High-level event recognition in unconstrained videos

202 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification (2015, background): “Video classification has been a longstanding research topic in multimedia and computer vision [16].”
DevNet: A Deep Event Network for multimedia event detection and evidence recounting (2015, background): “Most existing approaches focus on the temporal domain.”
Human Action Recognition in Unconstrained Videos by Explicit Motion Modeling (2015, background): “Readers are referred to[27], [28], [29] for comprehensive surveys of action recognition techniques, particularly those focusing on the design of recognition models.”
Video Event Detection by Inferring Temporal Instance Labels (2014, background): “A good survey of state-of-the-arts was made in [9].”
Blind late fusion in multimedia event retrieval (2016, methodology): “In 2011, the TRECVID Multimedia Event Detection (MED) task [20] defined a test bed for machine understanding of digital video, by creating a challenge to detect high level or complex events, defined as “long-term spatially and temporally dynamic object interactions” [4].”
A Review on Video-Based Human Activity Recognition (2013, background): “[96] focus on event recognition, rather than on human activity or crowd behavior.”