Publications

2022

  1. Dual-Key Multimodal Backdoors for Visual Question Answering
    Walmer, Matthew, Sikka, Karan, Sur, Indranil, Shrivastava, Abhinav, and Jha, Susmit
    In CVPR 2022
    PDF
  2. Challenges in Procedural Multimodal Machine Comprehension: A Novel Way To Benchmark
    Sahu, Pritish, Sikka, Karan, and Divakaran, Ajay
    In WACV 2022
    PDF Supp

2021

  1. Towards solving multimodal comprehension
    Sahu, Pritish, Sikka, Karan, and Divakaran, Ajay
    arXiv 2021
    PDF
  2. MISA: Online Defense of Trojaned Models using Misattributions
    Kiourti, Panagiota, Li, Wenchao, Roy, Anirban, Sikka, Karan, and Jha, Susmit
    In Annual Computer Security Applications Conference 2021
    PDF
  3. Resilient Data Augmentation Approaches to Multimodal Verification in the News Domain
    Cadigan, John, Sikka, Karan, Ye, Meng, and Graciarena, Martin
    In ICCV Workshops 2021
    PDF

2020

  1. Deep adaptive semantic logic (dasl): Compiling declarative knowledge into deep neural networks
    Sikka, Karan, Silberfarb, Andrew, Byrnes, John, Sur, Indranil, Chow, Ed, Divakaran, Ajay, and Rohwer, Richard
    arXiv 2020
    PDF
  2. Rgb2lidar: Towards solving large-scale cross-modal visual localization
    (Best Paper Finalist)
    Mithun, Niluthpol Chowdhury, Sikka, Karan, Chiu, Han-Pang, Samarasekera, Supun, and Kumar, Rakesh
    In ACMM 2020
    PDF
  3. Zero-shot learning with knowledge enhanced visual semantic embeddings
    Sikka, Karan, Huang, Jihua, Silberfarb, Andrew, Nayak, Prateeth, Rohrer, Luke, Sahu, Pritish, Byrnes, John, Divakaran, Ajay, and Rohwer, Richard
    arXiv 2020
    PDF
  4. Detecting trojaned dnns using counterfactual attributions
    Sikka, Karan, Sur, Indranil, Jha, Susmit, Roy, Anirban, and Divakaran, Ajay
    arXiv 2020
    PDF

2019

  1. Align2ground: Weakly supervised phrase grounding guided by image-caption alignment
    Datta, Samyak, Sikka, Karan, Roy, Anirban, Ahuja, Karuna, Parikh, Devi, and Divakaran, Ajay
    In ICCV 2019
    PDF
  2. Integrating text and image: Determining multimodal document intent in instagram posts
    Kruk, Julia, Lubin, Jonah, Sikka, Karan, Lin, Xiao, Jurafsky, Dan, and Divakaran, Ajay
    EMNLP 2019
    PDF Video DATASET Website
  3. Deep Unified Multimodal Embeddings for Understanding both Content and Users in Social Media Networks
    Sikka, Karan, Van Bramer, Lucas, and Divakaran, Ajay
    arXiv 2019
    PDF Video
  4. Foodx-251: a dataset for fine-grained food classification
    Kaur, Parneet, Sikka, Karan, Wang, Weijun, Belongie, Serge, and Divakaran, Ajay
    CVPR Workshops 2019
    PDF DATASET
  5. Sunny and dark outside?! improving answer consistency in vqa through entailed question generation
    Ray, Arijit, Sikka, Karan, Divakaran, Ajay, Lee, Stefan, and Burachas, Giedrius
    EMNLP 2019
    PDF DATASET Website
  6. Semantically-Aware Attentive Neural Embeddings for Long-Term 2D Visual Localization
    Seymour, Zachary, Sikka, Karan, Chiu, Han-Pang, Samarasekera, Supun, and Kumar, Rakesh
    In BMVC 2019
    PDF

2018

  1. Zero-shot object detection
    Bansal, Ankan, Sikka, Karan, Sharma, Gaurav, Chellappa, Rama, and Divakaran, Ajay
    In ECCV 2018
    PDF
  2. Understanding visual ads by aligning symbols and objects using co-attention
    Ahuja, Karuna, Sikka, Karan, Roy, Anirban, and Divakaran, Ajay
    In CVPR Workshops 2018
    PDF
  3. Make up your mind: Towards consistent answer predictions in vqa models
    Ray, Arijit, Burachas, Giedrius T, Sikka, Karan, Roy, Anirban, Ziskind, Avi, Yao, Yi, and Divakaran, Ajay
    In ECCV Workshops 2018
    PDF

2017

  1. Deep active object recognition by joint label and action prediction
    Malmir, Mohsen, Sikka, Karan, Forster, Deborah, Fasel, Ian, Movellan, Javier R, and Cottrell, Garrison W
    CVIU 2017
    PDF
  2. Discriminatively trained latent ordinal model for video classification
    Sikka, Karan, and Sharma, Gaurav
    PAMI 2017
    PDF
  3. Adascan: Adaptive scan pooling in deep convolutional neural networks for human action recognition in videos
    Kar, Amlan, Rai, Nishant, Sikka, Karan, and Sharma, Gaurav
    In CVPR 2017
    PDF

2016

  1. Lomo: Latent ordinal model for facial analysis in videos
    Sikka, Karan, Sharma, Gaurav, and Bartlett, Marian
    In CVPR 2016
    PDF Video

2015

  1. The more the merrier: Analysing the affect of a group of people in images
    Dhall, Abhinav, Joshi, Jyoti, Sikka, Karan, Goecke, Roland, and Sebe, Nicu
    In AFGR 2015
    PDF
  2. Exemplar hidden markov models for classification of facial expressions in videos
    Sikka, Karan, Dhall, Abhinav, and Bartlett, Marian
    In CVPR Workshops 2015
    PDF
  3. Automated assessment of children’s postoperative pain using computer vision
    Sikka, Karan, Ahmed, Alex A, Diaz, Damaris, Goodwin, Matthew S, Craig, Kenneth D, Bartlett, Marian S, and Huang, Jeannie S
    Pediatrics 2015
    PDF Supp
  4. Joint Clustering and Classification for Multiple Instance Learning
    Sikka, Karan, Giri, Ritwik, and Bartlett, Marian
    In BMVC 2015
    PDF
  5. Deep Q-learning for Active Recognition of GERMS: Baseline performance on a standardized dataset for active learning.
    Malmir, Mohsen, Sikka, Karan, Forster, Deborah, Movellan, Javier R, and Cottrell, Garison
    In BMVC 2015
    PDF

2014

  1. A discriminative parts based model approach for fiducial points free and shape constrained head pose normalisation in the wild
    Dhall, Abhinav, Sikka, Karan, Littlewort, Gwen, Goecke, Roland, and Bartlett, Marian
    In WACV 2014
    PDF
  2. Classification and weakly supervised pain localization using multiple segment representation
    Sikka, Karan, Dhall, Abhinav, and Bartlett, Marian Stewart
    IVC 2014
    PDF
  3. Emotion recognition in the wild challenge 2014: Baseline, data and protocol
    Dhall, Abhinav, Goecke, Roland, Joshi, Jyoti, Sikka, Karan, and Gedeon, Tom
    In ICMI 2014
    PDF Website
  4. Facial expression analysis for estimating pain in clinical settings
    Sikka, Karan
    In ICMI 2014
    PDF

2013

  1. Weakly supervised pain localization using multiple instance learning
    (Best Student Paper Honorable Mention Award)
    Sikka, Karan, Dhall, Abhinav, and Bartlett, Marian
    In AFGR 2013
    PDF
  2. Multiple kernel learning for emotion recognition in the wild
    (Best Paper Award)
    Sikka, Karan, Dykstra, Karmen, Sathyanarayana, Suchitra, Littlewort, Gwen, and Bartlett, Marian
    In ICMI 2013
    PDF
  3. Pseudo vs. true defect classification in printed circuits boards using wavelet features
    Sikka, Sahil, Sikka, Karan, Bhuyan, Manas Kamal, and Iwahori, Yuji
    arXiv preprint arXiv:1310.6654 2013
    PDF

2012

  1. Exploring bag of words architectures in the facial expression domain
    Sikka, Karan, Wu, Tingfan, Susskind, Josh, and Bartlett, Marian
    In ECCV 2012
    PDF

2011

  1. Texture information-based hybrid methodology for the segmentation of SAR images
    Singh, Pankaj K, Sinha, Nitesh, Sikka, Karan, and Mishra, Amit K
    International journal of remote sensing 2011
    PDF

2010

  1. Comparison of algorithms for ultrasound image segmentation without ground truth
    Sikka, Karan, and Deserno, Thomas M
    In Medical Imaging 2010: Image Perception, Observer Performance, and Technology Assessment 2010
    PDF

2009

  1. A fully automated algorithm under modified FCM framework for improved brain MR image segmentation
    Sikka, Karan, Sinha, Nitesh, Singh, Pankaj K, and Mishra, Amit K
    Magnetic Resonance Imaging 2009
    PDF