Antonio Torralba

is this you? claim profile

∙ 0 followers
MIT ∙ Facebook

Assistant Professor of Electrical Engineering and Computer Science at Massachusetts Institute of Technology

Seeing What a GAN Cannot Generate

Despite the success of Generative Adversarial Networks (GANs), mode coll...
10/24/2019 ∙ by David Bau, et al. ∙ 52 ∙ share

read it
Visualizing and Understanding Generative Adversarial Networks (Extended Abstract)

Generative Adversarial Networks (GANs) have achieved impressive results ...
01/29/2019 ∙ by David Bau, et al. ∙ 22 ∙ share

read it
Gaze360: Physically Unconstrained Gaze Estimation in the Wild

Understanding where people are looking is an informative social cue. In ...
10/22/2019 ∙ by Petr Kellnhofer, et al. ∙ 18 ∙ share

read it
Meta-Sim: Learning to Generate Synthetic Datasets

Training models to high-end performance requires availability of large l...
04/25/2019 ∙ by Amlan Kar, et al. ∙ 12 ∙ share

read it
CLEVRER: CoLlision Events for Video REpresentation and Reasoning

The ability to reason about temporal and causal events from videos lies ...
10/03/2019 ∙ by Kexin Yi, et al. ∙ 12 ∙ share

read it
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks

Generative Adversarial Networks (GANs) have recently achieved impressive...
11/26/2018 ∙ by David Bau, et al. ∙ 10 ∙ share

read it
Self-supervised Moving Vehicle Tracking with Stereo Sound

Humans are able to localize objects in the environment using both visual...
10/25/2019 ∙ by Chuang Gan, et al. ∙ 10 ∙ share

read it
Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks

We introduce a saliency-based distortion layer for convolutional neural ...
09/10/2018 ∙ by Adria Recasens, et al. ∙ 8 ∙ share

read it
Visual Object Networks: Image Generation with Disentangled 3D Representation

Recent progress in deep generative models has led to tremendous breakthr...
12/06/2018 ∙ by Jun-Yan Zhu, et al. ∙ 8 ∙ share

read it
Real-Time Object Pose Estimation with Pose Interpreter Networks

In this work, we introduce pose interpreter networks for 6-DoF object po...
08/03/2018 ∙ by Jimmy Wu, et al. ∙ 4 ∙ share

read it
Propagation Networks for Model-Based Control Under Partial Observation

There has been an increasing interest in learning dynamics simulators fo...
09/28/2018 ∙ by Yunzhu Li, et al. ∙ 4 ∙ share

read it
Connecting Touch and Vision via Cross-Modal Prediction

Humans perceive the world using multi-modal sensory inputs such as visio...
06/14/2019 ∙ by Yunzhu Li, et al. ∙ 4 ∙ share

read it
Dataset Distillation

Model distillation aims to distill the knowledge of a complex model into...
11/27/2018 ∙ by Tongzhou Wang, et al. ∙ 3 ∙ share

read it
Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input

In this paper, we explore neural network models that learn to associate ...
04/04/2018 ∙ by David Harwath, et al. ∙ 2 ∙ share

read it
Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids

Real-life control tasks involve matter of various substances---rigid or ...
10/03/2018 ∙ by Yunzhu Li, et al. ∙ 2 ∙ share

read it
Temporal Relational Reasoning in Videos

Temporal relational reasoning, the ability to link meaningful transforma...
11/22/2017 ∙ by Bolei Zhou, et al. ∙ 0 ∙ share

read it
Interpreting Deep Visual Representations via Network Dissection

The success of recent deep convolutional neural networks (CNNs) depends ...
11/15/2017 ∙ by Bolei Zhou, et al. ∙ 0 ∙ share

read it
Network Dissection: Quantifying Interpretability of Deep Visual Representations

We propose a general framework called Network Dissection for quantifying...
04/19/2017 ∙ by David Bau, et al. ∙ 0 ∙ share

read it
A Compositional Object-Based Approach to Learning Physical Dynamics

We present the Neural Physics Engine (NPE), a framework for learning sim...
12/01/2016 ∙ by Michael B. Chang, et al. ∙ 0 ∙ share

read it
See, Hear, and Read: Deep Aligned Representations

We capitalize on large amounts of readily-available, synchronous data to...
06/03/2017 ∙ by Yusuf Aytar, et al. ∙ 0 ∙ share

read it
Open Vocabulary Scene Parsing

Recognizing arbitrary objects in the wild has been a challenging problem...
03/26/2017 ∙ by Hang Zhao, et al. ∙ 0 ∙ share

read it
Face-to-BMI: Using Computer Vision to Infer Body Mass Index on Social Media

A person's weight status can have profound implications on their life, r...
03/09/2017 ∙ by Enes Kocabey, et al. ∙ 0 ∙ share

read it
SegICP: Integrated Deep Semantic Segmentation and Pose Estimation

Recent robotic manipulation competitions have highlighted that sophistic...
03/05/2017 ∙ by Jay M. Wong, et al. ∙ 0 ∙ share

read it
Is Saki #delicious? The Food Perception Gap on Instagram and Its Relation to Health

Food is an integral part of our life and what and how much we eat crucia...
02/21/2017 ∙ by Ferda Ofli, et al. ∙ 0 ∙ share

read it
Following Gaze Across Views

Following the gaze of people inside videos is an important signal for un...
12/09/2016 ∙ by Adria Recasens, et al. ∙ 0 ∙ share

read it
Who is Mistaken?

Recognizing when people have false beliefs is crucial for understanding ...
12/04/2016 ∙ by Benjamin Eysenbach, et al. ∙ 0 ∙ share

read it
Cross-Modal Scene Networks

People can recognize scenes across many different modalities beyond natu...
10/27/2016 ∙ by Yusuf Aytar, et al. ∙ 0 ∙ share

read it
SoundNet: Learning Sound Representations from Unlabeled Video

We learn rich natural sound representations by capitalizing on large amo...
10/27/2016 ∙ by Yusuf Aytar, et al. ∙ 0 ∙ share

read it
Places: An Image Database for Deep Scene Understanding

The rise of multi-million-item dataset initiatives has enabled data-hung...
10/06/2016 ∙ by Bolei Zhou, et al. ∙ 0 ∙ share

read it
Ambient Sound Provides Supervision for Visual Learning

The sound of crashing waves, the roar of fast-moving cars -- sound conve...
08/25/2016 ∙ by Andrew Owens, et al. ∙ 0 ∙ share

read it
Semantic Understanding of Scenes through the ADE20K Dataset

Scene parsing, or recognizing and segmenting objects and stuff in an ima...
08/18/2016 ∙ by Bolei Zhou, et al. ∙ 0 ∙ share

read it
Learning Aligned Cross-Modal Representations from Weakly Aligned Data

People can recognize scenes across many different modalities beyond natu...
07/25/2016 ∙ by Lluis Castrejon, et al. ∙ 0 ∙ share

read it
Eye Tracking for Everyone

From scientific research to commercial applications, eye tracking is an ...
06/18/2016 ∙ by Kyle Krafka, et al. ∙ 0 ∙ share

read it
What do different evaluation metrics tell us about saliency models?

How best to evaluate a saliency model's ability to predict where humans ...
04/12/2016 ∙ by Zoya Bylinskii, et al. ∙ 0 ∙ share

read it
Deep Neural Networks predict Hierarchical Spatio-temporal Cortical Dynamics of Human Visual Object Recognition

The complex multi-stage architecture of cortical visual pathways provide...
01/12/2016 ∙ by Radoslaw M. Cichy, et al. ∙ 0 ∙ share

read it
Visually Indicated Sounds

Objects make distinctive sounds when they are hit or scratched. These so...
12/28/2015 ∙ by Andrew Owens, et al. ∙ 0 ∙ share

read it
Learning Deep Features for Discriminative Localization

In this work, we revisit the global average pooling layer proposed in [1...
12/14/2015 ∙ by Bolei Zhou, et al. ∙ 0 ∙ share

read it
Anticipating Visual Representations from Unlabeled Video

Anticipating actions and objects before they start or appear is a diffic...
04/29/2015 ∙ by Carl Vondrick, et al. ∙ 0 ∙ share

read it
Visualizing Object Detection Features

We introduce algorithms to visualize feature spaces used by object detec...
02/19/2015 ∙ by Carl Vondrick, et al. ∙ 0 ∙ share

read it
Object Detectors Emerge in Deep Scene CNNs

With the success of new computational architectures for visual processin...
12/22/2014 ∙ by Bolei Zhou, et al. ∙ 0 ∙ share

read it
Learning visual biases from human imagination

Although the human visual system can recognize many concepts under chall...
10/17/2014 ∙ by Carl Vondrick, et al. ∙ 0 ∙ share

read it
Predicting Motivations of Actions by Leveraging Text

Understanding human actions is a key problem in computer vision. However...
06/20/2014 ∙ by Carl Vondrick, et al. ∙ 0 ∙ share

read it
Are all training examples equally valuable?

When learning a new concept, not all training examples may prove equally...
11/25/2013 ∙ by Agata Lapedriza, et al. ∙ 0 ∙ share

read it
Inverting and Visualizing Features for Object Detection

We introduce algorithms to visualize feature spaces used by object detec...
12/11/2012 ∙ by Carl Vondrick, et al. ∙ 0 ∙ share

read it
Notes on image annotation

We are under the illusion that seeing is effortless, but frequently the ...
10/12/2012 ∙ by Adela Barriuso, et al. ∙ 0 ∙ share

read it
Generating Videos with Scene Dynamics

We capitalize on large amounts of unlabeled video in order to learn a mo...
09/08/2016 ∙ by Carl Vondrick, et al. ∙ 0 ∙ share

read it
MovieQA: Understanding Stories in Movies through Question-Answering

We introduce the MovieQA dataset which aims to evaluate automatic story ...
12/09/2015 ∙ by Makarand Tapaswi, et al. ∙ 0 ∙ share

read it
Skip-Thought Vectors

We describe an approach for unsupervised learning of a generic, distribu...
06/22/2015 ∙ by Ryan Kiros, et al. ∙ 0 ∙ share

read it
Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books

Books are a rich source of both fine-grained information, how a characte...
06/22/2015 ∙ by Yukun Zhu, et al. ∙ 0 ∙ share

read it
Learning to Act Properly: Predicting and Explaining Affordances from Images

We address the problem of affordance reasoning in diverse scenes that ap...
12/20/2017 ∙ by Ching-Yao Chuang, et al. ∙ 0 ∙ share

read it

Antonio Torralba

Featured Co-authors