Command Palette
Search for a command to run...
Yutong Feng; Jianwen Jiang; Ziyuan Huang; Zhiwu Qing; Xiang Wang; Shiwei Zhang; Mingqian Tang; Yue Gao
Abstract
This paper presents our solution to the AVA-Kinetics Crossover Challenge of ActivityNet workshop at CVPR 2021. Our solution utilizes multiple types of relation modeling methods for spatio-temporal action detection and adopts a training strategy to integrate multiple relation modeling in end-to-end training over the two large-scale video datasets. Learning with memory bank and finetuning for long-tailed distribution are also investigated to further improve the performance. In this paper, we detail the implementations of our solution and provide experiments results and corresponding discussions. We finally achieve 40.67 mAP on the test set of AVA-Kinetics.
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| spatio-temporal-action-localization-on-ava | RM (multi-scale, ir-CSN-152) | val mAP: 37.95 |
| spatio-temporal-action-localization-on-ava | RM (multi-scale, ensemble) | val mAP: 40.52 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.