The 2014 Placing Task: Multimodal Location Estimation
The Placing Task captures the challenge of estimating geographical coordinates of multimedia items, such as images and videos, based on massive amounts of geo-tagged training data. The purpose of this challenge is to further the area of multimedia retrieval. For example, the developed methods could help a rescue team to infer where exactly a family disappeared in a remote area by discovering the locations shown in videos uploaded to a social network before they lost contact.
The Mediaeval Placing Task 2014 consists of the following:
1. General placing: participants are asked to explore textual, social, visual and/or acoustic cues, and precisely estimate the location of a given Flickr media item.
2. Placeability (optional): participants are asked to classify a media item as being objectively placeable in the world.
The task is of interest to researchers in the area of geographic multimedia information retrieval, social media and media analysis.
The training data consists of 5 million geotagged photos and 25,000 geotagged videos, whereas the test set consists of 500,000 photos and 10,000 videos. As in 2013, the training and the test set are mutually exclusive with respect to the users who contributed the media (i.e., the users in the training set will be different from the users in the test set). All photos and videos used in the benchmark have been taken from the YFCC100M dataset.
Ground truth and evaluation
The geo-coordinates associated with the Flickr/YouTube video will be used as the ground truth. Since these do not always serve to precisely pinpoint the location of the video, we will evaluate at each of a series of widening circles: 10m, 100m, 1km 10km 100km 1,000km 5,000km. Note: We are encouraging participants to be more accurate than in previous years by including the smaller error radius ranges.
 Cao, L., Yu, J., Luo, J., Huang, T. Enhancing Semantic and Geographic Annotation of Web Images Via Logistic Canonical Correlation Regression. In Proceedings of ACM International Conference on Multimedia. ACM, Beijing, China, 2009, 125-134.
 Choi, J., Lei, H., Ekambaram, V., Kelm, P., Gottlieb, L., Sikora, T., Ramchandran, K., Friedland, G. Human vs. Machine: Establishing a Human Baseline for Multimodal Location Estimation. In Proceedings of ACM International Conference on Multimedia. ACM, Barcelona, Spain, USA, 2013, 866-867.
 Hays, J., Efros, A. A. IM2GPS: Estimating Geographic Information from a Single Image. In Proceedings of CVPR Computer Vision and Pattern Recognition Conference. Anchorage, Alaska, USA, 2008.
 Kelm, P., Schmiedeke, S., Choi, J., Friedland, G., Ekambaram, V., Ramchandran, K., Sikora, T. A Novel Fusion Method for Integrating Multiple Modalities and Knowledge for Multimodal Location Estimation. In Proceedings of ACM Multimedia Workshop on Geotagging and Its Applications in Multimedia. ACM, Barcelona, Spain, 2013, 7-12.
 Larson, M., Soleymani, M., Serdyukov, P., Rudinac, S., Wartena, C., Murdock, V., Friedland, G., Ordelman, R., Jones, G. J.F. Automatic Tagging and Geotagging in Video Collections and Communities. In Proceedings of ACM ICMR International Conference on Multimedia Retrieval. ACM, Trento, Italy, 2011, 51-54.
 Luo, J., Joshi, D., Yu, J., Gallagher, A. Geotagging in Multimedia and Computer Vision - A Survey. In Springer Multimedia Tools and Applications, Special Issue: Survey Papers in Multimedia by World Experts, 51(1), 2011, 187–211.
 Penatti, O. A.B., Li, L. T., Almeida, J., Torres, R. da S. A Visual Approach for Video Geocoding using Bag-of-Scenes, In Proceedings of ACM ICMR International Conference on Multimedia Retrieval. ACM, Hong Kong, 2012.
 Trevisiol, M., Jégou, H., Delhumeau, J., Gravier, G. Retrieving Geo-location of Videos with a Divide & Conquer Hierarchical Multimodal Approach. In Proceedings of ACM ICMR International Conference on Multimedia Retrieval. ACM, Dallas, USA, 2013.
 Yin, Z., Cao, L., Han, J., Zhai, C., Huang, T. Geographical Topic Discovery and Comparison. In Proceedings of ACM WWW International Conference on World Wide Web. ACM, Hyderabad, India, 2011, 247-256.
Bart Thomee, Yahoo Labs, San Francisco, USA
Jaeyoung Choi and Gerald Friedland, ICSI and UC Berkeley, USA
Liangliang Cao, IBM TJ Watson, USA
21 June: Data release (note that this is an updated release date)
5 September: Run submission due
19 September: Results returned
28 September: Working notes paper deadline