Sloth Search System

In this paper, we present the Sloth Search System (SSS) for large scale video browsing. Our key concept is to apply object recognition and scene classification to generate keyword tags from video images. This indexing process is performed only on selected frames for faster processing. The keyword tags are used to retrieve videos from a text-based query. Additional feature signatures are also used to extract spatial and color information. These proposed signatures are stored as binary codes for a compact representation and for fast search. Such a representation allows users to search by drawing a sketch or a bounding box of a specific object.

[1]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Sergio Guadarrama,et al.  Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Heiko Schuldt,et al.  Enhanced Retrieval and Browsing in the IMOTION System , 2017, MMM.

[4]  Jakub Lokoc,et al.  Enhanced Signature-Based Video Browser , 2015, MMM.

[5]  Luca Rossetto,et al.  Interactive video search tools: a detailed analysis of the video browser showdown 2015 , 2016, Multimedia Tools and Applications.

[6]  Kai Uwe Barthel,et al.  Navigating a Graph of Scenes for Exploring Large Video Collections , 2016, MMM.

[7]  Bolei Zhou,et al.  Places: A 10 Million Image Database for Scene Recognition , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.