CDVA
The purpose of this document is to provide descriptions of three core experiments on MPEG Compact Descriptors for Video Analysis (CDVA) (see N15339, “Call for Proposals for Compact Descriptors for Video Analysis (CDVA) - Search and Retrieval”, June 2015, Warsaw (PL)) based on the proposals submitted at 114th MPEG meeting and the submission to the 115th meeting.
CDVA defines video descriptors for search and retrieval applications, specifically for visual content matching in video. Visual content matching includes matching of views of large and small objects and scenes, that is robust to partial occlusions as well as changes in view point, camera parameters, and lighting conditions.
CDVA defines video descriptors for search and retrieval applications, specifically for visual content matching in video. Visual content matching includes matching of views of large and small objects and scenes, that is robust to partial occlusions as well as changes in view point, camera parameters, and lighting conditions.
At its 112th meeting, MPEG issued a call for proposals for Compact Descriptors for Video Analysis (CDVA) - Search and Retrieval. In response to the CfP, three full proposals and one partial proposal (addressing trajectory coding) were received. At the 114th meeting, these proposals were evaluated and analyzed. This document provides a summary of the full proposals received and provides the preliminary evaluation results obtained at the meeting.
This document describes data requirements for CDVS.