Abstract
This paper describes graph-based approaches to extract the visual elements from social media regarding the TRECVID Linking task story topics. We propose a sequential graph model and a fully connected graph.
Original language | English |
---|---|
Title of host publication | 2018 TREC Video Retrieval Evaluation, TRECVID 2018 |
Editors | G. Awad, A. A. Butt, K. Curtis, Y. Lee, J. G. Fiscus, A. Godil, D. Joy, A. Delgado, A. F. Smeaton, Y. Graham, W. Kraaij, G. Quenot, J. Magalhães, D. Semedo, S. G. Blasi |
Publisher | National Institute of Standards and Technology (NIST) |
Publication status | Published - 2020 |
Event | 2018 TREC Video Retrieval Evaluation, TRECVID 2018 - Gaithersburg, United States Duration: 13 Nov 2018 → 15 Nov 2018 |
Conference
Conference | 2018 TREC Video Retrieval Evaluation, TRECVID 2018 |
---|---|
Country/Territory | United States |
City | Gaithersburg |
Period | 13/11/18 → 15/11/18 |