no code implementations • ECCV 2020 • Daksh Thapar, Chetan Arora, Aditya Nigam
In this work, we create a novel kind of privacy attack by extracting the wearer’s gait profile, a well known biometric signature, from such optical flow in the egocentric videos.
1 code implementation • ECCV 2020 • Ishant Shanu, Siddhant Bharti, Chetan Arora, S. N. Maheshwari
Earlier algorithms based on this transformation could not handle problems larger than 16 labels on cliques of size 4.
no code implementations • 25 Apr 2024 • Jaime Spencer, Fabio Tosi, Matteo Poggi, Ripudaman Singh Arora, Chris Russell, Simon Hadfield, Richard Bowden, Guangyuan Zhou, Zhengxin Li, Qiang Rao, Yiping Bao, Xiao Liu, Dohyeong Kim, Jinseong Kim, Myunghyun Kim, Mykola Lavreniuk, Rui Li, Qing Mao, Jiang Wu, Yu Zhu, Jinqiu Sun, Yanning Zhang, Suraj Patni, Aradhye Agarwal, Chetan Arora, Pihai Sun, Kui Jiang, Gang Wu, Jian Liu, Xianming Liu, Junjun Jiang, Xidan Zhang, Jianing Wei, Fangjun Wang, Zhiming Tan, Jiabao Wang, Albert Luginov, Muhammad Shahzad, Seyed Hosseini, Aleksander Trajcevski, James H. Elder
This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC).
no code implementations • 9 Apr 2024 • Alessio Ferrari, Sallam Abualhaija, Chetan Arora
Complementing natural language (NL) requirements with graphical models can improve stakeholders' communication and provide directions for system design.
1 code implementation • 27 Mar 2024 • Suraj Patni, Aradhye Agarwal, Chetan Arora
We argue that the embedding vector from a ViT model, pre-trained on a large dataset, captures greater relevant information for SIDE than the usual route of generating pseudo image captions, followed by CLIP based text embeddings.
Ranked #5 on Monocular Depth Estimation on NYU-Depth V2
1 code implementation • 13 Mar 2024 • Soumen Basu, Mayuna Gupta, Chetan Madan, Pankaj Gupta, Chetan Arora
We validate the proposed methods on the curated dataset, and report a new state-of-the-art (SOTA) accuracy of 96. 4% for the GBC detection problem, against an accuracy of 84% by current Image-based SOTA - GBCNet, and RadFormer, and 94. 7% by Video-based SOTA - AdaMAE.
no code implementations • 16 Jan 2024 • Ali Rezaei Nasab, Maedeh Dashti, Mojtaba Shahin, Mansooreh Zahedi, Hourieh Khalajzadeh, Chetan Arora, Peng Liang
Finally, the manual analysis of 2, 248 app owners' responses to the fairness reviews identified six root causes (e. g., 'copyright issues') that app owners report to justify fairness concerns.
1 code implementation • 8 Nov 2023 • Akshit Jindal, Vikram Goyal, Saket Anand, Chetan Arora
In this work, we explore the usage of an ensemble of deep learning models as our thief model.
no code implementations • 6 Nov 2023 • Siddhant Bansal, Chetan Arora, C. V. Jawahar
Given multiple videos of the same task, procedure learning addresses identifying the key-steps and determining their order to perform the task.
no code implementations • 1 Nov 2023 • Hira Naveed, Chetan Arora, Hourieh Khalajzadeh, John Grundy, Omar Haggag
Through this SLR, we wanted to analyze existing studies, including their motivations, MDE solutions, evaluation techniques, key benefits and limitations.
no code implementations • 11 Sep 2023 • Soumen Basu, Ashish Papanai, Mayank Gupta, Pankaj Gupta, Chetan Arora
We posit that even when we have only the image level label, still formulating the problem as object detection (with bounding box output) helps a deep neural network (DNN) model focus on the relevant region of interest.
1 code implementation • 27 Jun 2023 • Abdur Rahman, Arjun Ghosh, Chetan Arora
To address the limitations of previous works, which struggle to generalize to the intricacies of the Urdu script and the lack of sufficient annotated real-world data, we have introduced the UTRSet-Real, a large-scale annotated real-world dataset comprising over 11, 000 lines and UTRSet-Synth, a synthetic dataset with 20, 000 lines closely resembling real-world and made corrections to the ground truth of the existing IIITH dataset, making it a more reliable resource for future research.
Ranked #1 on Printed Text Recognition on UPTI
no code implementations • 18 Mar 2023 • Yaohou Fan, Chetan Arora, Christoph Treude
In this work, we investigate the usefulness of stop word removal in a software engineering context.
no code implementations • 6 Mar 2023 • Khlood Ahmad, Mohamed Abdelrazek, Chetan Arora, Arbind Agrahari Baniya, Muneera Bano, John Grundy
[Method] In this paper, we present a new framework developed based on human-centered AI guidelines and a user survey to aid in collecting requirements for human-centered AI-based software.
no code implementations • 26 Nov 2022 • Britty Baby, Daksh Thapar, Mustafa Chasmai, Tamajit Banerjee, Kunal Dargan, Ashish Suri, Subhashis Banerjee, Chetan Arora
Minimally invasive surgeries and related applications demand surgical tool classification and segmentation at the instance level.
1 code implementation • 9 Nov 2022 • Soumen Basu, Mayank Gupta, Pratyaksha Rana, Pankaj Gupta, Chetan Arora
We propose a novel deep neural network architecture to learn interpretable representation for medical image analysis.
1 code implementation • 17 Oct 2022 • Ashutosh Agarwal, Chetan Arora
Typically, a skip connection module is used to fuse the encoder and decoder features, which comprises of feature map concatenation followed by a convolution operation.
Ranked #19 on Monocular Depth Estimation on KITTI Eigen split (using extra training data)
1 code implementation • 13 Oct 2022 • Sharat Agarwal, Saket Anand, Chetan Arora
In this work, we propose an ADA strategy, which given a frame, identifies a set of classes that are hardest for the model to predict accurately, thereby recommending semantically meaningful regions to be annotated in a selected frame.
1 code implementation • 28 Jul 2022 • Ramya S. Hebbalaguppe, Soumya Suvra Goshal, Jatin Prakash, Harshad Khadilkar, Chetan Arora
One of the major advantages of CnC is that it does not require any hold-out data apart from the training set.
1 code implementation • 26 Jul 2022 • Soumen Basu, Somanshu Singla, Mayank Gupta, Pratyaksha Rana, Pankaj Gupta, Chetan Arora
We further validate the generalizability of our method on a publicly available lung US image dataset of COVID-19 pathologies and show an improvement of 1. 5% compared to SOTA.
1 code implementation • 22 Jul 2022 • Siddhant Bansal, Chetan Arora, C. V. Jawahar
Instead, we propose to use the signal provided by the temporal correspondences between key-steps across videos.
1 code implementation • 10 Jul 2022 • Ashutosh Agarwal, Chetan Arora
We also propose a Transbins module that divides the depth range into bins whose center value is estimated adaptively per image.
Ranked #29 on Monocular Depth Estimation on KITTI Eigen split (using extra training data)
no code implementations • 21 Jun 2022 • Saad Ezzini, Sallam Abualhaija, Chetan Arora, Mehrdad Sabetzadeh
We introduce TAPHSIR, a tool for anaphoric ambiguity detection and anaphora resolution in requirements.
1 code implementation • CVPR 2022 • Soumen Basu, Mayank Gupta, Pratyaksha Rana, Pankaj Gupta, Chetan Arora
However, USG images are challenging to analyze due to low image quality, noise, and varying viewpoints due to the handheld nature of the sensor.
Ranked #1 on Gallbladder Cancer Detection on GBCU
1 code implementation • CVPR 2022 • Ramya Hebbalaguppe, Jatin Prakash, Neelabh Madan, Chetan Arora
We show that training with MDCA leads to better-calibrated models in terms of Expected Calibration Error ( ECE ), and Static Calibration Error ( SCE ) on image classification, and segmentation tasks.
no code implementations • 22 Feb 2022 • Ngoc Dung Huynh, Mohamed Reda Bouadjenek, Imran Razzak, Kevin Lee, Chetan Arora, Ali Hassani, Arkady Zaslavsky
Indeed, Adversarial Artificial Intelligence (AI) which refers to a set of techniques that attempt to fool machine learning models with deceptive data, is a growing threat in the AI and machine learning research community, in particular for machine-critical applications.
1 code implementation • WACV 2022 • Vaishnavi Khindkar, Chetan Arora, Vineeth N Balasubramanian, Anbumani Subramanian, C. V. Jawahar
Qualitative results demonstrate the ability of ILLUME to attend important object instances required for alignment.
no code implementations • CVPR 2022 • Daksh Thapar, Aditya Nigam, Chetan Arora
On the other hand DNNs are known to be susceptible to Adversarial Attacks (AAs) which add im-perceptible noise to the input.
no code implementations • 12 Nov 2021 • Ashutosh Agarwal, Anay Majee, Anbumani Subramanian, Chetan Arora
To overcome these pitfalls in metric learning based FSOD techniques, we introduce Attention Guided Cosine Margin (AGCM) that facilitates the creation of tighter and well separated class-specific feature clusters in the classification head of the object detector.
1 code implementation • 23 Oct 2021 • Prachi Garg, Rohit Saluja, Vineeth N Balasubramanian, Chetan Arora, Anbumani Subramanian, C. V. Jawahar
Recent efforts in multi-domain learning for semantic segmentation attempt to learn multiple geographical datasets in a universal, joint model.
1 code implementation • 20 Oct 2021 • Sharat Agarwal, Sumanyu Muku, Saket Anand, Chetan Arora
Through a series of experiments, we validate that curating contextually fair data helps make model predictions fair by balancing the true positive rate for the protected class across groups without compromising on the model's overall performance.
no code implementations • 6 Aug 2021 • Bhavani Sambaturu, Ashutosh Gupta, C. V. Jawahar, Chetan Arora
We report a time saving of 2. 8, 3. 0, 1. 9, 4. 4, and 8. 6 fold compared to other interactive segmentation techniques.
no code implementations • ICCV 2021 • Daksh Thapar, Aditya Nigam, Chetan Arora
In a more damaging scenario, one can even recognize a wearer using hand gestures from egocentric videos, or identify a wearer in third person videos such as from a surveillance camera.
1 code implementation • ECCV 2020 • Sharat Agarwal, Himanshu Arora, Saket Anand, Chetan Arora
Contextual Diversity (CD) hinges on a crucial observation that the probability vector predicted by a CNN for a region of interest typically contains information from a larger receptive field.
5 code implementations • 21 Apr 2020 • Arpan Mangal, Surya Kalia, Harish Rajgopal, Krithika Rangarajan, Vinay Namboodiri, Subhashis Banerjee, Chetan Arora
This may be useful in an inpatient setting where the present systems are struggling to decide whether to keep the patient in the ward along with other patients or isolate them in COVID-19 areas.
1 code implementation • 18 Oct 2019 • Sagar Verma, Sukhad Anand, Chetan Arora, Atul Rai
In this paper, we propose to recommend images by explicitly learning and exploiting part based similarity.
1 code implementation • 17 Oct 2019 • Sagar Verma, Pravin Nagar, Divam Gupta, Chetan Arora
Unlike third person domain, researchers have divided first-person actions into two categories: involving hand-object interactions and the ones without, and developed separate techniques for the two action categories.
no code implementations • 24 Nov 2018 • Dinesh Khandelwal, Suyash Agrawal, Parag Singla, Chetan Arora
Designing such a network, as well as collecting jointly labeled data for training is a non-trivial task.
no code implementations • 12 Jun 2018 • Pulkit Kumar, Pravin Nagar, Chetan Arora, Anubha Gupta
Automated brain tissue segmentation into white matter (WM), gray matter (GM), and cerebro-spinal fluid (CSF) from magnetic resonance images (MRI) is helpful in the diagnosis of neuro-disorders such as epilepsy, Alzheimer's, multiple sclerosis, etc.
no code implementations • CVPR 2018 • Ishant Shanu, Chetan Arora, S. N. Maheshwari
Two popular combinatorial approaches for solving such formulations are flow based and polyhedral approaches.
no code implementations • 6 Nov 2017 • Suvam Patra, Pranjal Maheshwari, Shashank Yadav, Chetan Arora, Subhashis Banerjee
Finally, we use the obtained road segmentation with the 3D depth data from monocular SLAM to detect the free space for the navigation purposes.
no code implementations • 18 Jul 2017 • Suvam Patra, Kartikeya Gupta, Faran Ahmad, Chetan Arora, Subhashis Banerjee
The incremental nature of SOTA SLAM, in the presence of unreliable pose and 3D estimates in egocentric videos, with no opportunities for global loop closures, generates drifts and leads to the eventual failures of such techniques.
no code implementations • 17 Jan 2017 • Suvam Patra, Himanshu Aggarwal, Himani Arora, Chetan Arora, Subhashis Banerjee
Finding the camera pose is an important step in many egocentric video applications.
no code implementations • CVPR 2016 • Suriya Singh, Chetan Arora, C. V. Jawahar
It can also be trained from relatively small number of labeled egocentric videos that are available.
no code implementations • CVPR 2016 • Ishant Shanu, Chetan Arora, Parag Singla
Current state of the art inference algorithms for general submodular function takes many hours for problems with clique size 16, and fail to scale beyond.
no code implementations • 26 Apr 2016 • Tavi Halperin, Yair Poleg, Chetan Arora, Shmuel Peleg
However, this accentuates the shake caused by natural head motion in an egocentric video, making the fast forwarded video useless.
no code implementations • 7 Apr 2016 • Suriya Singh, Chetan Arora, C. V. Jawahar
Objects present in the scene and hand gestures of the wearer are the most important cues for first person action recognition but are difficult to segment and recognize in an egocentric video.
no code implementations • 28 Apr 2015 • Yair Poleg, Ariel Ephrat, Shmuel Peleg, Chetan Arora
Furthermore, our CNN is able to recognize whether a video is egocentric or not with 99. 2% accuracy, up by 24% from current state-of-the-art.
no code implementations • CVPR 2015 • Yair Poleg, Tavi Halperin, Chetan Arora, Shmuel Peleg
While egocentric cameras like GoPro are gaining popularity, the videos they capture are long, boring, and difficult to watch from start to end.
no code implementations • CVPR 2014 • Yair Poleg, Chetan Arora, Shmuel Peleg
Two sources of information for video segmentation are (i) the motion of the camera wearer, and (ii) the objects and activities recorded in the video.
no code implementations • CVPR 2014 • Chetan Arora, Subhashis Banerjee, Prem Kalra, S. N. Maheshwari
Generic Cuts (GC) of Arora et al. [9] shows that when potentials are submodular, inference problems can be solved optimally in polynomial time for fixed size cliques.
no code implementations • CVPR 2014 • Chetan Arora, S. N. Maheshwari
We exploit sparseness in the feasible configurations of the transformed 2-label problem to suggest an improvement to Generic Cuts [3] to solve the 2-label problems efficiently.