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 Makarand Tapaswi

Airbert: In-domain Pretraining for Vision-and-Language Navigation


Aug 20, 2021
Pierre-Louis Guhur, Makarand Tapaswi, Shizhe Chen, Ivan Laptev, Cordelia Schmid

* To be published on ICCV 2021. Webpage is at https://airbert-vln.github.io/ linking to our dataset, codes and models 

  Access Paper or Ask Questions

Learning Object Manipulation Skills via Approximate State Estimation from Real Videos


Nov 13, 2020
Vladimír Petrík, Makarand Tapaswi, Ivan Laptev, Josef Sivic

* CoRL 2020, code at https://github.com/makarandtapaswi/Real2Sim_CoRL2020, project page at https://data.ciirc.cvut.cz/public/projects/2020Real2Sim/ 

  Access Paper or Ask Questions

Deep Multimodal Feature Encoding for Video Ordering


Apr 05, 2020
Vivek Sharma, Makarand Tapaswi, Rainer Stiefelhagen

* IEEE International Conference on Computer Vision (ICCV) Workshop on Large Scale Holistic Video Understanding. The datasets and code are available at https://github.com/vivoutlaw/tcbp 

  Access Paper or Ask Questions

Clustering based Contrastive Learning for Improving Face Representations


Apr 05, 2020
Vivek Sharma, Makarand Tapaswi, M. Saquib Sarfraz, Rainer Stiefelhagen

* To appear at IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2020 

  Access Paper or Ask Questions

Learning Interactions and Relationships between Movie Characters


Mar 29, 2020
Anna Kukleva, Makarand Tapaswi, Ivan Laptev

* CVPR 2020 (Oral) 

  Access Paper or Ask Questions

The Shmoop Corpus: A Dataset of Stories with Loosely Aligned Summaries


Jan 01, 2020
Atef Chaudhury, Makarand Tapaswi, Seung Wook Kim, Sanja Fidler

* Project page: http://www.cs.toronto.edu/~makarand/shmoop/ Dataset at: https://github.com/achaudhury/shmoop-corpus/ 

  Access Paper or Ask Questions

Video Face Clustering with Unknown Number of Clusters


Aug 20, 2019
Makarand Tapaswi, Marc T. Law, Sanja Fidler

* Accepted to ICCV 2019, code and data at https://github.com/makarandtapaswi/BallClustering_ICCV2019 

  Access Paper or Ask Questions

HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips


Jul 31, 2019
Antoine Miech, Dimitri Zhukov, Jean-Baptiste Alayrac, Makarand Tapaswi, Ivan Laptev, Josef Sivic

* Accepted at ICCV 2019 

  Access Paper or Ask Questions

Self-Supervised Learning of Face Representations for Video Face Clustering


Mar 03, 2019
Vivek Sharma, Makarand Tapaswi, M. Saquib Sarfraz, Rainer Stiefelhagen

* To appear at International Conference on Automatic Face and Gesture Recognition (2019) as an Oral. The datasets and code are available at https://github.com/vivoutlaw/SSIAM 

  Access Paper or Ask Questions

Visual Reasoning by Progressive Module Networks


Sep 27, 2018
Seung Wook Kim, Makarand Tapaswi, Sanja Fidler

* 17 pages, 5 figures 

  Access Paper or Ask Questions

MovieGraphs: Towards Understanding Human-Centric Situations from Videos


Apr 15, 2018
Paul Vicol, Makarand Tapaswi, Lluis Castrejon, Sanja Fidler

* Spotlight at CVPR 2018. Webpage: http://moviegraphs.cs.toronto.edu 

  Access Paper or Ask Questions

Situation Recognition with Graph Neural Networks


Aug 14, 2017
Ruiyu Li, Makarand Tapaswi, Renjie Liao, Jiaya Jia, Raquel Urtasun, Sanja Fidler

* ICCV2017 

  Access Paper or Ask Questions

Relaxed Earth Mover's Distances for Chain- and Tree-connected Spaces and their use as a Loss Function in Deep Learning


Nov 22, 2016
Manuel Martinez, Monica Haurilet, Ziad Al-Halah, Makarand Tapaswi, Rainer Stiefelhagen


  Access Paper or Ask Questions

Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning


Oct 15, 2016
Ziad Al-Halah, Makarand Tapaswi, Rainer Stiefelhagen

* Published as a conference paper at CVPR 2016 

  Access Paper or Ask Questions

MovieQA: Understanding Stories in Movies through Question-Answering


Sep 21, 2016
Makarand Tapaswi, Yukun Zhu, Rainer Stiefelhagen, Antonio Torralba, Raquel Urtasun, Sanja Fidler

* CVPR 2016, Spotlight presentation. Benchmark @ http://movieqa.cs.toronto.edu/ Code @ https://github.com/makarandtapaswi/MovieQA_CVPR2016/ 

  Access Paper or Ask Questions