B
Bruno Korbar
Researcher at Facebook
Publications - 16
Citations - 1409
Bruno Korbar is an academic researcher from Facebook. The author has contributed to research in topics: Computer science & Cluster analysis. The author has an hindex of 10, co-authored 14 publications receiving 882 citations. Previous affiliations of Bruno Korbar include Dartmouth College & University of Oxford.
Papers
More filters
Proceedings Article
Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization
TL;DR: It is demonstrated that a calibrated curriculum learning scheme, a careful choice of negative examples, and the use of a contrastive loss are critical ingredients to obtain powerful multi-sensory representations from models optimized to discern temporal synchronization of audio-video pairs.
Journal ArticleDOI
Deep Learning for Classification of Colorectal Polyps on Whole-slide Images.
Bruno Korbar,Andrea M. Olofson,Allen P. Miraflor,Catherine M. Nicka,Matthew A. Suriawinata,Lorenzo Torresani,Arief A. Suriawinata,Saeed Hassanpour +7 more
TL;DR: An automatic image analysis method that can accurately classify different types of colorectal polyps on whole-slide images to help pathologists with this characterization and diagnosis and can reduce the cognitive burden on pathologists and improve their efficacy in histopathological characterization and follow-up recommendations.
Posted Content
Self-Supervised Learning by Cross-Modal Audio-Video Clustering
TL;DR: XDC as discussed by the authors leverages unsupervised clustering in one modality (e.g., audio) as a supervisory signal for the other modality, which helps XDC utilize the semantic correlation and the differences between the two modalities.
Proceedings ArticleDOI
SCSampler: Sampling Salient Clips From Video for Efficient Action Recognition
TL;DR: In this paper, a lightweight ''clip-sampling'' model is proposed to identify the most salient temporal clips within a long video. But the model is limited to action recognition on untrimmed videos.
Proceedings Article
Self-Supervised Learning by Cross-Modal Audio-Video Clustering
TL;DR: Cross-Modal Deep Clustering (XDC), a novel self-supervised method that leverages unsupervised clustering in one modality as a supervisory signal for the other modality, is proposed, which is the first self- supervised learning method that outperforms large-scale fully- Supervised pretraining for action recognition on the same architecture.