The Front-end of the presented video search system based on video data services. In the top panel, users can select dataset, feature representation model and submit custom text for question answering tasks. The left panel allows users to run text queries or use external image to initialize the search. Bayes update button is available for selected images as well. Bellow the button, statistics of detected class labels are presented for the current result set. Users can click on each class label to set it as filter.
This paper presents a tool relying on data service architecture, where technical details of all VBS datasets are completely hidden behind an abstract stateless data layer. The data services allow independent development of interactive search interfaces and refinement techniques, which is demonstrated by a smart front-end component. The component supports common search features and allows users to exploit content-based statistics for effective filtering. We believe that video data services might be a valuable addition to the open-source VBS toolkit, especially when available for the competition on a shared server with all VBS datasets, extracted features, and meta-data behind.
@inproceedings{Lokoc2024PraKToolInteractive, abstract = {This paper presents a tool relying on data service architecture, where technical details of all VBS datasets are completely hidden behind an abstract stateless data layer. The data services allow independent development of interactive search interfaces and refinement techniques, which is demonstrated by a smart front-end component. The component supports common search features and allows users to exploit content-based statistics for effective filtering. We believe that video data services might be a valuable addition to the open-source VBS toolkit, especially when available for the competition on a shared server with all VBS datasets, extracted features, and meta-data behind.}, address = {Cham}, author = {J. Lokoč, Z. Vopálková, M. Stroh, R. Buchmueller, U. Schlegel}, booktitle = {MultiMedia Modeling}, editor = {Rudinac, Stevan and Hanjalic, Alan and Liem, Cynthia and Worring, Marcel and Jónsson, Björn Þór and Liu, Bei and Yamakata, Yoko}, isbn = {978-3-031-53302-0}, pages = {340--346}, publisher = {Springer Nature Switzerland}, title = {PraK Tool: An Interactive Search Tool Based on Video Data Services}, year = {2024} }