TY - GEN
T1 - Towards Temporal Event Detection: A Dataset and Benchmarks
AU - Yang, Zhenguo
AU - Zhu, Haizhong
AU - Guo, Zhiwei
AU - Lin, Han
AU - Lin, Zehang
AU - Li, Qing
AU - Liu, Wenyin
N1 - Funding Information:
This work is supported by the National Natural Science Foundation of China (No.62076073), the Guangdong Basic and Applied Basic Research Foundation (No.2020A1515010616), Science and Technology Program of Guangzhou (No.202102020524), Guangdong Province Science and Technology Planning Project (No. 2019B010150002), Guangdong Innovative Research Team Program (No. 2014ZT05G157), and General Research Fund from the Hong Kong Research Grants Council (No. PolyU 11204919).
Publisher Copyright:
© 2022 IEEE.
PY - 2022/8
Y1 - 2022/8
N2 - In this paper, we present a new dataset with the target of advancing temporal real-world event detection from video-sharing social media. The collected temporal event dataset (TED) has certain characteristics. 1) Certainty of event labels that can be recognized as real-world happening. 2) Wide range of event categories covering public security, natural disasters, elections, sports and entertainment events, etc. 3) High overlap among event topics ensuring the difficulties in distinguishing the labels. 4) Multiple data modalities involving textual, acoustic, and visual information, etc. More specifically, two scenarios are defined based on the close or open domains, i.e., temporal event detection without/with new events, denoted as TED-W and TED-N, respectively. For comparisons, a few benchmarks are investigated on the two scenarios with the dataset.
AB - In this paper, we present a new dataset with the target of advancing temporal real-world event detection from video-sharing social media. The collected temporal event dataset (TED) has certain characteristics. 1) Certainty of event labels that can be recognized as real-world happening. 2) Wide range of event categories covering public security, natural disasters, elections, sports and entertainment events, etc. 3) High overlap among event topics ensuring the difficulties in distinguishing the labels. 4) Multiple data modalities involving textual, acoustic, and visual information, etc. More specifically, two scenarios are defined based on the close or open domains, i.e., temporal event detection without/with new events, denoted as TED-W and TED-N, respectively. For comparisons, a few benchmarks are investigated on the two scenarios with the dataset.
KW - Event detection
KW - social media
UR - http://www.scopus.com/inward/record.url?scp=85137661388&partnerID=8YFLogxK
U2 - 10.1109/ICME52920.2022.9859896
DO - 10.1109/ICME52920.2022.9859896
M3 - Conference article published in proceeding or book
AN - SCOPUS:85137661388
T3 - Proceedings - IEEE International Conference on Multimedia and Expo
SP - 1
EP - 6
BT - ICME 2022 - IEEE International Conference on Multimedia and Expo 2022, Proceedings
PB - IEEE Computer Society
T2 - 2022 IEEE International Conference on Multimedia and Expo, ICME 2022
Y2 - 18 July 2022 through 22 July 2022
ER -