LabCompass

Shujon Naha

Computer Science · Indiana University

OpenAlex
Advanced Neural Network ApplicationsAdvanced Image and Video Retrieval TechniquesDomain Adaptation and Few-Shot LearningHuman Pose and Action RecognitionMultimodal Machine Learning Applications

Publications

17

Citations

188

Est. group size

—

Recurring co-author estimate

Active years

15

Publishing since 2011

Research summary
AI-generated

Shujon Naha works in computer vision, a branch of computer science focused on teaching computers to interpret images and video. Their research develops methods for tasks like identifying and outlining objects in images (segmentation), recognizing human actions in videos, and connecting visual content with text descriptions. A recurring focus is on learning with limited labeled data, using unsupervised, semi-supervised, and zero-shot approaches.

Image and video segmentationAction and activity recognition in videoLearning with limited labels (unsupervised/semi-supervised/zero-shot)Neural network methods for visionConnecting images and text

Publication activity has been low and intermittent over the past decade, averaging under one paper per year in recent years with some gaps between active years.

Generated by claude-opus-4-8 from public bibliographic data · Jul 11, 2026

Publication cadence
Publications per year over the last 10 years — averaging 0.8/year recently
2017: 1 publication172018: 1 publication18192020: 3 publications3202021: 2 publications21222023: 1 publication232024: 2 publications242025: 1 publication2526
Recent publications
Publishes in
  • arXiv (Cornell University)×3
  • Advanced Functional Materials×1
  • eScholarship (California Digital Library)×1
  • Research Square×1

This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.

Last updated Jul 11, 2026.

Claim or correct this profile