6 citations · 11 across the 6 of their papers we have counts for
8 papers
Nonprehensile Riemannian Motion Predictive Control
Hamid Izadinia, Byron Boots, Steven M. Seitz
Nonprehensile manipulation involves long horizon underactuated object interactions and physical contact with different objects that can inherently introduce a high degree of uncert…
Scene Recomposition by Learning-based ICP
Hamid Izadinia, Steven M. Seitz
By moving a depth sensor around a room, we compute a 3D CAD model of the environment, capturing the room shape and contents such as chairs, desks, sofas, and tables. Rather than re…
VISER: Visual Self-Regularization
Hamid Izadinia, Pierre Garrigues
In this work, we propose the use of large set of unlabeled images as a source of regularization data for learning robust visual representation. Given a visual model trained by a la…
Tag Prediction at Flickr: a View from the Darkroom
Kofi Boakye, Sachin Farfade, Hamid Izadinia +2
Automated photo tagging has established itself as one of the most compelling applications of deep learning. While deep convolutional neural networks have repeatedly demonstrated to…
IM2CAD
Hamid Izadinia, Qi Shan, Steven M. Seitz
Given a single photo of a room and a large database of furniture CAD models, our goal is to reconstruct a scene that is as similar as possible to the scene depicted in the photogra…
Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing
Hamid Izadinia, Fereshteh Sadeghi, Santosh Kumar Divvala +2
We introduce Segment-Phrase Table (SPT), a large collection of bijective associations between textual phrases and their corresponding segmentations. Leveraging recent progress in o…
Decoding the Text Encoding
Fereshteh Sadeghi, Hamid Izadinia
Word clouds and text visualization is one of the recent most popular and widely used types of visualizations. Despite the attractiveness and simplicity of producing word clouds, th…
Image Classification and Retrieval from User-Supplied Tags
Hamid Izadinia, Ali Farhadi, Aaron Hertzmann +1
This paper proposes direct learning of image classification from user-supplied tags, without filtering. Each tag is supplied by the user who shared the image online. Enormous numbe…