Publications

2023

• RadFormer: Transformers with global–local attention for interpretable and accurate Gallbladder Cancer detection
  Soumen Basu, Mayank Gupta, Pratyaksha Rana, Pankaj Gupta, Chetan Arora
  Medical Image Analysis, January 2023
  [paper]

• From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instruments
  Britty Baby, Daksh Thapar, Mustafa Chasmai, Tamajit Banerjee, Kunal Dargan, Ashish Suri, Subhashis Banerjee, Chetan Arora
  IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), January 2023
  [paper]

• Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention
  Ashutosh Agarwal, Chetan Arora
  IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), January 2023
  [paper]

• Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shift
  Sharat Agarwal, Saket Anand, Chetan Arora
  IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), January 2023
  [paper]

• ScribbleNet: Efficient interactive annotation of urban city scenes for semantic segmentation
  Bhavani Sambaturu, Ashutosh Gupta, CV Jawahar, Chetan Arora
  Pattern Recognition, January 2023.
  [paper]

2022

• Ultra-high resolution, multi-scale, context-aware approach for detection of small cancers on mammography
  Krithika Rangarajan, Aman Gupta, Saptarshi Dasgupta, Uday Marri, Arun Kumar Gupta, Smriti Hari, Subhashis Banerjee, and Chetan Arora
  Nature Scientific Reports, July 2022.
  [paper]

• Master of All: Simultaneous Generalization of Urban-Scene Segmentation to All Adverse Weather Conditions
  Nikhil Reddy, Abhinav Singhal, Abhishek Kumar, Mahsa Baktashmotlagh, and Chetan Arora
  European Conference on Computer Vision (ECCV), October 2022.
  [paper]

• My View is the Best View: Procedure Learning from Egocentric Videos
  Siddhant Bansal, Chetan Arora, and C.V. Jawahar
  European Conference on Computer Vision (ECCV), October 2022.
  [paper]

• New Objects on the Road? No Problem - We’ll Learn Them Too
  Deepak Kumar Singh, Shyam Nandan Rai, K J Joseph, Rohit Saluja, Vineeth N Balasubramanian, Chetan Arora, Anbumani Subramanian, and C.V. Jawahar
  Accepted for publication in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 2022.
  [paper]

• Representation Learning using Rank Loss for Robust Neurosurgical Skills Evaluation
  Britty Baby, Mustafa Chasmai, Tamajit Banerjee, Ashish Suri, Subhashis Banerjee, and Chetan Arora
  Accepted for publication in International Conference on Image Processing (ICIP), October 2022.
  [paper]

• DepthFormer: Multiscale Vision Transformer for Monocular Depth Estimation with Global Local Information Fusion
  Ashutosh Agarwal, and Chetan Arora
  Accepted for publication in International Conference on Image Processing (ICIP), October 2022.
  [paper]

• A Novel Data Augmentation Technique for Out-of-Distribution Sample Detection using Compounded Corruptions
  Ramya Hebbalaguppe, Soumya Ghosal, Jatin Prakash, Harshad Khadilkar, Chetan Arora
  European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), September 2022.
  [paper]

• Unsupervised Contrastive Learning of Image Representations from Ultrasound Videos with Hard Negative Mining
  Soumen Basu, Somanshu Singla, Mayank Gupta, Pratyaksha Rana, Pankaj Gupta, and Chetan Arora
  International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), September 2022.
  [paper], [project page]

• Merry Go Round: Rotate a Frame and Fool a DNN
  Daksh Thapar, Aditya Nigam, and Chetan Arora
  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2022.
  [paper]

• Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learning
  Soumen Basu, Mayank Gupta, Pratyaksha Rana, Pankaj Gupta, and Chetan Arora
  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2022.
  [paper], [project page]

• A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration
  Ramya Hebbalaguppe, Jatin Prakash, Neelabh Madan, Chetan Arora
  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) [ Oral: acceptance rate 3%]
  [paper],[project page],[Suppl material],[code],[poster], [Video]

• FLUID: Few-Shot Self-Supervised Image Deraining
  Shyam Nandan Rai, Rohit Saluja, Chetan Arora, Vineeth N Balasubramanian, Anbumani Subramanian, and CV Jawahar
  IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), January 2022.
  [paper]

• Attention Guided Cosine Margin To Overcome Class-Imbalance in Few-Shot Road Object Detection
  Ashutosh Agarwal, Anay Majee, Anbumani Subramanian, and Chetan Arora
  IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), January 2022.
  [paper]

• To miss-attend is to misalign! Residual Self-Attentive Feature Alignment for Adapting Object Detectors
  Vaishnavi Khindkar, Chetan Arora, Vineeth N Balasubramanian, Anbumani Subramanian, Rohit Saluja, and CV Jawahar
  IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), January 2022.
  [paper]

• Does Data Repair Lead to Fair Models? Curating Contextually Fair Data To Reduce Model Bias
  Sharat Agarwal, Sumanyu Muku, Saket Anand, and Chetan Arora
  IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), January 2022.
  [paper]

• Multi-Domain Incremental Learning for Semantic Segmentation
  Prachi Garg, Rohit Saluja, Vineeth N Balasubramanian, Chetan Arora, Anbumani Subramanian, and CV Jawahar
  IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), January 2022.
  [paper]

2021

• Comprehensive Telerobotic Ultrasound System for Abdominal Development and in-vivo Feasibility Study
  Deepak Raina, Hardeep Singh, Subir Kumar Saha, Chetan Arora, Ayushi Agarwal, SH Chandrashekhara, Krithika Rangarajan, Suvayan Nandi
  International Symposium on Medical Robotics (ISMR), November 2021.
  [paper], [IIT Delhi Press Release], [Video Demo], [Media Coverage 1], [Media Coverage 2], [Media Coverage 3], [Media Coverage 4], [Media Coverage 5]

• Generating Personalized Summaries of Day Long Egocentric Videos
  Pravin Nagar, Anuj Rathore, CV Jawahar, and Chetan Arora
  IEEE Transactions on Pattern Analysis and Machine Intelligence, October 2021.
  [paper]

• Anonymizing Egocentric Videos
  Daksh Thapar, Aditya Nigam, and Chetan Arora
  IEEE/CVF International Conference on Computer Vision (ICCV), October 2021.
  [paper]

• VmAP: A Fair Metric for Video Object Detection
  Anupam Sobti, Vaibhav Mavi, M Balakrishnan, and Chetan Arora
  ACM International Conference on Multimedia (ACM-MM), October 2021.
  [paper], [code]

• Efficient and Generic Interactive Segmentation Framework to Correct Mispredictions during Clinical Evaluation of Medical Images
  Bhavani Sambaturu, Ashutosh Gupta, CV Jawahar, and Chetan Arora
  International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), September 2021.
  [paper]

• Identifying Physically Realizable Triggers for Backdoored Face Recognition Networks
  Ankita Raj, Ambar Pal, and Chetan Arora
  IEEE International Conference on Image Processing (ICIP), September 2021.
  [paper]

• Artificial Intelligence–assisted chest X-ray assessment scheme for COVID-19
  Krithika Rangarajan, Sumanyu Muku, ..., and Chetan Arora
  European Radiology, January 2021.
  [paper]

2020

• Recognizing Camera Wearer from Hand Gestures in Egocentric Videos
  Daksh Thapar, Aditya Nigam, and Chetan Arora
  ACM International Conference on Multimedia (ACM-MM), October 2020.
  [paper]

• Concept Drift Detection for Multivariate Data Streams and Temporal Segmentation of Daylong Egocentric Videos
  Pravin Nagar, Mansi Khemka, and Chetan Arora
  ACM International Conference on Multimedia (ACM-MM), October 2020.
  [paper]

• Is Sharing of Egocentric Video Giving Away Your Biometric Signature?
  Daksh Thapar, Chetan Arora and Aditya Nigam
  European Conference on Computer Vision (ECCV), August 2020.
  [paper]

• An Inference Algorithm for Multi-Label MRF-MAP Problems with Clique Size 100.
  Ishant Shanu, Siddhant Bharti, Chetan Arora, and S. N. Maheshwari.
  European Conference on Computer Vision (ECCV), August 2020.
  [paper]

• Contextual Diversity for Active Learning.
  Sharat Agarwal, Himanshu Arora, Saket Anand, and Chetan Arora
  European Conference on Computer Vision (ECCV), August 2020.
  [paper]

2019

• Generating 1 Minute Summaries of Day Long Egocentric Videos.
  Anuj Rathore, Pravin Nagar, Chetan Arora, and C.V. Jawahar
  ACM International Conference on Multimedia (ACM-MM), October 2019.
  [paper]

• Multi-sensor Energy Efficient Obstacle Detection
  Anupam Sobti, M. Balakrishnan, and Chetan Arora
  Euromicro Conference on Digital System Design (DSD), August 2019.
  [paper]

• MAVI: Mobility Assistant for Visually Impaired with Optional Use of Local and Cloud Resources.
  Rajesh Kedia, Anupam Sobti, Mukund Rungta, Sarvesh Chandoliya, Akhil Soni, Anil Kumar Meena, Chrystle Myrna Lobo, Richa Verma, M. Balakrishnan, and Chetan Arora
  International Conference on VLSI Design (VLSID), January 2019.
  [paper]

• EGO-SLAM: A Robust Monocular SLAM for Egocentric Videos.
  Suvam Patra, Kartikeya Gupta, Faran Ahmad, Chetan Arora, and Subhashis Banerjee
  IEEE Winter Conference on Applications of Computer Vision (WACV), January 2019.
  [paper]

2018

• Exploiting Texture Cues for Clothing Parsing in Fashion Images
  Tarasha Khurana, Kushagra Mahajan, Chetan Arora, and Atul Rai
  International Conference on Image Processing (ICIP), October 2018.
  [paper]

• Pose Aware Fine-Grained Visual Classification Using Pose Experts
  Kushagra Mahajan, Tarasha Khurana, Ayush Chopra, Isha Gupta, Chetan Arora, and Atul Rai
  International Conference on Image Processing (ICIP), October 2018.
  [paper]

• Diversity in Fashion Recommendation using Semantic Parsing
  Sagar Verma, Sukhad Anand, Chetan Arora, and Atul Rai
  International Conference on Image Processing (ICIP), October 2018.
  [paper]

• U-SegNet: Fully Convolutional Neural Network based Automated Brain tissue segmentation Tool
  Pulkit Kumar, Pravin Nagar, Chetan Arora, and Anubha Gupta
  International Conference on Image Processing (ICIP), October 2018.
  [paper]

• Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos
  Sagar Verma, Pravin Nagar, Divam Gupta, and Chetan Arora
  International Conference on Image Processing (ICIP), October 2018.
  [paper]

• Making Deep Neural Network Fooling Practical
  Ambar Pal, and Chetan Arora
  International Conference on Image Processing (ICIP), October 2018.
  [paper]

• Inference in Higher Order MRF-MAP Problems with Small and Large Cliques
  Ishant Shanu, Chetan Arora, and S.N. Maheshwari
  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
  [paper]

• Stabilizing First Person 360 Degree Videos
  Chetan Arora, and Vivek Kwatra
  IEEE Winter Conference on Applications of Computer Vision (WACV), March 2018.
  [paper], [demo video]

• Learning Higher Order Potentials For MRFs
  Dinesh Khandelwal, Chetan Arora, and Parag Singla
  IEEE Winter Conference on Applications of Computer Vision (WACV), March 2018.
  [paper]

• A Joint 3D-2D based Method for Free Space Detection on Roads
  Suvam Patra, Pranjal Maheshwari, Shashank Yadav, Subhashis Banerjee, and Chetan Arora
  IEEE Winter Conference on Applications of Computer Vision (WACV), March 2018.
  [paper]

• Object Detection in Real-Time Systems: Going Beyond Precision
  Anupam Sobti, Chetan Arora, and M. Balakrishnan
  IEEE Winter Conference on Applications of Computer Vision (WACV), March 2018.
  [paper]

2017

• Deep CNN with Color Lines Model for Unmarked Road Segmentation
  Shashank Yadav, Suvam Patra, Chetan Arora, and Subhashis Banerjee.
  International Conference on Image Processing (ICIP), September 2017.
  [paper]

• Unsupervised Learning of Deep Feature Representation for Clustering Egocentric Actions
  Bharat Bhatnagar, Suriya Singh, Chetan Arora, and C.V. Jawahar.
  International Joint Conference on Artificial Intelligence (IJCAI), August 2017.
  [paper]

• Trajectory Aligned Features For First Person Action Recognition
  Suriya Singh, Chetan Arora, and C.V. Jawahar.
  Pattern Recognition, February 2017.
  [paper], [project page]

• MAVI: An Embedded Device to Assist Mobility of Visually Impaired,
  Rajesh Kedia, K.K. Yoosuf, P. Dedeepya, M. Fazal, Chetan Arora, and M. Balakrishnan.
  16th IEEE International Conference on Embedded Systems and VLSI Design, January 2017.
  [paper]

• EgoSampling: Wide View Hyperlapse from Single and Multiple Egocentric Videos
  Tavi Halperin, Yair Poleg, Chetan Arora, and Shmuel Peleg.
  IEEE Transactions on Circuits and Systems for Video Technology, January 2017.
  [paper]

• Computing Egomotion with Local Loop Closures for Egocentric Videos,
  Suvam Patra, Himanshu Aggarwal, Himani Arora, Chetan Arora and Subhashis Banerjee.
  IEEE Winter Conference on Applications of Computer Vision (WACV), March 2017.
  [paper]

2016

• First Person Action Recognition Using Deep Learned Descriptors
  Suriya Singh, Chetan Arora and C.V. Jawahar
  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2016.
  [paper], [project page]

• Min Norm Point Algorithm for Higher Order MRF-MAP Inference
  Ishant Shanu, Chetan Aora and Parag Singla
  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2016.
  [paper], [project page]

• Compact CNN for Indexing Egocentric Videos
  Yair Poleg, Ariel Ephrat, Shmuel Peleg and Chetan Arora
  IEEE Winter Conference on Applications of Computer Vision (WACV), March 2016.
  [paper], [project page]

• Lazy Generic Cuts
  Dinesh Khandelwal, Kush Bhatia, Chetan Arora, and Parag Singla,
  Computer Vision and Image Understanding (CVIU), 2016
  [paper]

Before 2016

• Generic Action Recognition from Egocentric Videos
  Suriya Singh, Chetan Arora, and C.V. Jawahar
  Fifth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), December 2015.
  [paper], [project page]

• EgoSampling: Fast-Forward and Stereo for Egocentric Videos,
  Yair Poleg, Tavi Halperin, Chetan Arora, and Shmuel Peleg,
  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2015.
  [paper], [project page]

• Generalized Flows for Optimal Inference in Higher Order MRF-MAP
  Chetan Arora, Subhashis Banerjee, Prem Kalra, and S.N. Maheshwari
  IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2015
  [paper]

• Head Motion Signatures from Egocentric Videos
  Yair Poleg, Chetan Arora, and Shmuel Peleg
  Asian Conference on Computer Vision (ACCV), November 2014.
  [paper], [poster]

• Optical Flow for non Lambertian surfaces by cancelling illuminant chromaticity
  Chetan Arora and Michael Werman
  IEEE International Conference on Image Processing (ICIP), October 2014.
  [paper]

• Multi Label Generic Cuts: Optimal Inference in Multi Label Multi Clique MRF-MAP Problems
  Chetan Arora and S.N. Maheshwari,
  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2014.
  [paper], [project page]

• Fast Approximate Inference in Higher Order MRF-MAP Labeling Problems
  Chetan Arora, Subhashis Banerjee, Prem Kalra, and S.N. Maheshwari
  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2014.
  [paper], [project page],

• Temporal Segmentation of Egocentric Video
  Yair Poleg, Chetan Arora, and Shmuel Peleg
  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2014.
  [paper], [poster], [project page]

• Higher Order Matching for Consistent Multiple Target Tracking
  Chetan Arora and Amir Globerson
  IEEE International Conference on Computer Vision (ICCV), December 2013.
  [paper]

• Efficient Representation of Distributions for Background Subtraction
  Yedid Hoshen, Chetan Arora, Yair Poleg, and Shmuel Peleg
  IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), September 2013.
  
  [paper]

• Generic Cuts: An Efficient Optimal Algorithm for Submodular MRF-MAP Problems with Higher Order Cliques
  Chetan Arora, Subhashis Banerjee, Prem Kalra, and S.N. Maheshwari,
  European Conference on Computer Vision (ECCV), October 2012.
  [paper], [project page]

• An Efficient Graph Cut Algorithm for Computer Vision Problems
  Chetan Arora, Subhashis Banerjee, Prem Kalra, and S.N. Maheshwari,
  European Conference on Computer Vision (ECCV), September 2010.
  [paper]

• Rectified Mosaicing: Mosaics without the Curl
  Assaf Zomet, Shmuel Peleg, Chetan Arora, and Takeo Miyazawa
  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2000.
  [paper]

• Image: An Extensible Agent-based Architecture for Image Retrieval
  Hiranmay Ghosh, Santanu Chaudhury, Chetan Arora, and Paramjeet Nirankari
  International Journal on Digital Libraries (IJODL), 2000.
  [paper]

• Content based Image Retrieval using Mobile Agents
  Chetan Arora, Paramjeet Nirankari, Hiranmay Ghosh, and Santanu Chaudhury
  3rd International Conference on Computational Intelligence and Multimedia Applications (ICCIMA), 1999.
  [paper]