4.4k citations · 4.8k across the 50 of their papers we have counts for
53 papers
Forecasting Early with Meta Learning
Shayan Jawed, Kiran Madhusudhanan, Vijaya Krishna Yalavarthi +1
In the early observation period of a time series, there might be only a few historic observations available to learn a model. However, in cases where an existing prior set of datas…
DeepStay: Stay Region Extraction from Location Trajectories using Weak Supervision
Christian Löwens, Daniela Thyssens, Emma Andersson +2
Nowadays, mobile devices enable constant tracking of the user's position and location trajectories can be used to infer personal points of interest (POIs) like homes, workplaces, o…
Phantom Embeddings: Using Embedding Space for Model Regularization in Deep Neural Networks
Mofassir ul Islam Arif, Mohsan Jameel, Josif Grabocka +1
The strength of machine learning models stems from their ability to learn complex function approximations from data; however, this strength also makes training deep neural networks…
Directly Optimizing IoU for Bounding Box Localization
Mofassir ul Islam Arif, Mohsan Jameel, Lars Schmidt-Thieme
Object detection has seen remarkable progress in recent years with the introduction of Convolutional Neural Networks (CNN). Object detection is a multi-task learning problem where…
Neural Capacitated Clustering
Jonas K. Falkner, Lars Schmidt-Thieme
Recent work on deep clustering has found new promising methods also for constrained clustering problems. Their typically pairwise constraints often can be used to guide the partiti…
Auxiliary Quantile Forecasting with Linear Networks
Shayan Jawed, Lars Schmidt-Thieme
We propose a novel multi-task method for quantile forecasting with shared Linear layers. Our method is based on the Implicit quantile learning approach, where samples from the Unif…