Learning Visual Models from Paired Audio-Visual Examples

From the clink of a mug placed onto a saucer to the bustle of a busy café, our days are filled with visual experiences that are accompanied by distinctive sounds. In this thesis, we show that these sounds can provide a rich training signal for learning visual models. First, we propose the task of predicting the sound that an object makes when struck as a way of studying physical interactions within a visual scene. We demonstrate this idea by training an algorithm to produce plausible soundtracks for videos in which people hit and scratch objects with a drumstick. Then, with human studies and automated evaluations on recognition tasks, we verify that the sounds produced by the algorithm convey information about actions and material properties. Second, we show that ambient audio – e.g., crashing waves, people speaking in a crowd – can also be used to learn visual models. We train a convolutional neural network to predict a statistical summary of the sounds that occur within a scene, and we demonstrate that the visual representation learned by the model conveys information about objects and scenes. (Copies available exclusively from MIT Libraries, libraries.mit.edu/docs - [email protected])