no code implementations • 26 Oct 2023 • Takuma Yoneda, Tianchong Jiang, Gregory Shakhnarovich, Matthew R. Walter
A core capability for robot manipulation is reasoning over where and how to stably place objects in cluttered environments.
no code implementations • 2 Sep 2023 • Marcelo Sandoval-Castaneda, Yanhong Li, Diane Brentari, Karen Livescu, Gregory Shakhnarovich
This paper presents an in-depth analysis of various self-supervision methods for isolated sign language recognition (ISLR).
1 code implementation • 22 May 2023 • Jiading Fang, Shengjie Lin, Igor Vasiljevic, Vitor Guizilini, Rares Ambrus, Adrien Gaidon, Gregory Shakhnarovich, Matthew R. Walter
A practical benefit of implicit visual representations like Neural Radiance Fields (NeRFs) is their memory efficiency: large scenes can be efficiently stored and shared as small neural nets instead of collections of images.
no code implementations • 30 Jun 2020 • Yuval Bahat, Gregory Shakhnarovich
This suggests the task of detecting errors, which we tackle in this paper for the case of visual classification.
1 code implementation • ECCV 2020 • Sunnie S. Y. Kim, Nicholas Kolkin, Jason Salavon, Gregory Shakhnarovich
Both geometry and texture are fundamental aspects of visual style.
2 code implementations • 27 Feb 2020 • Ruotian Luo, Gregory Shakhnarovich
We investigate the effect of different model architectures, training objectives, hyperparameter settings and decoding procedures on the diversity of automatically generated image captions.
2 code implementations • 1 Aug 2019 • Igor Vasiljevic, Nick Kolkin, Shanyi Zhang, Ruotian Luo, Haochen Wang, Falcon Z. Dai, Andrea F. Daniele, Mohammadreza Mostajabi, Steven Basart, Matthew R. Walter, Gregory Shakhnarovich
We introduce DIODE, a dataset that contains thousands of diverse high resolution color images with accurate, dense, long-range depth measurements.
no code implementations • 1 Feb 2019 • Yuval Bahat, Michal Irani, Gregory Shakhnarovich
Our approach is based on the observation that correctly classified images tend to exhibit robust and consistent classifications under certain image transformations (e. g., horizontal flip, small image translation, etc.).
no code implementations • CVPR 2018 • Mohammadreza Mostajabi, Michael Maire, Gregory Shakhnarovich
Our technique is applicable when the ground-truth labels themselves exhibit internal structure; we derive a regularizer by learning an autoencoder over the set of annotations.
1 code implementation • 2 Apr 2018 • Yuval Bahat, Gregory Shakhnarovich
We develop a technique for automatically detecting the classification errors of a pre-trained visual classifier.
1 code implementation • CVPR 2018 • Ruotian Luo, Brian Price, Scott Cohen, Gregory Shakhnarovich
One property that remains lacking in image captions generated by contemporary methods is discriminability: being able to tell two images apart given the caption for one of them.
2 code implementations • 5 Oct 2017 • Herman Kamper, Gregory Shakhnarovich, Karen Livescu
We introduce a newly collected data set of human semantic relevance judgements and an associated task, semantic speech retrieval, where the goal is to search for spoken utterances that are semantically relevant to a given text query.
no code implementations • ICCV 2017 • Nicholas Kolkin, Gregory Shakhnarovich, Eli Shechtman
In many computer vision tasks, for example saliency prediction or semantic segmentation, the desired output is a foreground map that predicts pixels where some criteria is satisfied.
1 code implementation • 23 Mar 2017 • Herman Kamper, Shane Settle, Gregory Shakhnarovich, Karen Livescu
In this setting of images paired with untranscribed spoken captions, we consider whether computer vision systems can be used to obtain textual labels for the speech.
1 code implementation • CVPR 2017 • Gustav Larsson, Michael Maire, Gregory Shakhnarovich
How many labels are needed?
no code implementations • CVPR 2017 • Ruotian Luo, Gregory Shakhnarovich
Second, we use the comprehension module in a generate-and-rerank pipeline, which chooses from candidate expressions generated by a model according to their performance on the comprehension task.
no code implementations • 6 Dec 2016 • Mohammadreza Mostajabi, Nicholas Kolkin, Gregory Shakhnarovich
We propose an approach for learning category-level semantic segmentation purely from image-level classification tags indicating presence of categories.
no code implementations • 17 Nov 2016 • Igor Vasiljevic, Ayan Chakrabarti, Gregory Shakhnarovich
We investigate the extent to which this degradation is due to the mismatch between training and input image statistics.
no code implementations • 26 Sep 2016 • Taehwan Kim, Jonathan Keane, Weiran Wang, Hao Tang, Jason Riggle, Gregory Shakhnarovich, Diane Brentari, Karen Livescu
Recognizing fingerspelling is challenging for a number of reasons: It involves quick, small motions that are often highly coarticulated; it exhibits significant variation between signers; and there has been a dearth of continuous fingerspelling data collected.
4 code implementations • 24 May 2016 • Gustav Larsson, Michael Maire, Gregory Shakhnarovich
We introduce a design strategy for neural network macro-architecture based on self-similarity.
Ranked #29 on Image Classification on SVHN
no code implementations • NeurIPS 2016 • Ayan Chakrabarti, Jingyu Shao, Gregory Shakhnarovich
A single color image can contain many cues informative towards different aspects of local geometric structure.
3 code implementations • 22 Mar 2016 • Gustav Larsson, Michael Maire, Gregory Shakhnarovich
This intermediate output can be used to automatically generate a color image, or further manipulated prior to image formation.
1 code implementation • CVPR 2015 • Mohammadreza Mostajabi, Payman Yadollahpour, Gregory Shakhnarovich
We introduce a purely feed-forward architecture for semantic segmentation.
no code implementations • CVPR 2013 • Payman Yadollahpour, Dhruv Batra, Gregory Shakhnarovich
This paper introduces a two-stage approach to semantic image segmentation.
no code implementations • CVPR 2013 • Subhransu Maji, Gregory Shakhnarovich
We study the problem of part discovery when partial correspondence between instances of a category are available.
no code implementations • CVPR 2013 • Zhile Ren, Gregory Shakhnarovich
We propose a hierarchical segmentation algorithm that starts with a very fine oversegmentation and gradually merges regions using a cascade of boundary classifiers.
no code implementations • NeurIPS 2010 • Taehwan Kim, Gregory Shakhnarovich, Raquel Urtasun
Sparse coding has recently become a popular approach in computer vision to learn dictionaries of natural images.