Research

My research interests primarily lie in the intersection of vision and language learning. In general, I am interested in solving problems that stem from a lack of grounding, lack of annotated or domain-specific data, and problems where testing data is distributionally different from training data. Of late, I am particularly drawn to problems motivated by cognitive science, perhaps to my detriment.

Previously, I graduated from the University of Florida with my masters. Before that, I worked at the Indian Institute of Science under Prof. K R Ramakrishnan at the Computer Vision and Artificial Intelligence (CVAI) lab where I worked on touch-interface applications using a projector-camera based setup.

---

Publications

• Akhil Perincherry, Jacob Krantz, Stefan Lee, Do Visual Imaginations Improve Vision-and-Language Navigation Agents?, In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

• Tao Jun Lin, Wenqing Wang, Yujiao Shi, Akhil Perincherry, Ankit Vora, Hongdong Li, Geometry-guided Cross-view Diffusion for One-to-many Cross-view Image Synthesis, International Conference on 3D Vision (3DV), 2025

• Yujiao Shi, Hongdong Li, Akhil Perincherry, Ankit Vora, Weakly-supervised Camera Localization by Ground-to-satellite Image Registration, In Proc. European conference on computer vision (ECCV), 2024

• Yanhao Zhang, Yujiao Shi, Shan Wang, Ankit Vora, Akhil Perincherry, Yongbo Chen, Hongdong Li, Increasing SLAM Pose Accuracy by Ground-to-Satellite Image Registration, In Proc. IEEE Conference on Robotics and Automation (ICRA), 2024

• Yujiao Shi, Fei Wu, Akhil Perincherry, Ankit Vora, Hongdong Li, Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer, In Proc. IEEE International Conference on Computer Vision (ICCV), 2023

• Shan Wang, Yanhao Zhang, Akhil Perincherry, Ankit Vora, Hongdong Li, View Consistent Purification for Accurate Cross-View Localization, In Proc. IEEE International Conference on Computer Vision (ICCV), 2023

• Shan Wang, Yanhao Zhang, Ankit Vora, Akhil Perincherry, Hongdong Li, Satellite image based cross-view localization for autonomous vehicle, In Proc. IEEE Conference on Robotics and Automation (ICRA), 2023

• Adarsh Appaiah (equal contribution), Akhil Perincherry (equal contribution), Ajinkya Sanjeev Keskar (equal contribution) and Vijaya Krishna “Spectrum Sensing in Cognitive Radio Based on Compressive Measurements”. IEEE International conference on Emerging trends in Communication, Control, Signal Processing and Computing Applications (IEEE-C2SPCA), 2013

---

Patents

• A Perincherry, C Cruise “Domain Generation via Learned Partial Domain Translations” US Patent 11321587 - Generative modeling to generate novel domain data.

• A Perincherry, K Singh, N Nagraj Rao “Vehicle Intersection Operation” US Patent 11420625 - CNN+LSTM based model to predict vehicle right-of-way at intersections.

• A Perincherry, A Chand “Generating Artificial Video with Changed Domain” US Patent App. 18/065672 - Guiding video generation using associated audio.

• Y Shi, H Li, A Vora, A Perincherry “Camera Pose Relative to Overhead Image” US Patent App. 18/190194

• S Wang, Y Zhang, A Perincherry, A Vora, H Li, Y Shi, “Camera Localization” US Patent App. 18/191165

• Y Shi, H Li, A Perincherry, A Vora, “Camera Pose Refinement With Ground-To-Satellite Image Registration” US Patent App. 18/468981

• N Nagraj Rao, A Perincherry “Sensor Domain Adaptation” US Patent 12067087 - Generative modeling to translate legacy sensor data domain to newer domain.

• A Perincherry, A Mordovanakis, S Suthar, A Chand “Neural Network Object Identification” US Patent 11823465 - Radar camera sensor fusion to perform object 3D shape identification.

• A Perincherry, I Patel, K Min “RCCC to RGB Domain Translation with Deep Neural Networks” US Patent 11068749 - Generative modeling to translate automotive sensor domain to common domains.

• N Jaipuria, G Sholingar, V Murali, R Bhasin, A Perincherry “Vehicle Image Generation” US Patent 11042758 - Generative modeling to improve driving safety features via domain adaptation.

---

Knowledge Distillation Series (Paper Summaries)

• SimCLR
• SimCLRv2
• Big Self-Supervised Models Advance Medical Image Classification
• Contrastive Training for Improved Out-of-Distribution Detection
• Improving domain adaptation in de-identification of electronic health records through self-training
• Transformers
• ViT
• DALL-E
• Training data-efficient image transformers & distillation through attention
• BERT Pre-Training of Image Transformers
• Masked Autoencoders Are Scalable Vision Learners

Past Research

Rat whisker tracking - Univ. of Florida (2016)

---

Table-top touch interface using Kinect - Indian Institute of Science (2014)

---

Compressive sensing as a solution to Cognitive Radio (2013)

---

Service

• Served as a reviewer for CVPR 2025.

• Served as a reviewer for ICLR 2025.

• Served as a reviewer for TMLR.

• Served as a reviewer for NeurIPS 2024.

• Served as a reviewer for ACM SIGGRAPH Asia 2024.

• Served as a reviewer for ICCV WiCV 2023.

• MentorUF, University of Florida (2016) - Mentored a middle-school student for a year.

• IEEE Eta Kappa Nu, University of Florida (2016)

• Teaching Assistant for graduate course “Foundations of Digital Signal Processing” at University of Florida during (2015).

• Cluster coordinator for South-East Bangalore, Youth For Seva (2013-2014) - Involved in sapling planting and providing kids with computer training.