• Publications
  • Influence
Beyond PASCAL: A benchmark for 3D object detection in the wild
TLDR
We introduce PASCAL3D+ dataset, which is a novel and challenging dataset for 3D object detection and pose estimation. Expand
  • 499
  • 132
  • PDF
The Role of Context for Object Detection and Semantic Segmentation in the Wild
TLDR
We propose a novel deformable part-based model, which exploits both local context around each candidate detection as well as global context at the level of the scene. Expand
  • 672
  • 113
  • PDF
Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts
TLDR
We propose a novel approach to i) handle large deformations and partial occlusions in animals (as examples of highly deformable objects), ii) describe them in terms of body parts, and iii) detect them when they are hard to detect (e.g., animals depicted at low resolution). Expand
  • 348
  • 75
  • PDF
Target-driven visual navigation in indoor scenes using deep reinforcement learning
TLDR
We proposed a deep reinforcement learning (DRL) framework for target-driven visual navigation. Expand
  • 729
  • 72
  • PDF
On Evaluation of Embodied Navigation Agents
TLDR
We convened a working group to study empirical methodology in navigation research. Expand
  • 174
  • 43
  • PDF
AI2-THOR: An Interactive 3D Environment for Visual AI
We introduce The House Of inteRactions (THOR), a framework for visual AI research, available at this http URL AI2-THOR consists of near photo-realistic 3D indoor scenes, where AI agents can navigateExpand
  • 226
  • 36
  • PDF
ObjectNet3D: A Large Scale Database for 3D Object Recognition
TLDR
We contribute a large scale database for 3D object recognition, named ObjectNet3D, that consists of 100 categories, 90,127 images, 201,888 objects in these images and 44,147 3D shapes. Expand
  • 159
  • 22
  • PDF
Visual Semantic Navigation using Scene Priors
TLDR
We propose to use Graph Convolutional Networks (GCNs) (Kipf & Welling, 2017) to incorporate the prior knowledge into a deep reinforcement learning framework. Expand
  • 75
  • 12
  • PDF
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning
TLDR
In this paper we propose a self-adaptive visual navigation method (SAVN) which learns to adapt to new environments without any explicit supervision. Expand
  • 49
  • 11
  • PDF
Bottom-Up Segmentation for Top-Down Detection
TLDR
We propose a novel deformable part-based model which exploits region-based segmentation algorithms that compute candidate object regions by bottom-up clustering followed by ranking of those regions. Expand
  • 131
  • 8
  • PDF