369 citations · 1.8k across the 93 of their papers we have counts for
13 papers · 1 filter
Mesh Convolution with Continuous Filters for 3D Surface Parsing
Huan Lei, Naveed Akhtar, Mubarak Shah +1
Geometric feature learning for 3D surfaces is critical for many applications in computer graphics and 3D vision. However, deep learning currently lags in hierarchical modeling of 3…
Advances in adversarial attacks and defenses in computer vision: A survey
Naveed Akhtar, Ajmal Mian, Navid Kardan +1
Deep Learning (DL) is the most widely used tool in the contemporary field of computer vision. Its ability to accurately solve complex problems is employed in vision research to lea…
Object-to-Scene: Learning to Transfer Object Knowledge to Indoor Scene Recognition
Bo Miao, Liguang Zhou, Ajmal Mian +2
Accurate perception of the surrounding scene is helpful for robots to make reasonable judgments and behaviours. Therefore, developing effective scene representation and recognition…
Controlled Caption Generation for Images Through Adversarial Attacks
Nayyer Aafaq, Naveed Akhtar, Wei Liu +2
Deep learning is found to be vulnerable to adversarial examples. However, its adversarial susceptibility in image caption generation is under-explored. We study adversarial example…
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation
Bo Miao, Mohammed Bennamoun, Yongsheng Gao +1
We propose a self-supervised spatio-temporal matching method, coined Motion-Aware Mask Propagation (MAMP), for video object segmentation. MAMP leverages the frame reconstruction ta…
CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency
Mohammad A. A. K. Jalwana, Naveed Akhtar, Mohammed Bennamoun +1
Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input. However, class-insensitivity of the ea…
Attack to Fool and Explain Deep Networks
Naveed Akhtar, Muhammad A. A. K. Jalwana, Mohammed Bennamoun +1
Deep visual models are susceptible to adversarial perturbations to inputs. Although these signals are carefully crafted, they still appear noise-like patterns to humans. This obser…
PC-DAN: Point Cloud based Deep Affinity Network for 3D Multi-Object Tracking (Accepted as an extended abstract in JRDB-ACT Workshop at CVPR21)
Aakash Kumar, Jyoti Kini, Mubarak Shah +1
In recent times, the scope of LIDAR (Light Detection and Ranging) sensor-based technology has spread across numerous fields. It is popularly used to map terrain and navigation info…
Physical world assistive signals for deep neural network classifiers -- neither defense nor attack
Camilo Pestana, Wei Liu, David Glance +2
Deep Neural Networks lead the state of the art of computer vision tasks. Despite this, Neural Networks are brittle in that small changes in the input can drastically affect their p…
Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud
Mingtao Feng, Zhen Li, Qi Li +6
3D object grounding aims to locate the most relevant target object in a raw point cloud scene based on a free-form language description. Understanding complex and diverse descripti…
Picasso: A CUDA-based Library for Deep Learning over 3D Meshes
Huan Lei, Naveed Akhtar, Ajmal Mian
We present Picasso, a CUDA-based library comprising novel modules for deep learning over complex real-world 3D meshes. Hierarchical neural architectures have proved effective in mu…
LSDAT: Low-Rank and Sparse Decomposition for Decision-based Adversarial Attack
Ashkan Esmaeili, Marzieh Edraki, Nazanin Rahnavard +2
We propose LSDAT, an image-agnostic decision-based black-box attack that exploits low-rank and sparse decomposition (LSD) to dramatically reduce the number of queries and achieve s…
Deep Learning Based 3D Segmentation: A Survey
Yong He, Hongshan Yu, Xiaoyan Liu +4
3D segmentation is a fundamental and challenging problem in computer vision with applications in autonomous driving and robotics. It has received significant attention from the com…