849 citations · 2k across the 67 of their papers we have counts for
7 papers · 1 filter
UnweaveNet: Unweaving Activity Stories
Will Price, Carl Vondrick, Dima Damen
Our lives can be seen as a complex weaving of activities; we switch from one activity to another, to maximise our achievements or in reaction to demands placed upon us. Observing a…
Real-Time Neural Voice Camouflage
Mia Chiquier, Chengzhi Mao, Carl Vondrick
Automatic speech recognition systems have created exciting possibilities for applications, however they also enable opportunities for systematic eavesdropping. We propose a method…
Full-Body Visual Self-Modeling of Robot Morphologies
Boyuan Chen, Robert Kwiatkowski, Carl Vondrick +1
Internal computational models of physical bodies are fundamental to the ability of robots and animals alike to plan and control their actions. These "self-models" allow robots to c…
Discrete Representations Strengthen Vision Transformer Robustness
Chengzhi Mao, Lu Jiang, Mostafa Dehghani +3
Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional cou…
The Boombox: Visual Reconstruction from Acoustic Vibrations
Boyuan Chen, Mia Chiquier, Hod Lipson +1
Interacting with bins and containers is a fundamental task in robotics, making state estimation of the objects inside the bin critical. While robots often use cameras for state est…
Adversarial Attacks are Reversible with Natural Supervision
Chengzhi Mao, Mia Chiquier, Hao Wang +2
We find that images contain intrinsic structure that enables the reversal of many adversarial attacks. Attack vectors cause not only image classifiers to fail, but also collaterall…
Learning the Predictability of the Future
Dídac Surís, Ruoshi Liu, Carl Vondrick
We introduce a framework for learning from unlabeled video what is predictable in the future. Instead of committing up front to features to predict, our approach learns from data w…