Concept-based Video Search with the PicSOM Multimedia Retrieval System
Abstract
In this report we describe the structure of the PicSOM multimedia retrieval system and elaborate on its automatic concept detection and video search subsystems.We evaluate several alternative techniques for implementing these two components of the PicSOM system in a comprehensive series of experiments employing the large-scale setups of the TRECVID video retrieval evaluation campaigns of 2008 and 2009.Based on the results of the experiments, we conclude that fusion-based shot-wise visual analysis together with N -gram temporal concept-wise post-processing make an efficient combination of techniques for automatic semantic concept detection from video material.It has previously been shown that semantic concepts are very beneficial for video search.Here we investigate the lexical and visualexample-based selection of concepts for search queries, concluding that both selection methods are successful in matching useful concepts.Finally, we show that the performance of the PicSOM system has improved since the TRECVID 2008 evaluation and now compares very well with the state-ofthe-art in concept detection and video search.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.