Piotr Dollár

Computer Science · Physical Sciences

64h-index194.3kcitations109works23.12yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

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

Research Topics

Advanced Neural Network Applications(60), Advanced Image and Video Retrieval Techniques(46), Domain Adaptation and Few-Shot Learning(45), Multimodal Machine Learning Applications(21), Human Pose and Action Recognition(13)

Publications109 total

Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning
ArXiv.org·2025Open Access
Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning
arXiv (Cornell University)·2025Open Access
SAM Audio: Segment Anything in Audio
arXiv (Cornell University)·2025Open Access
SAM Audio: Segment Anything in Audio
ArXiv.org·2025Open Access
SAM 3D: 3Dfy Anything in Images
arXiv (Cornell University)·2025Open Access
SAM 3: Segment Anything with Concepts
ArXiv.org·2025· 1 citedOpen Access
PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
arXiv (Cornell University)·2025· 1 citedOpen Access
Perception Encoder: The best visual embeddings are not at the output of the network
arXiv (Cornell University)·2025Open Access
SAM 2: Segment Anything in Images and Videos
arXiv (Cornell University)·2024· 206 citedOpen Access
Segment Anything
2023· 7.8k cited
The effectiveness of MAE pre-pretraining for billion-scale pretraining
2023· 37 cited
Segment Anything
arXiv (Cornell University)·2023· 512 citedOpen Access
The effectiveness of MAE pre-pretraining for billion-scale pretraining
arXiv (Cornell University)·2023· 2 citedOpen Access
Revisiting Weakly Supervised Pre-Training of Visual Perception Models
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 84 cited
Masked Autoencoders Are Scalable Vision Learners
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022Open Access
Revisiting Weakly Supervised Pre-Training of Visual Perception Models
arXiv (Cornell University)·2022· 5 citedOpen Access
Early Convolutions Help Transformers See Better
Neural Information Processing Systems·2021· 19 cited
Benchmarking Detection Transfer Learning with Vision Transformers
arXiv (Cornell University)·2021· 75 citedOpen Access
Masked Autoencoders Are Scalable Vision Learners
arXiv (Cornell University)·2021· 190 citedOpen Access
Early Convolutions Help Transformers See Better
arXiv (Cornell University)·2021· 352 citedOpen Access
page 1 of 6Next →

Frequent Co-authors

Ross Girshick(26), Kaiming He(19), Serge Belongie(9), Pietro Perona(9), Tsung-Yi Lin(8), C. Lawrence Zitnick(7), Georgia Gkioxari(6), Zhuowen Tu(5), Priya Goyal(4), Bharath Hariharan(3), Saining Xie(3), Eric Mintun(3), Nikhila Ravi(3), Chloe Rolland(3), Laura Gustafson(3), Tete Xiao(3), Alexander C. Berg(3), Bernt Schiele(3), Xinlei Chen(3), Pedro O. Pinheiro(3)