We present a novel self-contained camera-projector tabletop system with ...
We present a multimodal deep learning (MDL) framework for predicting phy...
Machine learning is not readily accessible to domain experts from many
f...
Computer vision models learn to perform a task by capturing relevant
sta...
The ActivityNet Large Scale Activity Recognition Challenge 2017 Summary:...
Most natural videos contain numerous events. For example, in a video of ...
Microtask crowdsourcing is increasingly critical to the creation of extr...
Despite progress in perceptual tasks such as image classification, compu...
Microtask crowdsourcing has enabled dataset advances in social science a...