Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Achal Dave

Opening up Open-World Tracking


Apr 22, 2021
Yang Liu, Idil Esen Zulfikar, Jonathon Luiten, Achal Dave, Aljoša Ošep, Deva Ramanan, Bastian Leibe, Laura Leal-Taixé


  Access Paper or Ask Questions

Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details


Feb 01, 2021
Achal Dave, Piotr Dollár, Deva Ramanan, Alexander Kirillov, Ross Girshick


  Access Paper or Ask Questions

Detecting Invisible People


Dec 15, 2020
Tarasha Khurana, Achal Dave, Deva Ramanan

* Project page: http://www.cs.cmu.edu/~tkhurana/invisible.htm 

  Access Paper or Ask Questions

Measuring Robustness to Natural Distribution Shifts in Image Classification


Jul 01, 2020
Rohan Taori, Achal Dave, Vaishaal Shankar, Nicholas Carlini, Benjamin Recht, Ludwig Schmidt


  Access Paper or Ask Questions

TAO: A Large-Scale Benchmark for Tracking Any Object


May 20, 2020
Achal Dave, Tarasha Khurana, Pavel Tokmakov, Cordelia Schmid, Deva Ramanan

* Project page: http://taodataset.org/ 

  Access Paper or Ask Questions

Learning to Track Any Object


Oct 25, 2019
Achal Dave, Pavel Tokmakov, Cordelia Schmid, Deva Ramanan

* To be presented at the Holistic Video Understanding workshop at ICCV 

  Access Paper or Ask Questions

A systematic framework for natural perturbations from videos


Jun 05, 2019
Vaishaal Shankar, Achal Dave, Rebecca Roelofs, Deva Ramanan, Benjamin Recht, Ludwig Schmidt

* 16 pages, 5 tables, 6 figures. Paper Website: https://modestyachts.github.io/natural-perturbations-website/ 

  Access Paper or Ask Questions

Towards Segmenting Everything That Moves


Feb 11, 2019
Achal Dave, Pavel Tokmakov, Deva Ramanan


  Access Paper or Ask Questions

Predictive-Corrective Networks for Action Detection


Dec 12, 2017
Achal Dave, Olga Russakovsky, Deva Ramanan

* Accepted to CVPR 2017. [v2]: Updated Multi-LSTM mAP on MultiTHUMOS (should be 29.7, was initially reported as 29.6). [Project URL]: http://www.achaldave.com/projects/predictive-corrective/ 

  Access Paper or Ask Questions