Md Mohaiminul Islam

6

Papers

91

Total Citations

Papers (6)

Video ReCap: Recursive Captioning of Hour-Long Videos

ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos

BIMBA: Selective-Scan Compression for Long-Range Video Question Answering

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

Efficient Movie Scene Detection Using State-Space Transformers

Long Movie Clip Classification with State-Space Video Models