Karan Sikka

is this you? claim profile

∙ 0 followers
University of Maryland ∙ University of California, San Diego ∙ SRI International

Detecting Trojaned DNNs Using Counterfactual Attributions

We target the problem of detecting Trojans or backdoors in DNNs. Such mo...
12/03/2020 ∙ by Karan Sikka, et al. ∙ 7 ∙ share

read it
Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings

We improve zero-shot learning (ZSL) by incorporating common-sense knowle...
11/21/2020 ∙ by Karan Sikka, et al. ∙ 4 ∙ share

read it
RGB2LIDAR: Towards Solving Large-Scale Cross-Modal Visual Localization

We study an important, yet largely unexplored problem of large-scale cro...
09/12/2020 ∙ by Niluthpol Chowdhury Mithun, et al. ∙ 13 ∙ share

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

We introduce Deep Adaptive Semantic Logic (DASL), a novel framework for ...
03/16/2020 ∙ by Karan Sikka, et al. ∙ 10 ∙ share

read it
Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation

While models for Visual Question Answering (VQA) have steadily improved ...
09/10/2019 ∙ by Arijit Ray, et al. ∙ 0 ∙ share

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

Food classification is a challenging problem due to the large number of ...
07/14/2019 ∙ by Parneet Kaur, et al. ∙ 0 ∙ share

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

There has been an explosion of multimodal content generated on social me...
05/17/2019 ∙ by Karan Sikka, et al. ∙ 0 ∙ share

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

Computing author intent from multimodal data like Instagram posts requir...
04/19/2019 ∙ by Julia Kruk, et al. ∙ 18 ∙ share

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

We address the problem of grounding free-form textual phrases by using w...
03/27/2019 ∙ by Samyak Datta, et al. ∙ 0 ∙ share

read it
Semantically-Aware Attentive Neural Embeddings for Image-based Visual Localization

We present a novel method for fusing appearance and semantic information...
12/08/2018 ∙ by Zachary Seymour, et al. ∙ 0 ∙ share

read it
Understanding Visual Ads by Aligning Symbols and Objects using Co-Attention

We tackle the problem of understanding visual ads where given an ad imag...
07/04/2018 ∙ by Karuna Ahuja, et al. ∙ 0 ∙ share

read it
Zero-Shot Object Detection

We introduce and tackle the problem of zero-shot object detection (ZSD),...
04/12/2018 ∙ by Ankan Bansal, et al. ∙ 0 ∙ share

read it
Combining Weakly and Webly Supervised Learning for Classifying Food Images

Food classification from images is a fine-grained classification problem...
12/23/2017 ∙ by Parneet Kaur, et al. ∙ 0 ∙ share

read it
AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videos

We propose a novel method for temporally pooling frames in a video for t...
11/24/2016 ∙ by Amlan Kar, et al. ∙ 0 ∙ share

read it
Discriminatively Trained Latent Ordinal Model for Video Classification

We study the problem of video classification for facial analysis and hum...
08/08/2016 ∙ by Karan Sikka, et al. ∙ 0 ∙ share

read it
LOMo: Latent Ordinal Model for Facial Analysis in Videos

We study the problem of facial analysis in videos. We propose a novel we...
04/06/2016 ∙ by Karan Sikka, et al. ∙ 0 ∙ share

read it
Deep Active Object Recognition by Joint Label and Action Prediction

An active object recognition system has the advantage of being able to a...
12/17/2015 ∙ by Mohsen Malmir, et al. ∙ 0 ∙ share

read it
Pseudo vs. True Defect Classification in Printed Circuits Boards using Wavelet Features

In recent years, Printed Circuit Boards (PCB) have become the backbone o...
10/24/2013 ∙ by Sahil Sikka, et al. ∙ 0 ∙ share

read it

Karan Sikka

Featured Co-authors

Devi Parikh

Rama Chellappa

Serge Belongie

Dan Jurafsky

Stefan Lee

Xiao Lin

Gaurav Sharma

Ajay Divakaran

Garrison W. Cottrell

Susmit Jha

Ankan Bansal

Detecting Trojaned DNNs Using Counterfactual Attributions

Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings

RGB2LIDAR: Towards Solving Large-Scale Cross-Modal Visual Localization

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

Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation

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

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

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

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

Semantically-Aware Attentive Neural Embeddings for Image-based Visual Localization

Understanding Visual Ads by Aligning Symbols and Objects using Co-Attention

Zero-Shot Object Detection

Combining Weakly and Webly Supervised Learning for Classifying Food Images

AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videos

Discriminatively Trained Latent Ordinal Model for Video Classification

LOMo: Latent Ordinal Model for Facial Analysis in Videos

Deep Active Object Recognition by Joint Label and Action Prediction

Pseudo vs. True Defect Classification in Printed Circuits Boards using Wavelet Features