33 papers with code • 0 benchmarks • 2 datasets
Object Discovery is the task of identifying previously unseen objects.
These leaderboards are used to track progress in Object Discovery
Our key contribution is the collection of a large-scale dataset consisting of 150K human-played games with a total of 800K visual question-answer pairs on 66K images.
This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning.
In this paper, we identify that the problem is that the binary classifiers in existing proposal methods tend to overfit to the training categories.
The ability to decompose scenes into their object components is a desired property for autonomous agents, allowing them to reason and act in their surroundings.
Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development of related aerial robot applications.
Given an egocentric video/images sequence acquired by the camera, our algorithm uses both the appearance extracted by means of a convolutional neural network and an object refill methodology that allows to discover objects even in case of small amount of object appearance in the collection of images.
We contribute to this research thread with two findings: (1) a study correlating a given level of noisily labels to the expected drop in accuracy, for two deep architectures, on two different types of noise, that clearly identifies GoogLeNet as a suitable architecture for learning from Web data; (2) a recipe for the creation of Web datasets with minimal noise and maximum visual variability, based on a visual and natural language processing concept expansion strategy.