Antonio Torralba

TL;DR: Harmonic Convolution is proposed, an operation that helps deep networks distill priors in audio signals by explicitly utilizing the harmonic structure within by engineering the kernel to be supported by sets of harmonic series, instead of local neighborhoods for convolutional kernels.

TL;DR: A novel method is introduced that, inspired by well-known tools in human psychophysics, estimates the biases that the human visual system might use for recognition, but in computer vision feature spaces, and presents an SVM formulation that constrains the orientation of the SVM hyperplane to agree with the bias from human visualSystem.

TL;DR: This work builds upon VirtualHome, to create a new dataset VirtualHome-Env, where it collects program sketches to represent activities and match programs with environments that can afford them, and proposes RNN-ResActGraph, a network that generates a program from a given sketch and an environment graph and tracks the changes in the environment induced by the program.

TL;DR: ConceptFusion as mentioned in this paper is a scene representation that is fundamentally open-set, enabling reasoning beyond a closed set of concepts and inherently multimodal, enabling a diverse range of possible queries to the 3D map, from language, to images, to audio, to 3D geometry, all working in concert.

TL;DR: In this article, a generative adversarial network (GAN) is proposed to learn composable module operations that can either add or remove a particular ingredient in a food recipe, which can be seen as a way to change the visual appearance of a dish by adding extra objects or changing the appearance of the existing ones.