About Me

I am a PhD student (2016-) at Carnegie Mellon, working in computer vision with Deva Ramanan. Earlier I graduated with a masters from CMU itself, working with Martial Hebert, Abhinav Gupta, Kris Kitani and David Fouhey, and was named a Siebel Scholar. I was a CS undergrad at IIIT, Hyderabad, working with C. V. Jawahar.

I have been fortunate to spend some fun summers working with amazing people on interesting research problems. Recently, I worked with Andrew Zisserman, João Carreira and Carl Doersch at DeepMind. Earlier in 2016, I worked with Josef Sivic and Bryan Russell at CTL, Adobe Research (SF); and in 2017, with Georgia Gkioxari, Lorenzo Torresani and Du Tran at Facebook Research (Menlo Park). Even before in 2013, I was one of fourteen students from India to intern at the Facebook HQ (Menlo Park, CA). I worked on graph search with Yuval Kesten and also collaborated with Craig Campbell.

Major Publications

Video Action Transformer Network

Rohit Girdhar, João Carreira, Carl Doersch and Andrew Zisserman
arXiv 2018 · pre-print · webpage

A Better Baseline for AVA

Rohit Girdhar, João Carreira, Carl Doersch and Andrew Zisserman
ActivityNet Workshop, CVPR 2018 · Salt Lake City, UT · pdf

Detect-and-Track: Efficient Pose Estimation in Videos

Rohit Girdhar, Georgia Gkioxari, Lorenzo Torresani, Manohar Paluri and Du Tran
CVPR 2018 · Salt Lake City, UT · webpage

Simple, efficient and effective keypoint tracking

Rohit Girdhar, Georgia Gkioxari, Lorenzo Torresani, Deva Ramanan, Manohar Paluri and Du Tran
PoseTrack Workshop, ICCV 2017 · Venice, Italy · pdf
First in keypoint tracking challenge

Attentional Pooling for Action Recognition

Rohit Girdhar and Deva Ramanan
NIPS 2017 · Long Beach, CA · webpage

ActionVLAD: Learning spatio-temporal aggregation for action classification

Rohit Girdhar, Deva Ramanan, Abhinav Gupta, Josef Sivic and Bryan Russell
CVPR 2017 · Honolulu, HI · webpage

Binge Watching: Scaling Affordance Learning from Sitcoms

Xiaolong Wang*, Rohit Girdhar* and Abhinav Gupta (* equal contribution)
CVPR 2017 (spotlight) · Honolulu, HI · webpage · pdf · data

Learning a Predictable and Generative Representation for Objects

Rohit Girdhar, David Fouhey, Mikel Rodriguez and Abhinav Gupta
ECCV 2016 (spotlight) · Amsterdam, Netherlands · webpage

Cutting through the clutter: Task-relevant features for image matching

Rohit Girdhar, David Fouhey, Kris Kitani, Abhinav Gupta and Martial Hebert
WACV 2016 · Lake Placid, NY · pdf

Optimizing Storage Intensive Vision Applications to Device Capacity

Rohit Girdhar, Jayaguru Panda and C. V. Jawahar
ACCV 2014 · Singapore · pdf

Posts

Dec 23, 2016 · Compile TensorFlow on CentOS 6

Fun Stuff

Inspired by the great David Fouhey, I have tried dabbling in the fine art of joke publications. Here's a taste.

PSYCHO: PerSonalitY CHaracterizatiOn of artificial intelligence

Achal Dave and Rohit Girdhar
SIGBOVIK 2018 · Pittsburgh, PA · pdf