Deva Ramanan

Carnegie Mellon University — United States

Computer Science · Physical Sciences

79h-index79.1kcitations340works15.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(82), Human Pose and Action Recognition(80), Advanced Vision and Imaging(68), Video Surveillance and Tracking Methods(64), Advanced Image and Video Retrieval Techniques(57)

Publications340 total

LEARNER: Contrastive Pretraining for Learning Fine-Grained Patient Progression from Coarse Inter-Patient Labels
arXiv (Cornell University)·2024Open Access
FlashTex: Fast Relightable Mesh Texturing with LightControlNet
Lecture notes in computer science·2024· 10 cited
Evaluating Text-to-Visual Generation with Image-to-Text Generation
Lecture notes in computer science·2024· 41 cited
NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
arXiv (Cornell University)·2024· 3 citedOpen Access
Guardian PI : Raspberry Based Night Survaillance Camera
2024
Better Call SAL: Towards Learning to Segment Anything in Lidar
Lecture notes in computer science·2024· 7 cited
Neural Eulerian Scene Flow Fields
arXiv (Cornell University)·2024Open Access
I Can’t Believe It’s Not Scene Flow!
Lecture notes in computer science·2024· 3 cited
Lidar Panoptic Segmentation in an Open World
International Journal of Computer Vision·2024· 3 citedOpen Access
GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation
arXiv (Cornell University)·2024Open Access
SMORE: Simultaneous Map and Object REconstruction
arXiv (Cornell University)·2024Open Access
Evaluating and Improving Compositional Text-to-Visual Generation
2024· 27 cited
The Neglected Tails in Vision-Language Models
2024· 14 cited
SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM
2024· 280 cited
Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection
arXiv (Cornell University)·2024Open Access
Reanimating Images using Neural Representations of Dynamic Stimuli
arXiv (Cornell University)·2024Open Access
Predicting Long-horizon Futures by Conditioning on Geometry and Time
arXiv (Cornell University)·2024Open Access
Evaluating Text-to-Visual Generation with Image-to-Text Generation
arXiv (Cornell University)·2024· 3 citedOpen Access
Better Call SAL: Towards Learning to Segment Anything in Lidar
arXiv (Cornell University)·2024Open Access
RelPose++: Recovering 6D Poses from Sparse-view Observations
2024· 38 cited
← Previouspage 2 of 17Next →

Frequent Co-authors

Charless C. Fowlkes(7), Hamed Pirsiavash(5), Simon Lucey(4), Yi Yang(4), David Forsyth(4), James Hays(3), Xiangxin Zhu(3), Carl Vondrick(3), Rohit Girdhar(3), Yu-Xiong Wang(3), Martial Hebert(3), James Steven Supančič(3), Chaitanya Desai(3), Pedro F. Felzenszwalb(2), David McAllester(2), Ming-Fang Chang(2), John Lambert(2), Patsorn Sangkloy(2), Jagjeet Singh(2), Sławomir Bąk(2)