Object detection performance, as measured on the canonical PASCAL VOC Challenge
datasets, plateaued in the final years of the competition. The best-performing methods were …

This work explores the use of spatial context as a source of free and plentiful supervisory
signal for training a rich visual representation. Given only a large, unlabeled image …

The use of object proposals is an effective recent approach for increasing the computational
efficiency of object detection. We propose a novel method for generating object bounding …

This paper addresses the problem of generating possible object locations for use in object
recognition. We introduce selective search which combines the strength of both an …

Visual relationships capture a wide variety of interactions between pairs of objects in images
(eg “man riding bicycle” and “man pushing bicycle”). Consequently, the set of possible …

How do humans recognize the action" opening a book"? We argue that there are two
important cues: modeling temporal shape dynamics and modeling functional relationships …

Humans perceive the three-dimensional structure of the world with apparent ease. However,
despite all of the recent advances in computer vision research, the dream of having a …

Is strong supervision necessary for learning a good visual representation? Do we really
need millions of semantically-labeled images to train a Convolutional Neural Network …

We seek to build a large collection of images with ground truth labels to be used for object
detection and recognition research. Such data is useful for supervised learning and …

In this paper, we present an approach for learning a visual representation from the raw
spatiotemporal signals in videos. Our representation is learned without supervision from …