1

BIMBA: Selective-Scan Compression for Long-Range Video Question Answering
Mohaiminul Islam, Tushar Nagarajan, Huiyu Wang, Gedas Bertasius, Lorenzo Torresani
Cite ArXiv Website Code HuggingFace Demo
BIMBA: Selective-Scan Compression for Long-Range Video Question Answering
ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos
Tanveer Hannan, Mohaiminul Islam, Jindong Gu, Thomas Seidl, Gedas Bertasius
Cite ArXiv Code
ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos
Video ReCap: Recursive Captioning of Hour-Long Videos
Mohaiminul Islam, Ngan Ho, Xitong Yang, Tushar Nagarajan, Lorenzo Torresani, Gedas Bertasius
Cite ArXiv Website Code Dataset HuggingFace
Video ReCap: Recursive Captioning of Hour-Long Videos
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
Kristen Grauman, Mohaiminul Islam, et al
Cite ArXiv Website Blog Video
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos
Mohaiminul Islam, Tushar Nagarajan, Huiyu Wang, Fu-Jen Chu, Kris Kitani, Gedas Bertasius, Xitong Yang
Cite ArXiv Website Video
RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos
Tanveer Hannan, Mohaiminul Islam, Thomas Seidl, Gedas Bertasius
Cite ArXiv Code
RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos
A Simple LLM Framework for Long-Range Video Question-Answering
Ce Zhang, Taixi Lu, Mohaiminul Islam, Ziyang Wang, Shoubin Yu, Mohit Bansal, Gedas Bertasius
Cite ArXiv Code
A Simple LLM Framework for Long-Range Video Question-Answering
Efficient Movie Scene Detection using State-Space Transformers
Mohaiminul Islam, Mahmudul Hasan, Kishan Shamsundar Athrey, Tony Braskich, Gedas Bertasius
Cite ArXiv Code
Efficient Movie Scene Detection using State-Space Transformers
Long Movie Clip Classification with State-Space Video Models
Mohaiminul Islam, Gedas Bertasius
Cite ArXiv Code
Long Movie Clip Classification with State-Space Video Models
COVID-DenseNet: A Deep Learning Architecture to Detect COVID-19 from Chest Radiology Images
Mohaiminul Islam, Tanveer Hannan, Laboni Sarker, Zakaria Ahmed
Cite ArXiv Code
COVID-DenseNet: A Deep Learning Architecture to Detect COVID-19 from Chest Radiology Images