We propose Encyclopedic-VQA, a large scale visual question answering (VQ...
Computer Vision is driven by the many datasets which can be used for tra...
Transferability metrics is a maturing field with increasing interest, wh...
We address the problem of ensemble selection in transfer learning: Given...
Transfer learning has become a popular method for leveraging pre-trained...
Transfer learning enables to re-use knowledge learned on a source task t...
This paper makes a first step towards compatible and hence reusable netw...
We propose Localized Narratives, an efficient way to collect image capti...
In interactive object segmentation a user collaborates with a computer v...
We present Open Images V4, a dataset of 9.2M images with unified annotat...
We introduce Intelligent Annotation Dialogs for bounding box annotation....
Many machine vision applications require predictions for every pixel of ...
Semantic classes can be either things (objects with a well-defined shape...
We propose a novel method for semantic segmentation, the task of labelin...
Semantic segmentation is the task of assigning a class-label to each pix...
Intuitively, the appearance of true object boundaries varies from image ...