrnavhwy54

Concept-Oriented Indexing of Video Databases: Toward Semantic Sensitive Retrieval and Browsing

J. Fan, H. Luo, A.K. Elmagarmid
2004 IEEE Transactions on Image Processing  
; (c) Semantic video classification; (d) Concept-oriented video database indexing and access.  ...  Specifically, the framework includes: (1) A semantic-sensitive video content representation framework by using principal video shots to enhance the quality of features; (2) Semantic video concept interpretation  ...  Query Concept Evaluation for Query-By-Example After the query concepts are interpreted by the selected video clips, similarity search is performed through the underlying video database indexing structure  ... 
doi:10.1109/tip.2004.827232 pmid:15648863 fatcat:pevnxl3cfzb63fxyqbz3nssgti

Intent based Image Ranking for Web Search Reranking

Kshitija H. Ghadge, Sunil M. Sangve
2016 IOSR Journal of Computer Engineering  
New approach is presented for reranking of the images. While searching images on the web to increase the accuracy of the image search result Image search reranking is used.  ...  Image search reranking is an effective approach to refine the initial text-based image search result. In the reranking process,image visual contents are used to refine the initial text based result.  ...  Acknowledgment Authors would like to thank the researchers as well as publishers for making their resources available and teachers for their guidance.  ... 
doi:10.9790/0661-1804029096 fatcat:fjw64622k5atzhwdikx3el5gla

Optimizing video search reranking via minimum incremental information loss

Yuan Liu, Tao Mei, Xiuqing Wu, Xian-Sheng Hua
2008 Proceeding of the 1st ACM international conference on Multimedia information retrieval - MIR '08  
This paper is concerned with video search reranking -the task of reordering the initial ranked documents (video shots) to improve the search performance -in an optimization framework.  ...  We conducted comprehensive experiments on automatic video search task over TRECVID 2005-2007 benchmarks, and showed significant and consistent improvements over the text search baseline and other reranking  ...  For each query, video search systems are required to return a ranked list of up to 1, 000 shots.  ... 
doi:10.1145/1460096.1460139 dblp:conf/mir/LiuMWH08 fatcat:jqecownit5d2vgcv5rgyzv7xqa

Query-Document-Dependent Fusion: A Case Study of Multimodal Music Retrieval

Zhonghua Li, Bingjun Zhang, Yi Yu, Jialie Shen, Ye Wang
2013 IEEE transactions on multimedia  
We thus propose a general multimodal fusion framework, query-document-dependent fusion (QDDF), which derives the optimal fusion strategy for each query-document pair via intelligent content analysis of  ...  In recent years, multimodal fusion has emerged as a promising technology for effective multimedia retrieval.  ...  , such as meta search, and video/image retrieval.  ... 
doi:10.1109/tmm.2013.2280437 fatcat:7io6qmo4bre5vagrtaaap7lgcm

[Invited papers] Comparing Approaches to Interactive Lifelog Search at the Lifelog Search Challenge (LSC2018)

Cathal Gurrin, Klaus Schoeffmann, Hideo Joho, Andreas Leibetseder, Liting Zhou, Aaron Duane, Duc-Tien Dang-Nguyen, Michael Riegler, Luca Piras, Minh-Triet Tran, Jakub Lokoč, Wolfgang Hürst
2019 ITE Transactions on Media Technology and Applications  
The Lifelog Search Challenge (LSC) is an international content retrieval competition that evaluates search for personal lifelog data.  ...  We try to identify reasons why some systems performed better than others and provide an outlook as well as open issues for upcoming iterations of the challenge.  ...  Each task is represented by the temporal query, which is textual in nature and incrementally refined after every 30 seconds.  ... 
doi:10.3169/mta.7.46 fatcat:432mkxsdgbagjkx7z6cvdyr3hm

Text-to-image retrieval based on incremental association via multimodal hypernetworks

Jung-Woo Ha, Beom-Jin Lee, Byoung-Tak Zhang
2012 2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC)  
A text-to-image retrieval model requires an incremental learning method for its practical use since the multimodal data grow up dramatically.  ...  Using the HN incrementally learned by a sequential Bayesian sampling, in the multimodal hypernetwork-based text-to-image retrieval, a given text query is crossmodally expanded to the visual query and then  ...  [1] [2] and article or video searching [3] .  ... 
doi:10.1109/icsmc.2012.6378291 dblp:conf/smc/HaLZ12 fatcat:a6bxtihwnncarfinib6e3hgpne

Design of Multimodal Dissimilarity Spaces for Retrieval of Video Documents

E. Bruno, N. Moenne-Loccoz, S. Marchand-Maillet
2008 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This paper proposes a novel representation space for multimodal information, enabling fast and efficient retrieval of video data.  ...  The obtained results confirm the validity of the proposed approach for the representation and retrieval of multimodal information in a real-time framework.  ...  Abstract This paper proposes a novel representation space for multimodal information, enabling fast and efficient retrieval of video data.  ... 
doi:10.1109/tpami.2007.70801 pmid:18617712 fatcat:2f2egkuiwvecfc6awmj2b7wvaa

Cognitive learning and the multimodal memory game: Toward human-level machine learning

Byoung-Tak Zhang
2008 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)  
However, current machine learning techniques are far from sufficient for achieving human-level intelligence.  ...  We then propose a multimodal memory game as a research platform to study cognitive learning architectures and algorithms, where the machine learner and two human players question and answer about the scenes  ...  Image search application. Given a text query, the learner is to find an image that best matches with the text.  ... 
doi:10.1109/ijcnn.2008.4634261 dblp:conf/ijcnn/Zhang08 fatcat:k6ifhx3cbndk3nn7goqckaqupi

Handling temporal heterogeneous data for content-based management of large video collections

Nicolas Moënne-Loccoz, Bruno Janvier, Stéphane Marchand-Maillet, Eric Bruno
2006 Multimedia tools and applications  
Keywords Video document · MPEG-7 · TREC video track · Content-based multimedia retrieval · ViCoDE Motivations Video data processing has for long been of high interest for the development of compression  ...  However, unlike for other media, the management of a collection of video documents adds the problem of efficiently handling an overwhelming volume of temporal data.  ...  In this paper, we detail the framework we have constructed for the management of video document collections in the context of our research in video content retrieval.  ... 
doi:10.1007/s11042-006-0042-2 fatcat:oxv6cr6msvhz3hef2ldkofgipy

Retrieval of Multimedia Objects by Fusing Multiple Modalities

Ilias Gialampoukidis, Anastasia Moumtzidou, Theodora Tsikrika, Stefanos Vrochidis, Ioannis Kompatsiaris
2016 Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval - ICMR '16  
Searching for multimedia objects with heterogeneous modalities is critical for the construction of effective multimedia retrieval systems.  ...  Our framework integrates more than two modalities and high-level information, so as to retrieve multimedia objects enriched with high-level textual and visual concepts, in response to a multimodal query  ...  It should be noted that multimedia search systems are often interactive and user feedback is incorporated for progressively refining the query (e.g.  ... 
doi:10.1145/2911996.2912068 dblp:conf/mir/GialampoukidisM16 fatcat:uvpiiii4zbdfdpqnzz7724ivnu
« Previous Showing results 1 — 15 out of 1,810 results