Scale-free and Task-agnostic Attack: Generating Photo-realistic Adversarial Patterns with Patch Quilting Generator

no code implementations • 12 Aug 2022 • Xiangbo Gao, Cheng Luo, Qinliang Lin, Weicheng Xie, Minmin Liu, Linlin Shen, Keerthy Kusumam, Siyang Song

\noindent Traditional L_p norm-restricted image attack algorithms suffer from poor transferability to black box scenarios and poor robustness to defense algorithms.

Adversarial Attack Image Classification +4

Contrastive Learning for Image Registration in Visual Teach and Repeat Navigation

1 code implementation • MDPI Sensors 2022 • Zdeněk Rozsypálek, George Broughton, Pavel Linder, Tomáš Rouček, Jan Blaha, Leonard Mentzl, Keerthy Kusumam, Tomáš Krajník

Visual teach and repeat navigation (VT&R) is popular in robotics thanks to its simplicity and versatility.

Contrastive Learning Image Registration +2

Two-stage Temporal Modelling Framework for Video-based Depression Recognition using Graph Representation

no code implementations • 30 Nov 2021 • Jiaqi Xu, Siyang Song, Keerthy Kusumam, Hatice Gunes, Michel Valstar

The short-term depressive behaviour modelling stage first deep learns depression-related facial behavioural features from multiple short temporal scales, where a Depression Feature Enhancement (DFE) module is proposed to enhance the depression-related clues for all temporal scales and remove non-depression noises.