2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) (2016)
San Francisco, CA, USA
Aug. 18, 2016 to Aug. 21, 2016
Hyunsouk Cho , POSTECH, 77 Cheongam-Ro, Nam-Gu, Pohang, Gyeongbuk, 36763, Republic of Korea
Seung-won Hwang , Yonsei University, 50 Yonsei-ro, Seodaemun-Gu, Seoul, 03722, Republic of Korea
Visual scene understanding has been one of the major goals of computer vision. However, existing work has focused on the object-level understanding, which limits the visual questions that can be answered. The goal of this paper is to invite collective efforts for entity-level understanding of images, by releasing ECO datasets and baselines for this task.
Visualization, Grounding, Context, Joining processes, Urban areas, Knowledge discovery, Global Positioning System
H. Cho and S. Hwang, "ECO: Entity-level captioning in context," 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), San Francisco, CA, USA, 2016, pp. 750-751.