DDS: Decoupled Dynamic Scene-Graph Generation Network

no code implementations • 18 Jan 2023 • A S M Iftekhar, Raphael Ruschel, Satish Kumar, Suya You, B. S. Manjunath

Scene-graph generation involves creating a structural representation of the relationships between objects in a scene by predicting subject-object-relation triplets from input data.

Graph Generation Object +1

Context-Driven Detection of Invertebrate Species in Deep-Sea Video

no code implementations • 1 Jun 2022 • R. Austin McEver, BoWen Zhang, Connor Levenson, A S M Iftekhar, B. S. Manjunath

Each video includes annotations indicating the start and end times of substrates across the video in addition to counts of species of interest.

object-detection Object Detection

What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactions

no code implementations • CVPR 2022 • A S M Iftekhar, Hao Chen, Kaustav Kundu, Xinyu Li, Joseph Tighe, Davide Modolo

We propose a novel one-stage Transformer-based semantic and spatial refined transformer (SSRT) to solve the Human-Object Interaction detection task, which requires to localize humans and objects, and predicts their interactions.

Human-Object Interaction Detection Object

GTNet:Guided Transformer Network for Detecting Human-Object Interactions

1 code implementation • 2 Aug 2021 • A S M Iftekhar, Satish Kumar, R. Austin McEver, Suya You, B. S. Manjunath

For detecting HOI, it is important to utilize relative spatial configurations and object semantics to find salient spatial regions of images that highlight the interactions between human object pairs.

Human-Object Interaction Detection Object

StressNet: Detecting Stress in Thermal Videos

1 code implementation • 18 Nov 2020 • Satish Kumar, A S M Iftekhar, Michael Goebel, Tom Bullock, Mary H. MacLean, Michael B. Miller, Tyler Santander, Barry Giesbrecht, Scott T. Grafton, B. S. Manjunath

Precise measurement of physiological signals is critical for the effective monitoring of human vital signs.