Imperial College London

DrKrystianMikolajczyk

Faculty of EngineeringDepartment of Electrical and Electronic Engineering

Reader in Computer Vision
 
 
 
//

Contact

 

+44 (0)20 7594 6220k.mikolajczyk

 
 
//

Location

 

Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Snoek:2008,
author = {Snoek, C and Sande, K and Rooij, O and Huurnink, B and Gemert, J and Uijlings, J and He, J and Li, X and Everts, I and Nedovic, V and Liempt, M and Balen, R and Yan, F and Tahir, M and Mikolajczyk, K and Kittler, J and Rijke, M and Geusebroek, J and Gevers, T and Worring, M and Smeulders, A and Koelma, D},
title = {The MediaMill TRECVID 2008 Semantic Video Search Engine},
year = {2008}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - In this paper we describe our TRECVID 2008 video retrieval experiments. The MediaMill team participated in three tasks: concept detection, automatic search, and interac- tive search. Rather than continuing to increase the number of concept detectors available for retrieval, our TRECVID 2008 experiments focus on increasing the robustness of a small set of detectors using a bag-of-words approach. To that end, our concept detection experiments emphasize in particular the role of visual sampling, the value of color in- variant features, the influence of codebook construction, and the effectiveness of kernel-based learning parameters. For retrieval, a robust but limited set of concept detectors ne- cessitates the need to rely on as many auxiliary information channels as possible. Therefore, our automatic search ex- periments focus on predicting which information channel to trust given a certain topic, leading to a novel framework for predictive video retrieval. To improve the video retrieval re- sults further, our interactive search experiments investigate the roles of visualizing preview results for a certain browse- dimension and active learning mechanisms that learn to solve complex search topics by analysis from user brows- ing behavior. The 2008 edition of the TRECVID bench- mark has been the most successful MediaMill participation to date, resulting in the top ranking for both concept de- tection and interactive search, and a runner-up ranking for automatic retrieval. Again a lot has been learned during this year’s TRECVID campaign; we highlight the most im- portant lessons at the end of this paper.
AU - Snoek,C
AU - Sande,K
AU - Rooij,O
AU - Huurnink,B
AU - Gemert,J
AU - Uijlings,J
AU - He,J
AU - Li,X
AU - Everts,I
AU - Nedovic,V
AU - Liempt,M
AU - Balen,R
AU - Yan,F
AU - Tahir,M
AU - Mikolajczyk,K
AU - Kittler,J
AU - Rijke,M
AU - Geusebroek,J
AU - Gevers,T
AU - Worring,M
AU - Smeulders,A
AU - Koelma,D
PY - 2008///
TI - The MediaMill TRECVID 2008 Semantic Video Search Engine
ER -