UC Merced Submission to the ActivityNet Challenge 2016

Autor:	Zhu, Yi, Newsam, Shawn, Xu, Zaikun
Rok vydání:	2017
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Multimedia
Druh dokumentu:	Working Paper
Popis:	This notebook paper describes our system for the untrimmed classification task in the ActivityNet challenge 2016. We investigate multiple state-of-the-art approaches for action recognition in long, untrimmed videos. We exploit hand-crafted motion boundary histogram features as well feature activations from deep networks such as VGG16, GoogLeNet, and C3D. These features are separately fed to linear, one-versus-rest support vector machine classifiers to produce confidence scores for each action class. These predictions are then fused along with the softmax scores of the recent ultra-deep ResNet-101 using weighted averaging. Comment: Notebook paper for ActivityNet 2016 challenge, untrimmed video classification track
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1704.03503 Zobrazit plný text záznamu View this record from Arxiv