LabCompass

AJ Piergiovanni

Computer Science · Indiana University

OpenAlex
Multimodal Machine Learning ApplicationsHuman Pose and Action RecognitionDomain Adaptation and Few-Shot LearningAnomaly Detection Techniques and ApplicationsAdvanced Image and Video Retrieval Techniques

Publications

71

Citations

863

Est. group size

—

Recurring co-author estimate

Active years

11

Publishing since 2015

Research summary
AI-generated

AJ Piergiovanni works in computer vision and machine learning, focusing on systems that understand both images/videos and language together (called multimodal models). Recent work includes building models that can describe videos, answer questions about them, and align video content with text, as well as scaling up large vision-and-language models. Earlier work also addressed recognizing human actions in videos.

Multimodal vision-and-language modelsVideo understanding and captioningVideo question answeringObject detection and localization from text queriesHuman action recognition

Publication activity peaked around 2018-2022 and has been gradually declining in the most recent 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 4.8/year recently
2017: 1 publication172018: 8 publications182019: 15 publications15192020: 9 publications202021: 11 publications212022: 10 publications222023: 6 publications232024: 5 publications242025: 3 publications2526
Recent publications
Publishes in
  • arXiv (Cornell University)×33
  • Lecture notes in computer science×5
  • Proceedings of the AAAI Conference on Artificial Intelligence×2
  • International Journal of Computer Vision×2
  • Neural Information Processing Systems×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