Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering

Aishwarya AgrawalDhruv BatraDevi ParikhAniruddha Kembhavi
2018
CVPR

A number of studies have found that today’s Visual Question Answering (VQA) models are heavily driven by superficial correlations in the training data and lack sufficient image grounding. To… 

IQA: Visual Question Answering in Interactive Environments

Daniel GordonAniruddha KembhaviMohammad RastegariAli Farhadi
2018
CVPR

We introduce Interactive Question Answering (IQA), the task of answering questions that require an autonomous agent to interact with a dynamic visual environment. IQA presents the agent with a scene… 

LSTMs Exploit Linguistic Attributes of Data

Nelson F. LiuOmer LevyRoy SchwartzNoah A. Smith
2018
ACL • RepL4NLP Workshop

While recurrent neural networks have found success in a variety of natural language processing applications, they are general models of sequential data. We investigate how the properties of natural… 

Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples

Vidur JoshiMatthew Petersand Mark Hopkins
2018
ACL

We revisit domain adaptation for parsers in the neural era. First we show that recent advances in word representations greatly diminish the need for domain adaptation when the target domain is… 

AllenNLP: A Deep Semantic Natural Language Processing Platform

Matt GardnerJoel GrusMark NeumannLuke Zettlemoyer
2018
ACL • NLP OSS Workshop

This paper describes AllenNLP, a platform for research on deep learning methods in natural language understanding. AllenNLP is designed to support researchers who want to build novel language… 

Transferring Common-Sense Knowledge for Object Detection

Krishna Kumar SinghSantosh Kumar DivvalaAli Farhadiand Yong Jae Lee
2018
ECCV

We propose the idea of transferring common-sense knowledge from source categories to target categories for scalable object detection. In our setting, the training data for the source categories have… 

ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

Sachin MehtaMohammad RastegariAnat Caspiand Hannaneh Hajishirzi
2018
ECCV

We introduce a fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints. ESPNet is based on a new convolutional module,… 

Imagine This! Scripts to Compositions to Videos

Tanmay GuptaDustin SchwenkAli Farhadiand Aniruddha Kembhavi
2018
ECCV

Imagining a scene described in natural language with realistic layout and appearance of entities is the ultimate test of spatial, visual, and semantic world knowledge. Towards this goal, we present… 

Extracting Scientific Figures with Distantly Supervised Neural Networks

Noah SiegelNicholas LourieRussell Power and Waleed Ammar
2018
JCDL

Non-textual components such as charts, diagrams and tables provide key information in many scientific documents, but the lack of large labeled datasets has impeded the development of data-driven… 

VISIR: Visual and Semantic Image Label Refinement

Sreyasi Nag ChowdhuryNiket TandonHakan FerhatosmanogluGerhard Weikum
2018
WSDM

The social media explosion has populated the Internet with a wealth of images. There are two existing paradigms for image retrieval: 1)content-based image retrieval (BIR), which has traditionally…