MDMMT: Multidomain Multimodal Transformer for Video Retrieval

Авторы: Dzabraev Maksim, Kalashnikov Maksim, Komkov Stepan, Petiushko Aleksandr
Сборник: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
Год издания: 2021
Место издания: Nashville, TN, USA
Первая страница: 3354
Последняя страница: 3363
Аннотация: We present a new state-of-the-art on the text to video retrieval task on MSRVTT and LSMDC benchmarks where our model outperforms all previous solutions by a large margin. Moreover, state-of-the-art results are achieved with a single model on two datasets without finetuning. This multidomain generalisation is achieved by a proper combination of different video caption datasets. We show that training on different datasets can improve test results of each other. Additionally we check intersection between many popular datasets and found that MSRVTT has a significant overlap between the test and the train parts, and the same situation is observed for ActivityNet.
Добавил в систему: Комков Степан Алексеевич

	ИСТИНА	Войти в систему Регистрация
	ИСТИНА ЦЭМИ РАН
	Главная Поиск Статистика О проекте Помощь

ИСТИНА