1 code implementation • 12 Dec 2023 • Haoyu Tang, Han Jiang, Mingzhu Xu, Yupeng Hu, Jihua Zhu, Liqiang Nie
Thereafter, we design two (constant- and variable- speed) incremental instance learning strategies for easy-to-hard model training, thus ensuring the reliability of these video pseudolabels and further improving overall localization performance.