Interactive detection of incrementally learned concepts in images with ranking and semantic query interpretationSchutte, K., Bouma, H., Schavemaker, J., Daniele, L., Sappelli, M., Koot, G., Eendebak, P., Azzopardi, G., Spitters, M., De Boer, M., Kruithof, M. & Brandt, P., 9-Jul-2015, 2015 13th International Workshop on Content-Based Multimedia Indexing, CBMI 2015. IEEE Computer Society, 7153623. (Proceedings - International Workshop on Content-Based Multimedia Indexing; vol. 2015-July).
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review
The number of networked cameras is growing exponentially. Multiple applications in different domains result in an increasing need to search semantically over video sensor data. In this paper, we present the GOOSE demonstrator, which is a real-time general-purpose search engine that allows users to pose natural language queries to retrieve corresponding images. Top-down, this demonstrator interprets queries, which are presented as an intuitive graph to collect user feedback. Bottom-up, the system automatically recognizes and localizes concepts in images and it can incrementally learn novel concepts. A smart ranking combines both and allows effective retrieval of relevant images.
|Title of host publication||2015 13th International Workshop on Content-Based Multimedia Indexing, CBMI 2015|
|Publisher||IEEE Computer Society|
|Publication status||Published - 9-Jul-2015|
|Event||13th International Workshop on Content-Based Multimedia Indexing, CBMI 2015 - Prague, Czech Republic|
Duration: 10-Jun-2015 → 12-Jun-2015
|Name||Proceedings - International Workshop on Content-Based Multimedia Indexing|
|Conference||13th International Workshop on Content-Based Multimedia Indexing, CBMI 2015|
|Period||10/06/2015 → 12/06/2015|
13th International Workshop on Content-Based Multimedia Indexing, CBMI 2015
10/06/2015 → 12/06/2015Prague, Czech Republic
- concept detection, incremental learning, Semantic reasoning