Antonio Torralba

TL;DR: It is argued that to continue to approach human-level performance, saliency models will need to discover higher-level concepts in images: text, objects of gaze and action, locations of motion, and expected locations of people in images.

TL;DR: In this paper, a probabilistic framework for encoding the relationships between context and object properties is proposed, which can be used to reduce the search space by looking only in places in which the object is expected to be; this also increases performance, by rejecting patterns that look like the target but appear in unlikely places.

TL;DR: The authors explore neural network models that learn to associate segments of spoken audio captions with the semantically relevant portions of natural images that they refer to, and demonstrate that these audio-visual associative localizations emerge from network-internal representations learned as a byproduct of training to perform an image-audio retrieval task.

TL;DR: A simple method of label sharing between semantically similar categories is proposed that leverages the WordNet hierarchy to define semantic distance between any two categories and use this semantic distance to share labels.

TL;DR: Qualitative results suggest the PixelPlayer model learns to ground sounds in vision, enabling applications such as independently adjusting the volume of sound sources, and experimental results show that the proposed Mix-and-Separate framework outperforms several baselines on source separation.