Numerical recipes in C (2nd ed.): the art of scientific computing
Numerical recipes in C (2nd ed.): the art of scientific computing
Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval
Decision Theory: An Introduction to Dynamic Programming and Sequential Decisions
Decision Theory: An Introduction to Dynamic Programming and Sequential Decisions
Probabilistic models of indexing and searching
SIGIR '80 Proceedings of the 3rd annual ACM conference on Research and development in information retrieval
The combination limit in multimedia retrieval
MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Large-Scale Concept Ontology for Multimedia
IEEE MultiMedia
Evaluation campaigns and TRECVid
MIR '06 Proceedings of the 8th ACM international workshop on Multimedia information retrieval
The challenge problem for automated detection of 101 semantic concepts in multimedia
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
A note on Platt's probabilistic outputs for support vector machines
Machine Learning
A review of text and image retrieval approaches for broadcast news video
Information Retrieval
Semantic concept-based query expansion and re-ranking for multimedia retrieval
Proceedings of the 15th international conference on Multimedia
Probabilistic models for combining diverse knowledge sources in multimedia retrieval
Probabilistic models for combining diverse knowledge sources in multimedia retrieval
(Un)Reliability of video concept detection
CIVR '08 Proceedings of the 2008 international conference on Content-based image and video retrieval
A probabilistic ranking framework using unobservable binary events for video search
CIVR '08 Proceedings of the 2008 international conference on Content-based image and video retrieval
Reusing annotation labor for concept selection
Proceedings of the ACM International Conference on Image and Video Retrieval
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
Using high-level semantic features in video retrieval
CIVR'06 Proceedings of the 5th international conference on Image and Video Retrieval
Can High-Level Concepts Fill the Semantic Gap in Video Retrieval? A Case Study With Broadcast News
IEEE Transactions on Multimedia
MultiFusion: A boosting approach for multimedia fusion
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Portfolio theory of multimedia fusion
Proceedings of the international conference on Multimedia
Probabilistic temporal multimedia data mining
ACM Transactions on Intelligent Systems and Technology (TIST)
Short communication: Towards a universal detector by mining concepts with small semantic gaps
Expert Systems with Applications: An International Journal
Using visual lifelogs to automatically characterize everyday activities
Information Sciences: an International Journal
Hi-index | 0.00 |
Today, semantic concept based video retrieval systems often show insufficient performance for real-life applications. Clearly, a big share of the reason is the lacking performance of the detectors of these concepts. While concept detectors are on their endeavor to improve, following important questions need to be addressed: "How good do detectors need to be to produce usable search systems?" and "How does the detector performance influence different concept combination methods?". We use Monte Carlo Simulations to provide answers to the above questions. The main contribution of this paper is a probabilistic model of detectors which outputs confidence scores to indicate the likelihood of a concept to occur. This score is also converted into a posterior probability and a binary classification. We investigate the influence of changes to the model's parameters on the performance of multiple concept combination methods. Current web search engines produce a mean average precision (MAP) of around 0.20. Our simulation reveals that the best performing video search method achieve this performance using detectors with 0.60 MAP and is therefore usable in real-life. Furthermore, perfect detection allows the best performing combination method to produce 0.39 search MAP in an artificial environment with Oracle settings. We also find that MAP is not necessarily a good evaluation measure for concept detectors since it is not always correlated with search performance.