Skip to search formSkip to main contentSkip to account menu

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

TLDR
The Visual Genome dataset is presented, which contains over 108K images where each image has an average of $$35$$35 objects, $$26$$26 attributes, and $$21$$21 pairwise relationships between objects, and represents the densest and largest dataset of image descriptions, objects, attributes, relationships, and question answer pairs.
View on Springer (opens in a new tab)

Scene Graph Generation by Iterative Message Passing

TLDR
This work explicitly model the objects and their relationships using scene graphs, a visually-grounded graphical structure of an image, and proposes a novel end-to-end model that generates such structured scene representation from an input image.
View on IEEE (opens in a new tab)

DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion

TLDR
DenseFusion is a generic framework for estimating 6D pose of a set of known objects from RGB-D images that processes the two data sources individually and uses a novel dense fusion network to extract pixel-wise dense feature embedding, from which the pose is estimated.
View on IEEE (opens in a new tab)

AI2-THOR: An Interactive 3D Environment for Visual AI

TLDR
AI2-THOR consists of near photo-realistic 3D indoor scenes, where AI agents can navigate in the scenes and interact with objects to perform tasks and facilitate building visually intelligent models.
View PDF on arXiv (opens in a new tab)

Visual7W: Grounded Question Answering in Images

TLDR
A semantic link between textual descriptions and image regions by object-level grounding enables a new type of QA with visual answers, in addition to textual answers used in previous work, and proposes a novel LSTM model with spatial attention to tackle the 7W QA tasks.
View on IEEE (opens in a new tab)

Target-driven visual navigation in indoor scenes using deep reinforcement learning

TLDR
This paper proposes an actor-critic model whose policy is a function of the goal as well as the current state, which allows better generalization and proposes the AI2-THOR framework, which provides an environment with high-quality 3D scenes and a physics engine.
View on IEEE (opens in a new tab)

Neural Task Programming: Learning to Generalize Across Hierarchical Tasks

TLDR
A novel robot learning framework called Neural Task Programming (NTP), which bridges the idea of few-shot learning from demonstration and neural program induction, and achieves strong generalization across sequential tasks that exhibit hierarchal and compositional structures.
View on IEEE (opens in a new tab)

SURREAL: Open-Source Reinforcement Learning Framework and Robot Manipulation Benchmark

TLDR
SURREAL, an open-source scalable framework that supports state-of-the-art distributed reinforcement learning algorithms, is introduced, which demonstrates that SURREAL algorithms outperform existing opensource implementations in both agent performance and learning efficiency.
View Paper (opens in a new tab)

Reinforcement and Imitation Learning for Diverse Visuomotor Skills

TLDR
This work proposes a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent and trains end-to-end visuomotor policies that map directly from RGB camera inputs to joint velocities.
View PDF on arXiv (opens in a new tab)

Reasoning about Object Affordances in a Knowledge Base Representation

TLDR
This work learns a knowledge base (KB) using a Markov Logic Network (MLN) and shows that a diverse set of visual inference tasks can be done in this unified framework without training separate classifiers, including zero-shot affordance prediction and object recognition given human poses.
View via Publisher (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)