Krähenbühl, Philipp

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

Krähenbühl, P., & Koltun, V. (2012) · arXiv

Advanced Neural Network ApplicationsMedical Image Segmentation Techniques

Cited by 2,908

Tracking Objects as Points

Zhou, X., Koltun, V., & Krähenbühl, P. (2020) · Lecture Notes in Computer Science

Video Surveillance and Tracking MethodsAutonomous Vehicle Technology and Safety

Cited by 1,428

Detecting Twenty-Thousand Classes Using Image-Level Supervision

Zhou, X., Girdhar, R., Joulin, A., Krähenbühl, P., & Misra, I. (2022) · Lecture Notes in Computer Science

Advanced Neural Network ApplicationsDomain Adaptation and Few-Shot Learning

Cited by 564

Objects as Points

Zhou, X., Wang, D., & Krähenbühl, P. (2019) · arXiv

Advanced Neural Network ApplicationsEmbedded Systems Design Techniques

Cited by 288

Assessing Generalization in Deep Reinforcement Learning

Packer, C., Gao, K., Kos, J., Krähenbühl, P., Koltun, V., & Song, D. (2018) · arXiv

Reinforcement Learning in RoboticsDomain Adaptation and Few-Shot Learning

Cited by 114

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

Cho, J. H., Madotto, A., Mavroudi, E., Afouras, T., Nagarajan, T., Maaz, M., Song, Y., Ma, T., Hu, S., Jain, S., et al. (2025) · arXiv

Multimodal Machine Learning ApplicationsHuman Pose and Action Recognition

Cited by 8