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

G-CNN: an Iterative Grid Based Object Detector

Mahyar NajibiMohammad Rastegariand Larry Davis
2016
CVPR

We introduce G-CNN, an object detection technique based on CNNs which works without proposal algorithms. G-CNN starts with a multi-scale grid of fixed bounding boxes. We train a regressor to move… 

Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks

Junyuan XieRoss Girshickand Ali Farhadi
2016
ECCV

We propose Deep3D, a fully automatic 2D-to-3D conversion algorithm that takes 2D images or video frames as input and outputs stereo 3D image pairs. The stereo images can be viewed with 3D glasses or… 

FigureSeer: Parsing Result-Figures in Research Papers

Noah SiegelZachary HorvitzRoie Levinand Ali Farhadi
2016
ECCV

‘Which are the pedestrian detectors that yield a precision above 95% at 25% recall?’ Answering such a complex query involves identifying and analyzing the results reported in figures within several… 

Much Ado About Time: Exhaustive Annotation of Temporal Data

Gunnar A. SigurdssonOlga RussakovskyAli Farhadiand Abhinav Gupta
2016
HCOMP

Large-scale annotated datasets allow AI systems to learn from and build upon the knowledge of the crowd. Many crowdsourcing techniques have been developed for collecting image annotations. These… 

Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding

Gunnar A. SigurdssonGül VarolXiaolong Wangand Abhinav Gupta
2016
ECCV

Computer vision has a great potential to help our daily lives by searching for lost keys, watering flowers or reminding us to take a pill. To succeed with such tasks, computer vision methods need to… 

XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

Mohammad RastegariVicente OrdonezJoseph Redmonand Ali Farhadi
2016
ECCV

We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary… 

"What happens if..." Learning to Predict the Effect of Forces in Images

Roozbeh MottaghiMohammad RastegariAbhinav Guptaand Ali Farhadi
2016
ECCV

What happens if one pushes a cup sitting on a table toward the edge of the table? How about pushing a desk against a wall? In this paper, we study the problem of understanding the movements of… 

A Diagram Is Worth A Dozen Images

Aniruddha KembhaviMike SalvatoEric Kolveand Ali Farhadi
2016
ECCV

Diagrams are common tools for representing complex concepts, relationships and events, often when it would be difficult to portray the same information with natural images. Understanding natural… 

Unsupervised Deep Embedding for Clustering Analysis

Junyuan XieRoss Girshickand Ali Farhadi
2016
ICML

Clustering is central to many data-driven application domains and has been studied extensively in terms of distance functions and grouping algorithms. Relatively little work has focused on learning… 

Metaphor as a Medium for Emotion: An Empirical Study

Saif M. MohammadEkaterina Shutovaand Peter D. Turney
2016
SEM

It is generally believed that a metaphor tends to have a stronger emotional impact than a literal statement; however, there is no quantitative study establishing the extent to which this is true.…