I am an undergraduate B.Sc. student in Computer Engineering and a researcher affiliated with the Amirkabir University of Technology.
My research lies at the intersection of computer vision and deep learning. I am particularly interested in video understanding, image and video instance segmentation, and Vision-Language Models (VLMs) such as CLIP. I am passionate about rethinking standard paradigms and developing efficient training methods for complex vision tasks.
🎓 Education
Amirkabir University of Technology (Tehran Polytechnic)
B.Sc. in Computer Engineering
🔔 News
- [Jul 2026] Our paper QueenVIS has been uploaded to arXiv!
📝 Publications
QueenVIS: Rethinking Image-Only Training for Video Instance Segmentation via Query Enrichment
Arian Kheirandish, Fardin Ayar, Ehsan Javanmardi, Manabu Tsukada, Mahdi Javanmardi
arXiv preprint arXiv:2607.24598 (2026)