Search Results for author:
Found 9 papers, 3 papers with code
Deep Bayesian Bandits: Exploring in Online Personalized Recommendations
Recommender systems trained in a continuous learning fashion are plagued by the feedback loop problem, also known as algorithmic bias.
Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems
The large model size usually entails a cost, in the range of millions of dollars, for storage and communication with the inference services.
Privacy-Aware Recommender Systems Challenge on Twitter's Home Timeline
Recommender systems constitute the core engine of most social network platforms nowadays, aiming to maximize user satisfaction along with other key business objectives.
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Deep learning frameworks have often focused on either usability or speed, but not both.
Addressing Delayed Feedback for Continuous Training with Neural Networks in CTR prediction
The focus of this paper is to identify the best combination of loss functions and models that enable large-scale learning from a continuous stream of data in the presence of delayed labels.
Faster gaze prediction with dense networks and Fisher pruning
Predicting human fixations from images has recently seen large improvements by leveraging deep representations which were pretrained for object recognition.
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images.
Ranked #3 on
Image Super-Resolution
on VggFace2 - 8x upscaling
Latent-Class Hough Forests for 6 DoF Object Pose Estimation
In this paper we present Latent-Class Hough Forests, a method for object detection and 6 DoF pose estimation in heavily cluttered and occluded scenarios.
Latent Regression Forest: Structured Estimation of 3D Articulated Hand Posture
In contrast to prior forest-based methods, which take dense pixels as input, classify them independently and then estimate joint positions afterwards; our method can be considered as a structured coarse-to-fine search, starting from the centre of mass of a point cloud until locating all the skeletal joints.
