Dhruv Batra

TL;DR: This work proposes Seq-CVAE which learns a latent space for every word which encourages this temporal latent space to capture the 'intention' about how to complete the sentence by mimicking a representation which summarizes the future.

TL;DR: This paper presented an approach to simultaneously perform semantic segmentation and prepositional phrase attachment resolution for captioned images, which significantly outperforms the Stanford Parser (De Marneffe et al., 2006) by 17.91% (28.69% relative) and 12.83% (25.28%) in two different experiments.

TL;DR: CloudCV as discussed by the authors is a comprehensive system to provide access to state-of-the-art distributed computer vision algorithms as a cloud service through a Web Interface and APIs. But it does not address the same algorithmic, logistical, and infrastructural problems.

TL;DR: This paper proposes a multitask model which facilitates knowledge transfer across tasks by disentangling the knowledge of words and visual attributes in the intermediate representations and shows that this disentanglement of representations makes the model modular and interpretable which allows for transfer to instructions containing new concepts.

TL;DR: In this article, a modular architecture composed of a program generator, a controller, a navigator, and a VQA module is proposed to answer questions with multiple targets in them, such as "Is the dresser in the bedroom bigger than the oven in the kitchen?".