Vision and Language Pre-Trained Models

Computer Vision • 26 methods

Involves models that adapt pre-training to the field of Vision-and-Language (V-L) learning and improve the performance on downstream tasks like visual question answering and visual captioning.

According to Du et al. (2022), information coming from the different modalities can be encoded in three ways: fusion encoder, dual encoder, and a combination of both.

References:

Method Year Papers
2021 319
2021 295
2019 26
2019 21
2020 17
2019 15
2021 8
2021 5
2022 5
2019 4
2020 4
2021 4
2021 3
2021 3
2022 3
2021 2
2021 2
2021 2
2020 1
2020 1
2019 1
2020 1
2021 1
2021 1
2000 1