77 citations · 171 across the 21 of their papers we have counts for
6 papers · 1 filter
Spatio-Temporal Action Graph Networks
Roei Herzig, Elad Levi, Huijuan Xu +5
Events defined by the interaction of objects in a scene are often of critical importance; yet important events may have insufficient labeled examples to train a conventional deep m…
Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem
Alon Brutzkus, Amir Globerson
Empirical evidence suggests that neural networks with ReLU activations generalize better with over-parameterization. However, there is currently no theoretical analysis that explai…
Explaining Queries over Web Tables to Non-Experts
Jonathan Berant, Daniel Deutch, Amir Globerson +2
Designing a reliable natural language (NL) interface for querying tables has been a longtime goal of researchers in both the data management and natural language processing (NLP) c…
Learning Rules-First Classifiers
Deborah Cohen, Amit Daniely, Amir Globerson +1
Complex classifiers may exhibit "embarassing" failures in cases where humans can easily provide a justified classification. Avoiding such failures is obviously of key importance. I…
Predict and Constrain: Modeling Cardinality in Deep Structured Prediction
Nataly Brukhim, Amir Globerson
Many machine learning problems require the prediction of multi-dimensional labels. Such structured prediction models can benefit from modeling dependencies between labels. Recently…
Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
Roei Herzig, Moshiko Raboh, Gal Chechik +2
Machine understanding of complex images is a key goal of artificial intelligence. One challenge underlying this task is that visual scenes contain multiple inter-related objects, a…