Manohar Paluri

Manohar Paluri has worked on building Facebook’s Image and Video understanding platform since joining the company in 2012. His interests lie in using large amounts of annotated and weakly annotated image and video data to build a visual representation of everything in the world. Prior to joining Facebook, Manohar was pursuing his PhD from Georgia Tech and worked at Google, IBM Watson labs and Sarnoff Corporation (now SRI). Currently, he manages the computer vision group. This group focuses on building Facebook’s image and video understanding platform.

Manohar's Publications

January 30, 2019

RESEARCH

ML APPLICATIONS

Large-Scale Visual Relationship Understanding

Large scale visual understanding is challenging, as it requires a model to handle the widely-spread and imbalanced distribution of <subject, relation, object> triples. In real-world scenarios with large numbers of objects and relations, some are seen very …

Ji Zhang, Yannis Kalantidis, Marcus Rohrbach, Manohar Paluri, Ahmed Elgammal, Mohamed Elhoseiny

January 30, 2019

September 04, 2018

RESEARCH

ML APPLICATIONS

Self-Supervised Feature Learning for Semantic Segmentation of Overhead Imagery

Overhead imageries play a crucial role in many applications such as urban planning, crop yield forecasting, mapping, and policy making. Semantic segmentation could enable automatic, efficient, and large-scale understanding of overhead imageries for…

By: Suriya Singh, Anil Batra, Guan Pang, Lorenzo Torresani, Saikat Basu, Manohar Paluri, C.V. Jawahar

September 04, 2018

June 18, 2018

RESEARCH

ML APPLICATIONS

A Closer Look at Spatiotemporal Convolutions for Action Recognition

In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Our motivation stems from the observation that 2D CNNs applied to individual frames of the video have remained solid performers in action recognition. In this work we empirically demonstrate the accuracy advantages of 3D…

Du Tran, Heng Wang, Lorenzo Torresani, Jamie Ray, Yann LeCun, Manohar Paluri

June 18, 2018