Christoph Feichtenhofer

Computer Science · Physical Sciences

39h-index20.9kcitations97works15.42yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

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

Research Topics

Human Pose and Action Recognition(49), Multimodal Machine Learning Applications(36), Domain Adaptation and Few-Shot Learning(22), Advanced Neural Network Applications(21), Video Surveillance and Tracking Methods(18)

Publications96 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 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
An Empirical Study of Autoregressive Pre-training from Videos
arXiv (Cornell University)·2025Open Access
Gaussian Masked Autoencoders
arXiv (Cornell University)·2025Open Access
Altogether: Image Captioning via Re-aligning Alt-text
arXiv (Cornell University)·2024Open Access
SAM 2: Segment Anything in Images and Videos
arXiv (Cornell University)·2024· 206 citedOpen Access
Ego4D: Around the World in 3,600 Hours of Egocentric Video
IEEE Transactions on Pattern Analysis and Machine Intelligence·2024· 7 citedOpen Access
Altogether: Image Captioning via Re-aligning Alt-text
2024· 1 citedOpen Access
Window Attention is Bugged: How not to Interpolate Position Embeddings
arXiv (Cornell University)·2023Open Access
Diffusion Models as Masked Autoencoders
2023· 32 cited
CiT: Curation in Training for Effective Vision-Language Data
2023· 9 cited
The effectiveness of MAE pre-pretraining for billion-scale pretraining
2023· 37 cited
Demystifying CLIP Data
arXiv (Cornell University)·2023· 22 citedOpen Access
On the Benefits of 3D Pose and Tracking for Human Action Recognition
2023· 40 cited
Scaling Language-Image Pre-Training via Masking
2023· 206 cited
page 1 of 5Next →

Frequent Co-authors

Haoqi Fan(19), Axel Pinz(14), Chao-Yuan Wu(13), Jitendra Malik(13), Richard P. Wildes(10), Yanghao Li(9), Kaiming He(8), Karttikeya Mangalam(7), Bo Xiong(7), Ross Girshick(7), Andrew Zisserman(5), Po-Yao Huang(5), Saining Xie(4), Alan Yuille(3), Kristen Grauman(3), Philipp Krähenbühl(3), Florian Metze(3), Kalyan Vasudev Alwala(3), Zhuang Liu(2), Hanzi Mao(2)