Guest Editorial: Big Media Data: Understanding, Search, and Mining

BIG media data is a new research area, and has been attracting a lot of research interests in both industry and academia. This editorial, as the third part of this special issue, introduces two papers on video copy detection data and personalized travel sequence recommendation from social media. The first paper is “Partial Copy Detection in Videos: A Benchmark and An Evaluation of Popular Methods” by Y.-G. Jiang and J. Wang. The authors introduce a large-scale video copy database that consists of over 100,000 videos and includes more than 9,000 copy pairs found by manual annotation. Existing video copy detection techniques and the deep learning features are evaluated over the introduced database. The evaluation shows that all the existing techniques, including the deep learning features, are far from satisfactory in detecting complex real copies. In their paper “Personalized Travel Sequence Recommendation on Multi-Source Big Social Media,” S. Jiang, X. Qian, T. Mei, and Y. Fu present a personalized travel sequence recommendation approach by learning topical package model from bigmulti-source socialmedia: travelogues and community contributed photos. The approach can automatically mine user’s and routes’ travel topical preferences, and recommend not only POIs but also travel sequence. Experimental results on a collection of 7 million Flickr images uploaded by 7,387 users and 24,000 travelogues covering over 800 travel POIs in nine famous cities show the effectiveness of the proposed approach. In addition, this paper also introduce a newdataset withmore than 200 K photoswith heterogeneousmetadata in nine famous cities. Wewould like to extend our thanks to the authors and the reviewers for their efforts. We also thank the staff of TBD and especially Kathy Santa Maria and Leigh Ann Testa for their help and guidance throughout the publication process.