4 citations · 10 across the 10 of their papers we have counts for
10 papers
Almost Ramanujan Expanders from Arbitrary Expanders via Operator Amplification
Fernando Granha Jeronimo, Tushant Mittal, Sourya Roy +1
We give an efficient algorithm that transforms any bounded degree expander graph into another that achieves almost optimal (namely, near-quadratic, ) trade-off…
Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection
Kyle Min, Sourya Roy, Subarna Tripathi +2
Active speaker detection (ASD) in videos with multiple speakers is a challenging task as it requires learning effective audiovisual features and spatial-temporal correlations over…
Analyzing Ta-Shma's Code via the Expander Mixing Lemma
Silas Richelson, Sourya Roy
Random walks in expander graphs and their various derandomizations (e.g., replacement/zigzag product) are invaluable tools from pseudorandomness. Recently, Ta-Shma used s-wide repl…
Learning Spatial-Temporal Graphs for Active Speaker Detection
Sourya Roy, Kyle Min, Subarna Tripathi +2
We address the problem of active speaker detection through a new framework, called SPELL, that learns long-range multimodal graphs to encode the inter-modal relationship between au…
Mixing of 3-term progressions in Quasirandom Groups
Amey Bhangale, Prahladh Harsha, Sourya Roy
In this note, we show the mixing of three-term progressions in every finite quasirandom groups, fully answering a question of Gowers. More precisely, we show that f…
Incorporating Scalability in Unsupervised Spatio-Temporal Feature Learning
Sujoy Paul, Sourya Roy, Amit K. Roy-Chowdhury
Deep neural networks are efficient learning machines which leverage upon a large amount of manually labeled data for learning discriminative features. However, acquiring substantia…
W-TALC: Weakly-supervised Temporal Activity Localization and Classification
Sujoy Paul, Sourya Roy, Amit K Roy-Chowdhury
Most activity localization methods in the literature suffer from the burden of frame-wise annotation requirement. Learning from weak labels may be a potential solution towards redu…
WEPSAM: Weakly Pre-Learnt Saliency Model
Avisek Lahiri, Sourya Roy, Anirban Santara +2
Visual saliency detection tries to mimic human vision psychology which concentrates on sparse, important areas in natural image. Saliency prediction research has been traditionally…
Visual saliency detection: a Kalman filter based approach
Sourya Roy, Pabitra Mitra
In this paper we propose a Kalman filter aided saliency detection model which is based on the conjecture that salient regions are considerably different from our "visual expectatio…
Elastic Fidelity: Trading-off Computational Accuracy for Energy Reduction
Sourya Roy, Tyler Clemons, S M Faisal +3
Power dissipation and energy consumption have become one of the most important problems in the design of processors today. This is especially true in power-constrained environments…