research
∙
09/15/2022
Almost Ramanujan Expanders from Arbitrary Expanders via Operator Amplification
We give an efficient algorithm that transforms any bounded degree expand...
share
research
∙
07/15/2022
Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection
Active speaker detection (ASD) in videos with multiple speakers is a cha...
research
∙
01/26/2022
Analyzing Ta-Shma's Code via the Expander Mixing Lemma
Random walks in expander graphs and their various derandomizations (e.g....
research
∙
12/02/2021
Learning Spatial-Temporal Graphs for Active Speaker Detection
We address the problem of active speaker detection through a new framewo...
research
∙
09/26/2021
Mixing of 3-term progressions in Quasirandom Groups
In this note, we show the mixing of three-term progressions (x, xg, xg^2...
research
∙
08/06/2018
Incorporating Scalability in Unsupervised Spatio-Temporal Feature Learning
Deep neural networks are efficient learning machines which leverage upon...
research
∙
07/27/2018
W-TALC: Weakly-supervised Temporal Activity Localization and Classification
Most activity localization methods in the literature suffer from the bur...
research
∙
04/17/2016