YH Technologies at ActivityNet Challenge 2018
arXiv:1807.00686
Abstract
This notebook paper presents an overview and comparative analysis of our systems designed for the following five tasks in ActivityNet Challenge 2018: temporal action proposals, temporal action localization, dense-captioning events in videos, trimmed action recognition, and spatio-temporal action localization.
arXiv commentRank 2 in both Temporal Activity Detection Task & Kinetics Task @ ActivityNet 2018. arXiv admin note: substantial text overlap with arXiv:1710.08011 by other authors
References in corpus (8)
- The Kinetics Human Action Video Dataset
- Deformable Convolutional Networks
- Towards Good Practices for Very Deep Two-Stream ConvNets
- Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks
- A Pursuit of Temporal Accuracy in General Activity Detection
- Temporal Convolution Based Action Proposal: Submission to ActivityNet 2017
- Jointly Localizing and Describing Events for Dense Video Captioning
- Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects