S
Sami Abu-El-Haija
Researcher at University of Southern California
Publications - 39
Citations - 2776
Sami Abu-El-Haija is an academic researcher from University of Southern California. The author has contributed to research in topics: Graph (abstract data type) & Graph embedding. The author has an hindex of 16, co-authored 36 publications receiving 1977 citations. Previous affiliations of Sami Abu-El-Haija include Information Sciences Institute & Altera.
Papers
More filters
Posted Content
YouTube-8M: A Large-Scale Video Classification Benchmark
Sami Abu-El-Haija,Nisarg Dilipkumar Kothari,Joonseok Lee,Apostol Natsev,George Toderici,Balakrishnan Varadarajan,Sudheendra Vijayanarasimhan +6 more
TL;DR: YouTube-8M is introduced, the largest multi-label video classification dataset, composed of ~8 million videos (500K hours of video), annotated with a vocabulary of 4800 visual entities, and various (modest) classification models are trained on the dataset.
Posted Content
MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
Sami Abu-El-Haija,Bryan Perozzi,Amol Kapoor,Nazanin Alipourfard,Kristina Lerman,Hrayr Harutyunyan,Greg Ver Steeg,Aram Galstyan +7 more
TL;DR: This work proposes a new model, MixHop, that can learn a general class of neighborhood mixing relationships by repeatedly mixing feature representations of neighbors at various distances, and proposes sparsity regularization that allows to visualize how the network prioritizes neighborhood information across different graph datasets.
Proceedings ArticleDOI
Detecting Events and Key Actors in Multi-person Videos
Vignesh Ramanathan,Jonathan Huang,Sami Abu-El-Haija,Alexander Gorban,Kevin Murphy,Li Fei-Fei +5 more
TL;DR: In this paper, a recurrent neural network (RNN) was used to represent the track features of people in videos and learned time-varying attention weights to combine these features at each time-instant.
Posted Content
Machine Learning on Graphs: A Model and Comprehensive Taxonomy
TL;DR: A comprehensive taxonomy of representation learning methods for graph-structured data is proposed, aiming to unify several disparate bodies of work and provide a solid foundation for understanding the intuition behind these methods, and enables future research in the area.