Publications

2026

1. ECCV
   
   

   WildProp: Visual Estimation of Wildlife Body Proportions at Scale

   Mustafa Chasmai, Aaron Sun, and Subhransu Maji

   In European conference on computer vision 2026

   Bib HTML Code

   @inproceedings{chasmai2026wildprop,
     title = {WildProp: Visual Estimation of Wildlife Body Proportions at Scale},
     author = {Chasmai, Mustafa and Sun, Aaron and Maji, Subhransu},
     booktitle = {European conference on computer vision},
     year = {2026},
     organization = {Springer},
   }

2. ICML
   
   

   Bioacoustic Geolocation: Species Sounds as Geographic Signals

   Mustafa Chasmai, Wuao Liu, Subhransu Maji, and Grant Van Horn

   In The Forty-third International Conference on Machine Learning 2026

   arXiv Bib HTML Code

   @inproceedings{chasmai2026bioacoustic,
     title = {Bioacoustic Geolocation: Species Sounds as Geographic Signals},
     author = {Chasmai, Mustafa and Liu, Wuao and Maji, Subhransu and Van Horn, Grant},
     booktitle = {The Forty-third International Conference on Machine Learning},
     year = {2026},
   }

3. ICML
   
   

   MetaPerch: Learning from metadata for bioacoustics foundation models

   Mustafa Chasmai, Vincent Dumoulin, and Jenny Hamer

   In The Forty-third International Conference on Machine Learning 2026

   Bib HTML Code

   @inproceedings{chasmai2026metaperch,
     title = {MetaPerch: Learning from metadata for bioacoustics foundation models},
     author = {Chasmai, Mustafa and Dumoulin, Vincent and Hamer, Jenny},
     booktitle = {The Forty-third International Conference on Machine Learning},
     year = {2026},
   }

4. CVPR
   
   

   RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs

   Logan Lawrence, Oindrila Saha, Rangel Daroya, Mustafa Chasmai, Wuao Liu, and 6 more authors

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026

   arXiv Bib Code

   @inproceedings{lawrence2026realbirdid,
     title = {RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs},
     author = {Lawrence, Logan and Saha, Oindrila and Daroya, Rangel and Chasmai, Mustafa and Liu, Wuao and Hamilton, Max and Sun, Aaron and Jeong, Seoyun and Delattre, Fabien and Maji, Subhransu and others},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     pages = {2445--2456},
     year = {2026},
   }

5. CVPR-W
   
   

   Masked Autoencoders with Limited Data: Does It Work? A Fine-Grained Bioacoustics Case Study

   Wuao Liu, Mustafa Chasmai, Subhransu Maji, and Grant Van Horn

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026

   arXiv Bib

   @inproceedings{liu2026masked,
     author = {Liu, Wuao and Chasmai, Mustafa and Maji, Subhransu and Van Horn, Grant},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     pages = {3131--3140},
     year = {2026},
   }

2025

1. CVPR-W
   
   

   Moment Sampling in Video LLMs for Long-Form Video QA

   Mustafa Chasmai, Gauri Jagatap, Gouthaman KV, Grant Van Horn, Subhransu Maji, and 1 more author

   CVPR Workshop on Video Large Language Models 2025

   arXiv Bib

   @article{chasmai2025moment,
     title = {Moment Sampling in Video LLMs for Long-Form Video QA},
     author = {Chasmai, Mustafa and Jagatap, Gauri and KV, Gouthaman and Van Horn, Grant and Maji, Subhransu and Fanelli, Andrea},
     journal = {CVPR Workshop on Video Large Language Models},
     year = {2025},
   }

2024

1. NeurIPS
   
   

   The iNaturalist Sounds Dataset

   Mustafa Chasmai, Alexander Shepard, Subhransu Maji, and Grant Van Horn

   In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track 2024

   arXiv Bib HTML Code

   @inproceedings{chasmai2024inaturalist,
     title = {The iNaturalist Sounds Dataset},
     author = {Chasmai, Mustafa and Shepard, Alexander and Maji, Subhransu and Van Horn, Grant},
     booktitle = {The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
     year = {2024},
   }

2023

1. ICME
   
   

   Weakly Supervised Few-Shot and Zero-Shot Semantic Segmentation with Mean Instance Aware Prompt Learning

   Prashant Pandey*, Mustafa Chasmai*, Monish Natarajan, and Brejesh Lall

   In 2023 IEEE International Conference on Multimedia and Expo (ICME) 2023

   Bib HTML Code

   @inproceedings{pandey2023weakly,
     title = {Weakly Supervised Few-Shot and Zero-Shot Semantic Segmentation with Mean Instance Aware Prompt Learning},
     author = {Pandey*, Prashant and Chasmai*, Mustafa and Natarajan, Monish and Lall, Brejesh},
     booktitle = {2023 IEEE International Conference on Multimedia and Expo (ICME)},
     pages = {1--6},
     year = {2023},
     organization = {IEEE},
     fau = {Joint First Author}
   }

2. TMI
   
   

   Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEs

   Prashant Pandey*, Mustafa Chasmai*, Tanuj Sur, and Brejesh Lall

   IEEE Transactions on Medical Imaging 2023

   arXiv Bib HTML Code

   @article{pandey2022robust,
     title = {Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEs},
     author = {Pandey*, Prashant and Chasmai*, Mustafa and Sur, Tanuj and Lall, Brejesh},
     journal = {IEEE Transactions on Medical Imaging},
     year = {2023},
     fau = {Joint First Author},
     core = {Core A* Journal}
   }

3. WACV
   
   

   From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instruments

   Britty Baby, Daksh Thapar, Mustafa Chasmai, Tamajit Banerjee, Kunal Dargan, and 3 more authors

   In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision 2023

   arXiv Bib Code Website

   @inproceedings{baby2023from,
     title = {From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instruments},
     author = {Baby, Britty and Thapar, Daksh and Chasmai, Mustafa and Banerjee, Tamajit and Dargan, Kunal and Suri, Ashish and Banerjee, Subhashis and Arora, Chetan},
     booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
     year = {2023},
     organization = {IEEE},
     core = {Core A Conference}
   }

2022

1. MICCAI
   
   

   Adversarially Robust Prototypical Few-Shot Segmentation with Neural-ODEs

   Prashant Pandey*, Aleti Vardhan*, Mustafa Chasmai*, Tanuj Sur, and Brejesh Lall

   In International Conference on Medical Image Computing and Computer-Assisted Intervention 2022

   arXiv Bib HTML Code Website

   @inproceedings{pandey2022adversarially,
     title = {Adversarially Robust Prototypical Few-Shot Segmentation with Neural-ODEs},
     author = {Pandey*, Prashant and Vardhan*, Aleti and Chasmai*, Mustafa and Sur, Tanuj and Lall, Brejesh},
     booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
     pages = {77--87},
     year = {2022},
     organization = {Springer},
     core = {Core A Conference}
   }

2. CoRL-W
   
   

   Learning Generalizable Task Policies for Embodied Agents in Domains with Rich Inter-object Interactions

   Mustafa Chasmai, Shreshth Tuli,  Mausam, and Rohan Paul

   In CoRL 2022 Workshop on Learning, Perception, and Abstraction for Long-Horizon Planning 2022

   Bib HTML

   @inproceedings{chasmai2022learning,
     title = {Learning Generalizable Task Policies for Embodied Agents in Domains with Rich Inter-object Interactions},
     author = {Chasmai, Mustafa and Tuli, Shreshth and Mausam and Paul, Rohan},
     booktitle = {CoRL 2022 Workshop on Learning, Perception, and Abstraction for Long-Horizon Planning},
     year = {2022},
     fau = {First Author}
   }

3. SNCS
   
   

   A View Independent Classification Framework for Yoga Postures

   Mustafa Chasmai, Nirjhar Das, Aman Bhardwaj, and Rahul Garg

   SN computer science 2022

   arXiv Bib HTML Code

   @article{chasmai2022view,
     title = {A View Independent Classification Framework for Yoga Postures},
     author = {Chasmai, Mustafa and Das, Nirjhar and Bhardwaj, Aman and Garg, Rahul},
     journal = {SN computer science},
     volume = {3},
     number = {6},
     pages = {1--15},
     year = {2022},
     publisher = {Springer},
     fau = {First Author}
   }

4. ICIP
   
   

   Representation Learning Using Rank Loss for Robust Neurosurgical Skills Evaluation

   Britty Baby, Mustafa Chasmai, Tamajit Banerjee, Ashish Suri, Subhashis Banerjee, and 1 more author

   In 2022 IEEE International Conference on Image Processing (ICIP) 2022

   Bib HTML Code Website

   @inproceedings{baby2022representation,
     title = {Representation Learning Using Rank Loss for Robust Neurosurgical Skills Evaluation},
     author = {Baby, Britty and Chasmai, Mustafa and Banerjee, Tamajit and Suri, Ashish and Banerjee, Subhashis and Arora, Chetan},
     booktitle = {2022 IEEE International Conference on Image Processing (ICIP)},
     pages = {4048--4052},
     year = {2022},
     organization = {IEEE},
   }

5. CIKM
   
   

   PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python

   Haiping Lu, Xianyuan Liu, Shuo Zhou, Robert Turner, Peizhen Bai, and 4 more authors

   In Proceedings of the 31st ACM International Conference on Information & Knowledge Management 2022

   arXiv Bib HTML Code

   @inproceedings{lu2022pykale,
     title = {PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python},
     author = {Lu, Haiping and Liu, Xianyuan and Zhou, Shuo and Turner, Robert and Bai, Peizhen and Koot, Raivo E and Chasmai, Mustafa and Schobs, Lawrence and Xu, Hao},
     booktitle = {Proceedings of the 31st ACM International Conference on Information \& Knowledge Management},
     pages = {4274--4278},
     year = {2022},
   }