369 citations · 1.8k across the 93 of their papers we have counts for
15 papers · 1 filter
Fast Parallel Bayesian Network Structure Learning
Jiantong Jiang, Zeyi Wen, Ajmal Mian
Bayesian networks (BNs) are a widely used graphical model in machine learning for representing knowledge with uncertainty. The mainstream BN structure learning methods require perf…
Fast Parallel Exact Inference on Bayesian Networks: Poster
Jiantong Jiang, Zeyi Wen, Atif Mansoor +1
Bayesian networks (BNs) are attractive, because they are graphical and interpretable machine learning models. However, exact inference on BNs is time-consuming, especially for comp…
Query Efficient Cross-Dataset Transferable Black-Box Attack on Action Recognition
Rohit Gupta, Naveed Akhtar, Gaurav Kumar Nayak +2
Black-box adversarial attacks present a realistic threat to action recognition systems. Existing black-box attacks follow either a query-based approach where an attack is optimized…
Simultaneous Multiple Object Detection and Pose Estimation using 3D Model Infusion with Monocular Vision
Congliang Li, Shijie Sun, Xiangyu Song +3
Multiple object detection and pose estimation are vital computer vision tasks. The latter relates to the former as a downstream problem in applications such as robotics and autonom…
3DMODT: Attention-Guided Affinities for Joint Detection & Tracking in 3D Point Clouds
Jyoti Kini, Ajmal Mian, Mubarak Shah
We propose a method for joint detection and tracking of multiple objects in 3D point clouds, a task conventionally treated as a two-step process comprising object detection followe…
Vision Transformer Based Model for Describing a Set of Images as a Story
Zainy M. Malakan, Ghulam Mubashar Hassan, Ajmal Mian
Visual Story-Telling is the process of forming a multi-sentence story from a set of images. Appropriately including visual variation and contextual information captured inside the…
Vision Transformers for Action Recognition: A Survey
Anwaar Ulhaq, Naveed Akhtar, Ganna Pogrebna +1
Vision transformers are emerging as a powerful tool to solve computer vision problems. Recent techniques have also proven the efficacy of transformers beyond the image domain to so…
Domain-invariant Prototypes for Semantic Segmentation
Zhengeng Yang, Hongshan Yu, Wei Sun +2
Deep Learning has greatly advanced the performance of semantic segmentation, however, its success relies on the availability of large amounts of annotated data for training. Hence,…
Region Aware Video Object Segmentation with Deep Motion Modeling
Bo Miao, Mohammed Bennamoun, Yongsheng Gao +1
Current semi-supervised video object segmentation (VOS) methods usually leverage the entire features of one frame to predict object masks and update memory. This introduces signifi…
Contrastive Self-Supervised Learning Leads to Higher Adversarial Susceptibility
Rohit Gupta, Naveed Akhtar, Ajmal Mian +1
Contrastive self-supervised learning (CSL) has managed to match or surpass the performance of supervised learning in image and video classification. However, it is still largely un…
Learning from Pixel-Level Noisy Label : A New Perspective for Light Field Saliency Detection
Mingtao Feng, Kendong Liu, Liang Zhang +3
Saliency detection with light field images is becoming attractive given the abundant cues available, however, this comes at the expense of large-scale pixel level annotated data wh…
UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning
Nazmul Karim, Mamshad Nayeem Rizve, Nazanin Rahnavard +2
Supervised deep learning methods require a large repository of annotated data; hence, label noise is inevitable. Training with such noisy data negatively impacts the generalization…
Visual Attention Methods in Deep Learning: An In-Depth Survey
Mohammed Hassanin, Saeed Anwar, Ibrahim Radwan +2
Inspired by the human cognitive system, attention is a mechanism that imitates the human cognitive awareness about specific information, amplifying critical details to focus more o…
DualConv: Dual Convolutional Kernels for Lightweight Deep Neural Networks
Jiachen Zhong, Junying Chen, Ajmal Mian
CNN architectures are generally heavy on memory and computational requirements which makes them infeasible for embedded systems with limited hardware resources. We propose dual con…
Bi-CLKT: Bi-Graph Contrastive Learning based Knowledge Tracing
Xiangyu Song, Jianxin Li, Qi Lei +3
The goal of Knowledge Tracing (KT) is to estimate how well students have mastered a concept based on their historical learning of related exercises. The benefit of knowledge tracin…