Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019
arXiv:1906.07016
Abstract
This notebook paper presents an overview and comparative analysis of our systems designed for the following three tasks in ActivityNet Challenge 2019: trimmed action recognition, dense-captioning events in videos, and spatio-temporal action localization.
arXiv commentarXiv admin note: substantial text overlap with arXiv:1807.00686, arXiv:1710.08011
References in corpus (6)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Semi-Supervised Classification with Graph Convolutional Networks
- The Kinetics Human Action Video Dataset
- Deformable Convolutional Networks
- Jointly Localizing and Describing Events for Dense Video Captioning
- Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects