Search Results for author:
Found 12 papers, 5 papers with code
Synthesizing Traffic Datasets using Graph Neural Networks
This paper introduces a novel methodology for bridging this `sim-real' gap by creating photorealistic images from 2D traffic simulations and recorded junction footage.
Self-supervised Monocular Depth Estimation: Let's Talk About The Weather
For these architectures to be effective in real-world applications, we must create models that can generalise to all weather conditions, times of the day and image qualities.
Ranked #2 on
Unsupervised Monocular Depth Estimation
on KITTI-C
(using extra training data)
Multi-person 3D pose estimation from unlabelled data
Its numerous applications make multi-human 3D pose estimation a remarkably impactful area of research.
Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth Maps
Much of the recent work focuses on improving depth estimation by increasing architecture complexity.
Multi-camera Torso Pose Estimation using Graph Neural Networks
The proposal presented in this paper makes use of graph neural networks to merge the information acquired from multiple camera sources, achieving a mean absolute error below 125 mm for the location and 10 degrees for the orientation using low-resolution RGB images.
Look and Listen: A Multi-modality Late Fusion Approach to Scene Classification for Autonomous Machines
The image and the audio datasets are first classified independently, using a fine-tuned VGG16 and an evolutionary optimised deep neural network, with accuracies of 89. 27% and 93. 72%, respectively.
Domain Adaptation for Reinforcement Learning on the Atari
Deep reinforcement learning agents have recently been successful across a variety of discrete and continuous control tasks; however, they can be slow to train and require a large number of interactions with the environment to learn a suitable policy.
How to Read Paintings: Semantic Art Understanding with Multi-Modal Retrieval
Automatic art analysis has been mostly focused on classifying artworks into different artistic styles.
Dress like a Star: Retrieving Fashion Products from Videos
This work proposes a system for retrieving clothing and fashion products from video content.
Learning Non-Metric Visual Similarity for Image Retrieval
Theoretically, non-metric distances are able to generate a more complex and accurate similarity model than metric distances, provided that the non-linear data distribution is precisely captured by the system.
Large Scale Multi-view Stereopsis Evaluation
The seminal multiple view stereo benchmark evaluations from Middlebury and by Strecha et al. have played a major role in propelling the development of multi-view stereopsis methodology.
