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 Ravi Kiran Sarvadevabhatla

Ravi Kiran Sarvadevabhatla

Detecting, Tracking and Counting Motorcycle Rider Traffic Violations on Unconstrained Roads


Apr 18, 2022
Aman Goyal, Dev Agarwal, Anbumani Subramanian, C. V. Jawahar, Ravi Kiran Sarvadevabhatla, Rohit Saluja

Figure 1 for Detecting, Tracking and Counting Motorcycle Rider Traffic Violations on Unconstrained Roads
Figure 2 for Detecting, Tracking and Counting Motorcycle Rider Traffic Violations on Unconstrained Roads
Figure 3 for Detecting, Tracking and Counting Motorcycle Rider Traffic Violations on Unconstrained Roads
Figure 4 for Detecting, Tracking and Counting Motorcycle Rider Traffic Violations on Unconstrained Roads
* 10 pages, 9 figures, Accepted at The 5th Workshop and Prize Challenge: Bridging the Gap between Computational Photography and Visual Recognition (UG2+) in conjunction with IEEE CVPR 2022 
  Access Paper or Ask Questions

Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches


Apr 10, 2022
Sravya Vardhani Shivapuja, Ashwin Gopinath, Ayush Gupta, Ganesh Ramakrishnan, Ravi Kiran Sarvadevabhatla

Figure 1 for Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches
Figure 2 for Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches
Figure 3 for Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches
Figure 4 for Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches
* Extended version of arXiv:2108.08784. In review 
  Access Paper or Ask Questions

Automatic Quantification and Visualization of Street Trees


Jan 17, 2022
Arpit Bahety, Rohit Saluja, Ravi Kiran Sarvadevabhatla, Anbumani Subramanian, C. V. Jawahar

Figure 1 for Automatic Quantification and Visualization of Street Trees
Figure 2 for Automatic Quantification and Visualization of Street Trees
Figure 3 for Automatic Quantification and Visualization of Street Trees
Figure 4 for Automatic Quantification and Visualization of Street Trees
* Accepted at ICVGIP 2021 
  Access Paper or Ask Questions

MUGL: Large Scale Multi Person Conditional Action Generation with Locomotion


Oct 21, 2021
Shubh Maheshwari, Debtanu Gupta, Ravi Kiran Sarvadevabhatla

Figure 1 for MUGL: Large Scale Multi Person Conditional Action Generation with Locomotion
Figure 2 for MUGL: Large Scale Multi Person Conditional Action Generation with Locomotion
Figure 3 for MUGL: Large Scale Multi Person Conditional Action Generation with Locomotion
Figure 4 for MUGL: Large Scale Multi Person Conditional Action Generation with Locomotion
* Accepted at WACV 2022. Project page : https://skeleton.iiit.ac.in/mugl 
  Access Paper or Ask Questions

MeronymNet: A Hierarchical Approach for Unified and Controllable Multi-Category Object Generation


Oct 17, 2021
Rishabh Baghel, Abhishek Trivedi, Tejas Ravichandran, Ravi Kiran Sarvadevabhatla

Figure 1 for MeronymNet: A Hierarchical Approach for Unified and Controllable Multi-Category Object Generation
Figure 2 for MeronymNet: A Hierarchical Approach for Unified and Controllable Multi-Category Object Generation
Figure 3 for MeronymNet: A Hierarchical Approach for Unified and Controllable Multi-Category Object Generation
Figure 4 for MeronymNet: A Hierarchical Approach for Unified and Controllable Multi-Category Object Generation
* Accepted at ACM Multimedia (ACMMM) 2021 [ORAL] . Website : https://meronymnet.github.io/. arXiv admin note: text overlap with arXiv:2006.00190 
  Access Paper or Ask Questions

Palmira: A Deep Deformable Network for Instance Segmentation of Dense and Uneven Layouts in Handwritten Manuscripts


Aug 21, 2021
Prema Satish Sharan, Sowmya Aitha, Amandeep Kumar, Abhishek Trivedi, Aaron Augustine, Ravi Kiran Sarvadevabhatla

Figure 1 for Palmira: A Deep Deformable Network for Instance Segmentation of Dense and Uneven Layouts in Handwritten Manuscripts
Figure 2 for Palmira: A Deep Deformable Network for Instance Segmentation of Dense and Uneven Layouts in Handwritten Manuscripts
Figure 3 for Palmira: A Deep Deformable Network for Instance Segmentation of Dense and Uneven Layouts in Handwritten Manuscripts
Figure 4 for Palmira: A Deep Deformable Network for Instance Segmentation of Dense and Uneven Layouts in Handwritten Manuscripts
* Accepted at ICDAR-21. Watch teaser video https://www.youtube.com/watch?v=V4XWngkrtxQ , code and pretrained models https://github.com/ihdia/Palmira , project page https://ihdia.iiit.ac.in/Palmira 
  Access Paper or Ask Questions

BoundaryNet: An Attentive Deep Network with Fast Marching Distance Maps for Semi-automatic Layout Annotation


Aug 21, 2021
Abhishek Trivedi, Ravi Kiran Sarvadevabhatla

Figure 1 for BoundaryNet: An Attentive Deep Network with Fast Marching Distance Maps for Semi-automatic Layout Annotation
Figure 2 for BoundaryNet: An Attentive Deep Network with Fast Marching Distance Maps for Semi-automatic Layout Annotation
Figure 3 for BoundaryNet: An Attentive Deep Network with Fast Marching Distance Maps for Semi-automatic Layout Annotation
Figure 4 for BoundaryNet: An Attentive Deep Network with Fast Marching Distance Maps for Semi-automatic Layout Annotation
* Accepted at ICDAR-21 for oral presentation - watch video https://www.youtube.com/watch?v=NfeDrFUJuxc. View webpage http://ihdia.iiit.ac.in/BoundaryNet/. Code and pretrained models https://github.com/ihdia/BoundaryNet 
  Access Paper or Ask Questions

Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting


Aug 19, 2021
Sravya Vardhani Shivapuja, Mansi Pradeep Khamkar, Divij Bajaj, Ganesh Ramakrishnan, Ravi Kiran Sarvadevabhatla

Figure 1 for Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting
Figure 2 for Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting
Figure 3 for Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting
Figure 4 for Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting
* Accepted at ACM Multimedia (ACMMM) 2021 . Code, pretrained models and interactive visualizations can be viewed at our project page https://deepcount.iiit.ac.in/ 
  Access Paper or Ask Questions

Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization


Jul 06, 2021
Anurag Bagchi, Jazib Mahmood, Dolton Fernandes, Ravi Kiran Sarvadevabhatla

Figure 1 for Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization
Figure 2 for Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization
Figure 3 for Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization
Figure 4 for Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization

  Access Paper or Ask Questions

RackLay: Multi-Layer Layout Estimation for Warehouse Racks


Mar 17, 2021
Meher Shashwat Nigam, Avinash Prabhu, Anurag Sahu, Puru Gupta, Tanvi Karandikar, N. Sai Shankar, Ravi Kiran Sarvadevabhatla, K. Madhava Krishna

Figure 1 for RackLay: Multi-Layer Layout Estimation for Warehouse Racks
Figure 2 for RackLay: Multi-Layer Layout Estimation for Warehouse Racks
Figure 3 for RackLay: Multi-Layer Layout Estimation for Warehouse Racks
Figure 4 for RackLay: Multi-Layer Layout Estimation for Warehouse Racks
* Visit our project repository at https://github.com/Avinash2468/RackLay 
  Access Paper or Ask Questions

NTU60-X: Towards Skeleton-based Recognition of Subtle Human Actions


Jan 29, 2021
Anirudh Thatipelli, Neel Trivedi, Ravi Kiran Sarvadevabhatla

Figure 1 for NTU60-X: Towards Skeleton-based Recognition of Subtle Human Actions
Figure 2 for NTU60-X: Towards Skeleton-based Recognition of Subtle Human Actions
Figure 3 for NTU60-X: Towards Skeleton-based Recognition of Subtle Human Actions
Figure 4 for NTU60-X: Towards Skeleton-based Recognition of Subtle Human Actions
* Code repository at https://github.com/skelemoa/ntu-x 
  Access Paper or Ask Questions

Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition


Jan 27, 2021
Pranay Gupta, Divyanshu Sharma, Ravi Kiran Sarvadevabhatla

Figure 1 for Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition
Figure 2 for Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition
Figure 3 for Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition
Figure 4 for Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition
* Code and pretrained models available at https://github.com/skelemoa/synse-zsl 
  Access Paper or Ask Questions

Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-Aliased Indoor Environments


Oct 03, 2020
Satyajit Tourani, Dhagash Desai, Udit Singh Parihar, Sourav Garg, Ravi Kiran Sarvadevabhatla, K. Madhava Krishna

Figure 1 for Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-Aliased Indoor Environments
Figure 2 for Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-Aliased Indoor Environments
Figure 3 for Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-Aliased Indoor Environments
Figure 4 for Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-Aliased Indoor Environments
* Under review 
  Access Paper or Ask Questions

Quo Vadis, Skeleton Action Recognition ?


Jul 04, 2020
Pranay Gupta, Anirudh Thatipelli, Aditya Aggarwal, Shubh Maheshwari, Neel Trivedi, Sourav Das, Ravi Kiran Sarvadevabhatla

Figure 1 for Quo Vadis, Skeleton Action Recognition ?
Figure 2 for Quo Vadis, Skeleton Action Recognition ?
Figure 3 for Quo Vadis, Skeleton Action Recognition ?
Figure 4 for Quo Vadis, Skeleton Action Recognition ?
* Reference video : https://www.youtube.com/watch?v=YKjQcV_2gLU 
  Access Paper or Ask Questions

OPAL-Net: A Generative Model for Part-based Object Layout Generation


May 30, 2020
Rishabh Baghel, Ravi Kiran Sarvadevabhatla

Figure 1 for OPAL-Net: A Generative Model for Part-based Object Layout Generation
Figure 2 for OPAL-Net: A Generative Model for Part-based Object Layout Generation
Figure 3 for OPAL-Net: A Generative Model for Part-based Object Layout Generation
Figure 4 for OPAL-Net: A Generative Model for Part-based Object Layout Generation
* Code repository at https://github.com/atmacvit/opalnet 
  Access Paper or Ask Questions

Topological Mapping for Manhattan-like Repetitive Environments


Mar 10, 2020
Sai Shubodh Puligilla, Satyajit Tourani, Tushar Vaidya, Udit Singh Parihar, Ravi Kiran Sarvadevabhatla, K. Madhava Krishna

Figure 1 for Topological Mapping for Manhattan-like Repetitive Environments
Figure 2 for Topological Mapping for Manhattan-like Repetitive Environments
Figure 3 for Topological Mapping for Manhattan-like Repetitive Environments
Figure 4 for Topological Mapping for Manhattan-like Repetitive Environments
* Accepted to ICRA 2020. Project Page: https://github.com/Shubodh/ICRA2020 
  Access Paper or Ask Questions

Indiscapes: Instance Segmentation Networks for Layout Parsing of Historical Indic Manuscripts


Dec 15, 2019
Abhishek Prusty, Sowmya Aitha, Abhishek Trivedi, Ravi Kiran Sarvadevabhatla

Figure 1 for Indiscapes: Instance Segmentation Networks for Layout Parsing of Historical Indic Manuscripts
Figure 2 for Indiscapes: Instance Segmentation Networks for Layout Parsing of Historical Indic Manuscripts
Figure 3 for Indiscapes: Instance Segmentation Networks for Layout Parsing of Historical Indic Manuscripts
Figure 4 for Indiscapes: Instance Segmentation Networks for Layout Parsing of Historical Indic Manuscripts
* Oral presentation at International Conference on Document Analysis and Recognition (ICDAR) - 2019. For dataset, pre-trained networks and additional details, visit project page at http://ihdia.iiit.ac.in/ 
  Access Paper or Ask Questions

Operator-In-The-Loop Deep Sequential Multi-camera Feature Fusion for Person Re-identification


Nov 06, 2018
Navaneet K L, Ravi Kiran Sarvadevabhatla, Shashank Shekhar, R. Venkatesh Babu, Anirban Chakraborty

Figure 1 for Operator-In-The-Loop Deep Sequential Multi-camera Feature Fusion for Person Re-identification
Figure 2 for Operator-In-The-Loop Deep Sequential Multi-camera Feature Fusion for Person Re-identification
Figure 3 for Operator-In-The-Loop Deep Sequential Multi-camera Feature Fusion for Person Re-identification
Figure 4 for Operator-In-The-Loop Deep Sequential Multi-camera Feature Fusion for Person Re-identification

  Access Paper or Ask Questions

Game of Sketches: Deep Recurrent Models of Pictionary-style Word Guessing


Jan 29, 2018
Ravi Kiran Sarvadevabhatla, Shiv Surya, Trisha Mittal, Venkatesh Babu Radhakrishnan

Figure 1 for Game of Sketches: Deep Recurrent Models of Pictionary-style Word Guessing
Figure 2 for Game of Sketches: Deep Recurrent Models of Pictionary-style Word Guessing
Figure 3 for Game of Sketches: Deep Recurrent Models of Pictionary-style Word Guessing
Figure 4 for Game of Sketches: Deep Recurrent Models of Pictionary-style Word Guessing
* To be presented at AAAI-2018. Code, pre-trained models and dataset at github.com/val-iisc/sketchguess 
  Access Paper or Ask Questions

SketchParse : Towards Rich Descriptions for Poorly Drawn Sketches using Multi-Task Hierarchical Deep Networks


Sep 05, 2017
Ravi Kiran Sarvadevabhatla, Isht Dwivedi, Abhijat Biswas, Sahil Manocha, R. Venkatesh Babu

Figure 1 for SketchParse : Towards Rich Descriptions for Poorly Drawn Sketches using Multi-Task Hierarchical Deep Networks
Figure 2 for SketchParse : Towards Rich Descriptions for Poorly Drawn Sketches using Multi-Task Hierarchical Deep Networks
Figure 3 for SketchParse : Towards Rich Descriptions for Poorly Drawn Sketches using Multi-Task Hierarchical Deep Networks
Figure 4 for SketchParse : Towards Rich Descriptions for Poorly Drawn Sketches using Multi-Task Hierarchical Deep Networks
* A shorter version of this submission was accepted at ACM Multimedia (ACMMM) 2017. Code, annotated datasets and pre-trained models available at https://github.com/val-iisc/sketch-parse 
  Access Paper or Ask Questions

DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data


Jun 07, 2017
Swaminathan Gurumurthy, Ravi Kiran Sarvadevabhatla, Venkatesh Babu Radhakrishnan

Figure 1 for DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data
Figure 2 for DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data
Figure 3 for DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data
Figure 4 for DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data
* Accepted at CVPR-2017. Code for training the GAN models and computing modified inception-scores can be found at https://github.com/val-iisc/deligan 
  Access Paper or Ask Questions

Object category understanding via eye fixations on freehand sketches


Mar 20, 2017
Ravi Kiran Sarvadevabhatla, Sudharshan Suresh, R. Venkatesh Babu

Figure 1 for Object category understanding via eye fixations on freehand sketches
Figure 2 for Object category understanding via eye fixations on freehand sketches
Figure 3 for Object category understanding via eye fixations on freehand sketches
Figure 4 for Object category understanding via eye fixations on freehand sketches
* Accepted for publication in Transactions on Image Processing (http://ieeexplore.ieee.org/document/7866001/) 
  Access Paper or Ask Questions

'Part'ly first among equals: Semantic part-based benchmarking for state-of-the-art object recognition systems


Nov 24, 2016
Ravi Kiran Sarvadevabhatla, Shanthakumar Venkatraman, R. Venkatesh Babu

Figure 1 for 'Part'ly first among equals: Semantic part-based benchmarking for state-of-the-art object recognition systems
Figure 2 for 'Part'ly first among equals: Semantic part-based benchmarking for state-of-the-art object recognition systems
Figure 3 for 'Part'ly first among equals: Semantic part-based benchmarking for state-of-the-art object recognition systems
Figure 4 for 'Part'ly first among equals: Semantic part-based benchmarking for state-of-the-art object recognition systems
* Extended version of our ACCV-2016 paper. Author formatting modified 
  Access Paper or Ask Questions

Enabling My Robot To Play Pictionary : Recurrent Neural Networks For Sketch Recognition


Aug 11, 2016
Ravi Kiran Sarvadevabhatla, Jogendra Kundu, Babu R. Venkatesh

Figure 1 for Enabling My Robot To Play Pictionary : Recurrent Neural Networks For Sketch Recognition
Figure 2 for Enabling My Robot To Play Pictionary : Recurrent Neural Networks For Sketch Recognition
Figure 3 for Enabling My Robot To Play Pictionary : Recurrent Neural Networks For Sketch Recognition
Figure 4 for Enabling My Robot To Play Pictionary : Recurrent Neural Networks For Sketch Recognition
* Accepted at ACMMM 2016. Code and models at https://github.com/val-iisc/sketch-object-recognition 
  Access Paper or Ask Questions

SwiDeN : Convolutional Neural Networks For Depiction Invariant Object Recognition


Jul 29, 2016
Ravi Kiran Sarvadevabhatla, Shiv Surya, Srinivas S S Kruthiventi, Venkatesh Babu R

Figure 1 for SwiDeN : Convolutional Neural Networks For Depiction Invariant Object Recognition
Figure 2 for SwiDeN : Convolutional Neural Networks For Depiction Invariant Object Recognition
Figure 3 for SwiDeN : Convolutional Neural Networks For Depiction Invariant Object Recognition
Figure 4 for SwiDeN : Convolutional Neural Networks For Depiction Invariant Object Recognition
* Accepted at ACMMM 2016. The first two authors contributed equally. Code and models at https://github.com/val-iisc/swiden 
  Access Paper or Ask Questions

A Taxonomy of Deep Convolutional Neural Nets for Computer Vision


Jan 25, 2016
Suraj Srinivas, Ravi Kiran Sarvadevabhatla, Konda Reddy Mopuri, Nikita Prabhu, Srinivas S S Kruthiventi, R. Venkatesh Babu

Figure 1 for A Taxonomy of Deep Convolutional Neural Nets for Computer Vision
Figure 2 for A Taxonomy of Deep Convolutional Neural Nets for Computer Vision
Figure 3 for A Taxonomy of Deep Convolutional Neural Nets for Computer Vision
Figure 4 for A Taxonomy of Deep Convolutional Neural Nets for Computer Vision
* Frontiers in Robotics and AI 2(36), January 2016 
 * Published in Frontiers in Robotics and AI (http://goo.gl/6691Bm) 
  Access Paper or Ask Questions