Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Page not in menu
This is a page not in th emain menu
Posts
publications
Vision-Based Obstacle Avoidance in Drone Navigation using Deep Reinforcement Learning
Published in 11th International Conference on Computer Engineering and Knowledge (ICCKE), 2021
Recommended citation: P. R. Gervi, A. Harati and S. K. Ghiasi-Shirazi, "Vision-Based Obstacle Avoidance in Drone Navigation using Deep Reinforcement Learning," 2021 11th International Conference on Computer Engineering and Knowledge (ICCKE), Mashhad, Iran, Islamic Republic of, 2021, pp. 363-368, doi: 10.1109/ICCKE54056.2021.9721451. https://ieeexplore.ieee.org/abstract/document/9721451
Vision language models are blind
Published in Proceedings of the Asian Conference on Computer Vision, 2024
Recommended citation: Rahmanzadehgervi, P., Bolton, L., Taesiri, M.R. and Nguyen, A.T., 2024. Vision language models are blind. In Proceedings of the Asian Conference on Computer Vision (pp. 18-34). https://link.springer.com/chapter/10.1007/978-981-96-0917-8_17
Improving Zero-Shot Object-Level Change Detection by Incorporating Visual Correspondence
Published in IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
Recommended citation: Nguyen, H.H., Rahmanzadehgervi, P., Mai, L. and Nguyen, A.T., 2025, February. Improving zero-shot object-level change detection by incorporating visual correspondence. In 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (pp. 8826-8833). IEEE. https://ieeexplore.ieee.org/abstract/document/10943983
TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models
Published in IEEE/CVF International Conference on Computer Vision (ICCV), 2025
Recommended citation: Rahmanzadehgervi, P., Nguyen, H.H., Liu, R., Mai, L. and Nguyen, A.T., 2024. TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models. arXiv preprint arXiv:2412.18675. https://arxiv.org/pdf/2412.18675