1. Modeling visual context is key to augmenting object detection datasets;dvornik;Euro-pean Conference on Computer Vision,2018
2. Exceeding the limits of visual-linguistic multi-task learning;wolfe;arXiv preprint arXiv 2107 13054,2021
3. An image is worth 16x16 words: Transformers for image recognition at scale;dosovitskiy;Proceedings of the International Conference on Learning Representations (ICLR),2021
4. Person Transfer GAN to Bridge Domain Gap for Person Re-identification
5. Domain-adversarial training of neural networks;ganin;The Journal of Machine Learning Research,2016