Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019

2019/06/14 by Zhaofan Qiu, Dong Li, Qiu, Zhaofan +9
Computer Science · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition #Multimodal Machine Learning Applications #cs.CV

paper · pdf · doi:10.48550/arxiv.1906.07016

arXiv admin note: substantial text overlap with arXiv:1807.00686, arXiv:1710.08011

arxiv created 2019/06/14 · openalex publication_date 2019/06/14 · arxiv updated 2019/06/18 · openalex created_date 2019/06/27 · openalex updated_date 2026/07/28

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.

Citations

• YH Technologies at ActivityNet Challenge 2018
• ActivityNet Challenge 2017 Summary
• Show and tell: A neural image caption generator
• Semi-Supervised Classification with Graph Convolutional Networks
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• The Kinetics Human Action Video Dataset
• Jointly Localizing and Describing Events for Dense Video Captioning
• Deformable Convolutional Networks

Related

• YH Technologies at ActivityNet Challenge 2018
• Action recognition in real-world videos
• Three Branches: Detecting Actions With Richer Features
• The ActivityNet Large-Scale Activity Recognition Challenge 2018 Summary
• UC Merced Submission to the ActivityNet Challenge 2016