Skip to search formSkip to main contentSkip to account menu

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

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)

Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation

This paper proposes a multimodal MAML (MMAML) framework, which is able to modulate its meta-learned prior parameters according to the identified mode, allowing more efficient fast adaptation and demonstrating the effectiveness of the model in modulating the meta-learning prior in response to the characteristics of tasks.
View PDF on arXiv (opens in a new tab)

Multi-view to Novel View: Synthesizing Novel Views With Self-learned Confidence

This paper proposes an end-to-end trainable framework that learns to exploit multiple viewpoints to synthesize a novel view without any 3D supervision, and introduces a self-learned confidence aggregation mechanism.
View via Publisher (opens in a new tab)

Learning and Using the Arrow of Time

A ConvNet suitable for extended temporal footprints and for class activation visualization, and the effect of artificial cues, such as cinematographic conventions, on learning is studied, which achieves state-of-the-art performance on large-scale real-world video datasets.
View on IEEE (opens in a new tab)

Accelerating Reinforcement Learning with Learned Skill Priors

This work proposes a deep latent variable model that jointly learns an embedding space of skills and the skill prior from offline agent experience, and extends common maximum-entropy RL approaches to use skill priors to guide downstream learning.
View PDF on arXiv (opens in a new tab)

Demo2Vec: Reasoning Object Affordances from Online Videos

The Demo2Vec model is designed which learns to extract embedded vectors of demonstration videos and predicts the interaction region and the action label on a target image of the same object.
View on IEEE (opens in a new tab)

High-fidelity facial and speech animation for VR HMDs

This work introduces a novel system for HMD users to control a digital avatar in real-time while producing plausible speech animation and emotional expressions and demonstrates the quality of the system on a variety of subjects and evaluates its performance against state-of-the-art real- time facial tracking techniques.
View on ACM (opens in a new tab)

Neural Program Synthesis from Diverse Demonstration Videos

This work proposes a neural program synthesizer that is able to explicitly synthesize underlying programs from behaviorally diverse and visually complicated demonstration videos and introduces a summarizer module as part of the model to improve the network’s ability to integrate multiple demonstrations varying in behavior.
View Paper (opens in a new tab)

Learning to Coordinate Manipulation Skills via Skill Behavior Diversification

The proposed framework is able to efficiently learn sub-skills with diverse behaviors and coordinate them to solve challenging collaborative control tasks such as picking up a long bar, placing a block inside a container while pushing the container with two robot arms, and pushing a box with two ant agents.
View Paper (opens in a new tab)

Program Guided Agent

Experimental results on a 2D Minecraft environment not only demonstrate that the proposed framework learns to reliably accomplish program instructions and achieves zero-shot generalization to more complex instructions but also verify the efficiency of the proposed modulation mechanism for learning the multitask policy.
View Paper (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)