General engine for indexing events

Sangmin Oh, Ilseo Kim, Megha Pandey, Amitha Perera, Kevin Cannons, Hossein Hajimirsadeghi, Arash Vahdat, Greg Mori, Ben Miller, Scott McCloskey, You Chi Cheng, Zhen Huang, Chin Hui Lee, Chenliang Xu, Rohit Kumar, Wei Chen, Jason Corso, Fei Fei Li, Daphne Koller, Vignesh RamanathanKevin Tang, Armand Joulin, Alexandre Alahi

Research output: Contribution to conferencePaperpeer-review

Abstract

TRECVID community is making impressive progress on solving multimedia event detection. 100 Ex works well for many event types. 10 Ex is the next real challenge, which is gradually being addressed. Search by Semantics (0Ex) is still challenging Our attempts to improve 0Ex include: Bottom-Up Concepts. Score Calibration Our MER incorporated. Feature-to-text translation. Discriminative Image selection. Fusion of results across multiple base classifier is the next step.

Original languageEnglish
StatePublished - 2013
Event2013 TREC Video Retrieval Evaluation, TRECVID 2013 - Gaithersburg, United States
Duration: 20 Nov 201322 Nov 2013

Conference

Conference2013 TREC Video Retrieval Evaluation, TRECVID 2013
Country/TerritoryUnited States
CityGaithersburg
Period20/11/1322/11/13

Fingerprint

Dive into the research topics of 'General engine for indexing events'. Together they form a unique fingerprint.

Cite this