Multimodal Vision Research Laboratory

MVRL

about us

The Multimodal Vision Research Laboratory (MVRL) develops novel algorithms for image understanding and works to solve challenging problems in areas including remote sensing, image localization, and medical imaging. If you are interested in joining us, please check out our openings page for more information and a description of current open positions.

recent news

• 26 Feb 2025 : two papers accepted to CVPR, congrats to first authors Eric Xing and Aayush Dhakal!
• 09 Dec 2024 : two papers accepted to AAAI!
• 04 Nov 2024 : one paper accepted to WACV, congrats to Srikumar Sastry, Subash Khanal, Aayush Dhakal, and Adeel Ahmad!
• 03 Oct 2024 : five abstracts accepted to the AGU Fall Meeting!
• 25 Sep 2024 : one paper accepted to NeurIPS, congrats to Anindiya Sarkar, Srikumar Sastry, Aleksis Pirinen, Chongjie Zhang, and Eugene Vorobeychik!
• 15 Jul 2024 : one paper accepted to ICMLA, congrats to Michael Lanier and one paper accepted to WIFS, congrats to José Nascimento!

Check the archives for old news.

selected recent publications

See our publications page for a complete listing.

1. 

   Xing E, Kolouju P, Pless R, Stylianou A, Jacobs N. 2025. ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
   bibtex

   close  

   @inproceedings{xing2025cir,
     annotation = {spotlight},
     author = {Xing, Eric and Kolouju, Pranavi and Pless, Robert and Stylianou, Abby and Jacobs, Nathan},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     title = {{ConText-CIR}: Learning from Concepts in Text for Composed Image Retrieval},
     month = jun,
     year = {2025}
   }
   

2. 

   Dhakal A, Sastry S, Khanal S, Ahmad A, Xing E, Jacobs N. 2025. RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
   bibtex | paper | linkedin

   close  

   @inproceedings{dhakal2025range,
     annotation = {spotlight,remote_sensing,conservation},
     author = {Dhakal, Aayush and Sastry, Srikumar and Khanal, Subash and Ahmad, Adeel and Xing, Eric and Jacobs, Nathan},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pdf = {https://arxiv.org/pdf/2502.19781},
     linkedin = {https://www.linkedin.com/posts/jacobsn_range-retrieval-augmented-neural-fields-activity-7301277448279638016-q_vx?utm_source=share&utm_medium=member_desktop&rcm=ACoAAACWgMUBbrOLvty2wxK6klz29_SYYIMtEis},
     title = {{RANGE}: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings},
     month = jun,
     year = {2025},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
     eprint = {2502.19781}
   }
   

3. 

   Sastry S, Khanal S, Dhakal A, Ahmad A, Jacobs N. 2025. TaxaBind: A Unified Embedding Space for Ecological Applications. In: IEEE Winter Conference on Applications of Computer Vision (WACV).
   bibtex | paper | website | linkedin | code

   close  

   @inproceedings{sastry2025taxa,
     annotation = {remote_sensing,spotlight,conservation},
     title = {{TaxaBind}: A Unified Embedding Space for Ecological Applications},
     author = {Sastry, Srikumar and Khanal, Subash and Dhakal, Aayush and Ahmad, Adeel and Jacobs, Nathan},
     year = {2025},
     month = feb,
     booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
     author+an = {5=highlight},
     archiveprefix = {arXiv},
     thumbnail = {/thumbnails/taxabind.jpg},
     primaryclass = {cs.CV},
     eprint = {2411.00683},
     code = {https://github.com/mvrl/TaxaBind},
     project = {https://vishu26.github.io/taxabind},
     linkedin = {https://www.linkedin.com/posts/jacobsn_im-excited-to-share-that-taxabind-a-unified-activity-7259230411728277504-HgXc?utm_source=share&utm_medium=member_desktop&rcm=ACoAAACWgMUBbrOLvty2wxK6klz29_SYYIMtEis},
     pdf = {https://openaccess.thecvf.com/content/WACV2025/papers/Sastry_TaxaBind_A_Unified_Embedding_Space_for_Ecological_Applications_WACV_2025_paper.pdf}
   }
   

4. 

   Kerner H, Chaudhari S, Ghosh A, Robinson C, Ahmad A, Choi E, Jacobs N, Holmes C, Mohr M, Dodhia R, Ferres JML, Marcus J. 2025. Fields of The World: A Machine Learning Benchmark Dataset For Global Agricultural Field Boundary Segmentation. In: Association for the Advancement of Artificial Intelligence (AAAI).
   bibtex | paper | website

   close  

   @inproceedings{kerner2025ftw,
     annotation = {spotlight,remote_sensing,agriculture},
     title = {{Fields of The World}: A Machine Learning Benchmark Dataset For Global Agricultural Field Boundary Segmentation},
     author = {Kerner, Hannah and Chaudhari, Snehal and Ghosh, Aninda and Robinson, Caleb and Ahmad, Adeel and Choi, Eddie and Jacobs, Nathan and Holmes, Chris and Mohr, Matthias and Dodhia, Rahul and Ferres, Juan M. Lavista and Marcus, Jennifer},
     author+an = {7=highlight},
     thumbnail = {/thumbnails/ftw.jpg},
     booktitle = {Association for the Advancement of Artificial Intelligence (AAAI)},
     volume = {2409.16252},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
     eprint = {2409.16252},
     pdf = {https://arxiv.org/pdf/2409.16252},
     day = {27},
     month = feb,
     year = {2025},
     project = {https://fieldsofthe.world/}
   }
   

5. 

   Sarkar A, Sastry S, Pirinen A, Zhang C, Jacobs N, Vorobeychik Y. 2024. GOMAA-Geo: GOal Modality Agnostic Active Geo-localization. In: Neural Information Processing Systems (NeurIPS).
   bibtex | paper | linkedin | code

   close  

   @inproceedings{sarkar2024gomaageo,
     annotation = {spotlight,remote_sensing,localization},
     title = {{GOMAA-Geo}: GOal Modality Agnostic Active Geo-localization},
     author = {Sarkar, Anindya and Sastry, Srikumar and Pirinen, Aleksis and Zhang, Chongjie and Jacobs, Nathan and Vorobeychik, Yevgeniy},
     year = {2024},
     month = dec,
     day = {9},
     booktitle = {Neural Information Processing Systems (NeurIPS)},
     eprint = {2406.01917},
     archiveprefix = {arXiv},
     thumbnail = {/thumbnails/gomaa.jpg},
     author+an = {5=highlight},
     pdf = {https://papers.nips.cc/paper_files/paper/2024/file/bd8b52c2fefdb37e3b3953a37408e9dc-Paper-Conference.pdf},
     arxiv = {https://arxiv.org/pdf/2406.01917},
     code = {https://github.com/mvrl/GOMAA-Geo},
     linkedin = {https://www.linkedin.com/posts/jacobsn_im-excited-to-announce-that-gomaa-geo-activity-7244782724610211840-43Vs?utm_source=share&utm_medium=member_desktop},
     primaryclass = {cs.CV}
   }
   

---