Recent Publications


Pritish Sahu, Michael Cogswell, Yunye Gong, Ajay Divakaran

Unpacking Large Language Models with Conceptual Consistency


https://arxiv.org/abs/2209.15093



Ajay Divakaran, Aparna Sridhar, Ramya Srinivasan:

Broadening AI Ethics Narratives: An Indic Art View. CoRR abs/2204.03789 (2022)

https://arxiv.org/abs/2204.03789


Manoj Acharya, Anirban Roy, Kaushik Koneripalli, Susmit Jha, Christopher Kanan, Ajay Divakaran

IJCAI 2022

Detecting out-of-context objects using graph contextual reasoning network

https://arxiv.org/abs/2202.05930


Meng Ye, Xiao Lin, Giedrius Burachas, Ajay Divakaran, Yi Yao; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 2726-2735

Received Best Paper award from workshop

https://arxiv.org/pdf/2011.10082.pdf


Arijit Ray, Michael Cogswell, Xiao Lin, Kamran Alipour, Ajay Divakaran, Yi Yao, Giedrius Burachas, Knowing What VQA Does Not: Pointing to Error-Inducing Regions to Improve Explanation Helpfulness, 2021 Applied AI Letters (Wiley), [pdf] [arXiv] [Project Page]


Sujeong Kim, Abhinav Garlapati, Jonah Lubin, Amir Tamrakar, Ajay Divakaran, Towards Understanding Confusion and Affective States Under Communication Failures in Voice-Based Human-Machine Interaction, 2021 9th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)


A. Som, S. Kim, B. Lopez-Prado, S. Dhamija, N. Alozie, A. Tamrakar. "Automated Student Group Collaboration Assessment and Recommendation System Using Individual Role and Behavioral Cues". Frontiers in Computer Science, 2021.

A.Som, S. Kim, B. Lopez-Prado, S. Dhamija, N. Alozie, A. Tamrakar. "Towards Explainable Student Group Collaboration Assessment Models Using Temporal Representations of Individual Student Roles". Educational Data Mining (EDM) Conference, 2021.

Pritish Sahu, Michael Cogswell, Sara Rutherford-Quach, Ajay Divakaran

Comprehension Based Question Answering using Bloom's Taxonomy, 6th Workshop on Representation Learning for NLP, 2021

https://arxiv.org/abs/2106.04653

.

5:04

Towards Solving Multimodal Comprehension, arXiv

arXiv.org

Towards Solving Multimodal Comprehension

This paper targets the problem of procedural multimodal machine comprehension (M3C). This task requires an AI to comprehend given steps of multimodal instructions and then answer questions....

5:04

WACV 2022

Challenges in Procedural Multimodal Machine Comprehension: A Novel Way

Pritish Sahu, Karan Sikka, Ajay Divakaran

https://openaccess.thecvf.com/content/WACV2022/html/Sahu_Challenges_in_Procedural_Multimodal_Machine_Comprehension_A_Novel_Way_To_WACV_2022_paper.html

Pritish Sahu, Karan Sikka, Ajay Divakaran

Towards Multimodal Comprehension

Abstract

PDF

ICCV 2021

Yunye Gong, Xiao Lin, Yi Yao, Thomas G. Dietterich, Ajay Divakaran, Melinda Gervasio

Confidence Calibration for Cross-Domain Generalization under Covariate Shift (To appear at ICCV 2021)

Abstract

PDF

https://openaccess.thecvf.com/content/ICCV2021/html/Gong_Confidence_Calibration_for_Domain_Generalization_Under_Covariate_Shift_ICCV_2021_paper.html

Xiao Lin, Meng Ye, Yunye Gong, Giedrius Buracas, Nikoletta Basiou, Ajay Divakaran, Yi Yao

Modular Adaptation for Cross-Domain Few-Shot Learning

Abstract

PDF

Arijit Ray, Michael Cogswell, Xiao Lin, Kamran Alipour, Ajay Divakaran, Yi Yao, Giedrius Burachas

Knowing What VQA Does Not: Pointing to Error-Inducing Regions to Improve Explanation Helpfulness

Abstract

PDF

Karan Sikka, Indranil Sur, Susmit Jha, Anirban Roy, Ajay Divakaran,

Detecting Trojaned DNNs Using Counterfactual Attributions, arXiv:2012.02275

PDF

Pritish Sahu, Michael Cogswell, Sara Rutherford-Quach, Ajay Divakaran

Comprehension Based Question Answering using Bloom's Taxonomy

To Appear at the 6th Workshop on Representation Learning for NLP, 2021


Abstract

PDF



Pritish Sahu, Karan Sikka, Ajay Divakaran

Towards Multimodal Comprehension

Abstract

PDF


ICCV 2021

Yunye Gong, Xiao Lin, Yi Yao, Thomas G. Dietterich, Ajay Divakaran, Melinda Gervasio

Confidence Calibration for Cross-Domain Generalization under Covariate Shift (To appear at ICCV 2021)

Abstract

PDF



Xiao Lin, Meng Ye, Yunye Gong, Giedrius Buracas, Nikoletta Basiou, Ajay Divakaran, Yi Yao

Modular Adaptation for Cross-Domain Few-Shot Learning

Abstract

PDF


Arijit Ray, Michael Cogswell, Xiao Lin, Kamran Alipour, Ajay Divakaran, Yi Yao, Giedrius Burachas

Knowing What VQA Does Not: Pointing to Error-Inducing Regions to Improve Explanation Helpfulness

Abstract

PDF


Karan Sikka, Indranil Sur, Susmit Jha, Anirban Roy, Ajay Divakaran,

Detecting Trojaned DNNs Using Counterfactual Attributions, arXiv:2012.02275

PDF

Karan Sikka, Jihua Huang, Andrew Silberfarb, Prateeth Nayak, Luke Rohrer, Pritish Sahu, John Byrnes, Ajay Divakaran, Richard Rohwer , "Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings," arXiv:2011.10889

PDF

Meng Ye, Xiao Lin, Giedrius Burachas, Ajay Divakaran, Yi Yao, "Hybrid Consistency Training with Prototype Adaptation for Few-Shot Learning," Arxiv submission November 2020

https://arxiv.org/abs/2011.10082

PDF

4th Life Long Machine Learning Workshop at ICML 2020


Raghavan, A., Hostetler, J., Sur, I., Rahman, A., & Divakaran, A. (2020). Lifelong Learning using Eigentasks:Task Separation, Skill Acquisition, and Selective Transfer. 4th Lifelong Machine Learning Workshop, Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR, 8.

Paper link:

https://openreview.net/pdf?id=SD7m4B3kGiQ

video for the paper:

https://www.youtube.com/watch?v=IsO2Yz4z43Q

DASL

Karan Sikka, Andrew Silberfarb, John Byrnes, Indranil Sur, Edmond Chow, Ajay Divakaran, Richard Rohwer

Deep Adaptive Semantic Logic (DASL) : Compiling Declarative Knowledge into Deep Neural Networks

https://arxiv.org/abs/2003.07344

ICLR 2020 Workshop on Integration of Deep Neural Models and Differential Equations.

Hammad Ayyubi, Yi Yao, Ajay Divakaran

Progressive Growing of Neural ODE's

http://arxiv.org/abs/2003.03695


WACV 2019

Pallabi Ghosh, Yi Yao, Larry S. Davis, Ajay Divakaran:

Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation.

https://arxiv.org/pdf/1811.10575v1.pdf

WACV poster presentation at 24:25

https://www.youtube.com/watch?v=zZDhauFsOUo


FoodX-251: A Dataset for Fine-grained Food Classification

https://arxiv.org/abs/1907.06167


"Brain to Brain" communications

Xiao Lin, Indranil Sur, Samuel A. Nastase, Ajay Divakaran, Uri Hasson, Mohamed R. Amer:

Data-Efficient Mutual Information Neural Estimator.

https://arxiv.org/abs/1905.03319

Karan Sikka, Lucas Van Bramer, Ajay Divakaran

Deep Unified Multimodal Embeddings for Understanding both Content and Users in Social Media Networks

https://arxiv.org/abs/1905.07075

Demo Video

https://youtu.be/8pM78EVpErQ

MatchStax Multimodal Embedding API

Video Retrieval with MatchStax

https://www.youtube.com/watch?v=NFmM4ZlMPTY

Cross-Platform (Instagram-Twitter) Retrieval with Matchstax

https://youtu.be/4rpEhQ6_RyY

EMNLP 2019

Julia Kruk, Jonah Lubin, Karan Sikka, Xiao Lin, Dan Jurafsky, Ajay Divakaran:

Integrating Text and Image: Determining Multimodal Document Intent in Instagram Posts.

https://arxiv.org/abs/1904.09073

Demo Video

https://youtu.be/kwx3dquSQ7M


ICCV 2019

Samyak Datta, Karan Sikka, Anirban Roy, Karuna Ahuja, Devi Parikh, Ajay Divakaran:

Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment.

https://arxiv.org/abs/1903.11649


ECCV 2018

Ankan Bansal, Karan Sikka, Gaurav Sharma, Rama Chellappa, Ajay Divakaran:

Zero-Shot Object Detection. ECCV (1) 2018: 397-414

https://www.researchgate.net/publication/324492738_Zero-Shot_Object_Detection


ICMI 2015

Behjat Siddiquie, Dave Chisholm, Ajay Divakaran:

Exploiting Multimodal Affect and Semantics to Identify Politically Persuasive Web Videos. ICMI 2015: 203-210

https://drive.google.com/open?id=0B1TzavQVNsXGcVFmR3RBNy1QdWc

ICME 2015

Dave Chisholm, Behjat Siddiquie, Ajay Divakaran, Elizabeth Shriberg:

Audio-based affect detection in web videos. ICME 2015: 1-6

https://drive.google.com/open?id=0B1TzavQVNsXGdmFLVzJ4SmNldlk