Lorenzo Torresani

Lorenzo is a Research Scientist at Facebook AI Research (FAIR). He is also a Professor in the Computer Science Department at Dartmouth. He received a Laurea Degree in computer science with summa cum laude honors from the University of Milan (Italy), and an M.S. and Ph.D. in computer science from Stanford University. Prior to Facebook, Lorenzo worked at several industrial research labs, including Microsoft Research, Like.com, and Digital Persona. His research interests lie in computer vision and deep learning. He is the recipient of a CVPR Best Student Paper prize, a National Science Foundation CAREER Award, a Google Faculty Research Award, three Facebook Faculty Awards, and a Fulbright US Scholar Award.

Lorenzo's Publications

October 27, 2019

COMPUTER VISION

ML APPLICATIONS

Listen to Look: Action Recognition by Previewing Audio

In the face of the video data deluge, today’s expensive clip-level classifiers are increasingly impractical. We propose a framework for efficient action recognition in untrimmed video that uses audio as a preview mechanism to eliminate both short-term and long-term visual redundancies.

Ruohan Gao, Tae-Hyun Oh, Kristen Grauman, Lorenzo Torresani

October 27, 2019

June 16, 2020

COMPUTER VISION

Video Modeling with Correlation Networks

Motion is a salient cue to recognize actions in video. Modern action recognition models leverage motion information either explicitly by using optical flow as input or…

Heng Wang, Du Tran, Lorenzo Torresani, Matt Feiszli

June 16, 2020

June 14, 2020

RESEARCH

COMPUTER VISION

Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation

Gedas Bertasius, Lorenzo Torresani

June 14, 2020

October 27, 2019

RESEARCH

COMPUTER VISION

Video Classification with Channel-Separated Convolutional Networks

Group convolution has been shown to offer great computational savings in various 2D convolutional architectures for image classification. It is natural to ask: 1) if group convolution can help to alleviate the high computational cost of video…

Du Tran, Heng Wang, Lorenzo Torresani, Matt Feiszli,

October 27, 2019

October 27, 2019

RESEARCH

COMPUTER VISION

DistInit: Learning Video Representations Without a Single Labeled Video

Video recognition models have progressed significantly over the past few years, evolving from shallow classifiers trained on hand-crafted features to deep spatiotemporal networks. However, labeled video data required to train such models has…

Rohit Girdhar, Du Tran, Lorenzo Torresani, Deva Ramanan,

October 27, 2019

October 27, 2019

RESEARCH

COMPUTER VISION

SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition

While many action recognition datasets consist of collections of brief, trimmed videos each containing a relevant action, videos in the real-world (e.g., on YouTube) exhibit very different properties: they are often several minutes long, where…

Bruno Korbar, Du Tran, Lorenzo Torresani,

October 27, 2019