The THUMOS challenge on action recognition for videos “in the wild”

• Published in: Computer vision and image understanding Vol. 155; pp. 1 - 23
• Main Authors: Idrees, Haroon, Zamir, Amir R., Jiang, Yu-Gang, Gorban, Alex, Laptev, Ivan, Sukthankar, Rahul, Shah, Mubarak
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.02.2017; Elsevier
• Subjects: Action detection; Action localization; Action recognition; Benchmark; Computer Science; Computer Vision and Pattern Recognition; Dataset; THUMOS; UCF101; Untrimmed videos; Action recognition; THUMOS; Dataset; UCF101; Action localization; Untrimmed videos; Benchmark; Action detection; Untrimmed Videos; Action Recognition; Action Localization; Action Detection

•THUMOS challenge was introduced in 2013 to serve as a benchmark for action recognition.•In this paper we describe the THUMOS benchmark in detail.•Give an overview of data collection and annotation procedures.•Present results of submissions to the THUMOS 2015 challenge and review the participating a...