Antonio Torralba

TL;DR: PropNet (PropNet) as discussed by the authors is a differentiable, learnable dynamics model that handles partially observable scenarios and enables instantaneous propagation of signals beyond pairwise interactions, and it not only outperforms current learnable physics engines in forward simulation, but also achieves superior performance on various control tasks.

TL;DR: RF-Avatar, a neural network model that can estimate 3D meshes of the human body in the presence of occlusions, baggy clothes, and bad lighting conditions, and even through walls, is presented.

TL;DR: Foley Music, a system that can synthesize plausible music for a silent video clip about people playing musical instruments, is introduced and a Graph$-$Transformer framework that can accurately predict MIDI event sequences in accordance with the body movements is presented.

TL;DR: This work proposes a model that exploits Graph Neural Networks to propagate contextual information from the scene in order to perform detailed affordance reasoning about each object, and collects a new dataset that builds upon ADE20k, referred to as ADE-Affordance, which contains annotations enabling such rich visual reasoning.

TL;DR: Various applications and opportunities of SM multimodal data, latest advancements, current challenges, and future directions for the crisis informatics and other related research fields are highlighted.