Humans can recognize the gist of a novel image in a single glance, independent of its
complexity. How is this remarkable feat accomplished? On the basis of behavioral and …

In the real world, objects never occur in isolation; they co-vary with other objects and
particular environments, providing a rich source of contextual associations to be exploited by …

Self-powered sensing systems augmented with machine learning (ML) represent a path
toward the large-scale deployment of the internet of things (IoT). With autonomous energy …

In this work, we revisit the global average pooling layer proposed in [13], and shed light on
how it explicitly enables the convolutional neural network (CNN) to have remarkable …

The rise of multi-million-item dataset initiatives has enabled data-hungry machine learning
algorithms to reach near-human semantic classification performance at tasks such as visual …

In this paper, we propose a computational model of the recognition of real world scenes that
bypasses the segmentation and the processing of individual objects or regions. The …

Scene categorization is a fundamental problem in computer vision. However, scene
understanding research has been constrained by the limited scope of currently-used …

Scene recognition is one of the hallmark tasks of computer vision, allowing definition of a
context for object recognition. Whereas the tremendous recent progress in object recognition …

Datasets are an integral part of contemporary object recognition research. They have been
the chief reason for the considerable progress in the field, not just as source of large …

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It
offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household …