publication . Other literature type . Conference object . 2015

ActivityNet: A large-scale video benchmark for human activity understanding

Victor Escorcia; Juan Carlos Niebles; Fabian Caba Heilbron; Bernard Ghanem;
Open Access
  • Published: 01 Jun 2015
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Abstract
In spite of many dataset efforts for human action recognition, current computer vision algorithms are still severely limited in terms of the variability and complexity of the actions that they can recognize. This is in part due to the simplicity of current benchmarks, which mostly focus on simple actions and movements occurring on manually trimmed videos. In this paper we introduce ActivityNet, a new large-scale video benchmark for human activity understanding. Our benchmark aims at covering a wide range of complex human activities that are of interest to people in their daily living. In its current version, ActivityNet provides samples from 203 activity classes...
Subjects
free text keywords: Benchmark (computing), Contextual image classification, Action recognition, Artificial intelligence, business.industry, business, Computer vision algorithms, Activity detection, Machine learning, computer.software_genre, computer, Object detection, Gesture recognition, Computer science, Semantics
Any information missing or wrong?Report an Issue