41 citations · 76 across the 27 of their papers we have counts for
13 papers
Task-Aware Asynchronous Multi-Task Model with Class Incremental Contrastive Learning for Surgical Scene Understanding
Lalithkumar Seenivasan, Mobarakol Islam, Mengya Xu +2
Purpose: Surgery scene understanding with tool-tissue interaction recognition and automatic report generation can play an important role in intra-operative guidance, decision-makin…
Class Balanced PixelNet for Neurological Image Segmentation
Mobarakol Islam, Hongliang Ren
In this paper, we propose an automatic brain tumor segmentation approach (e.g., PixelNet) using a pixel-level convolutional neural network (CNN). The model extracts feature from mu…
Ischemic Stroke Lesion Segmentation Using Adversarial Learning
Mobarakol Islam, N Rajiv Vaidyanathan, V Jeya Maria Jose +1
Ischemic stroke occurs through a blockage of clogged blood vessels supplying blood to the brain. Segmentation of the stroke lesion is vital to improve diagnosis, outcome assessment…
Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding
Lalithkumar Seenivasan, Sai Mitheran, Mobarakol Islam +1
Global and local relational reasoning enable scene understanding models to perform human-like scene analysis and understanding. Scene understanding enables better semantic segmenta…
Class-Distribution-Aware Calibration for Long-Tailed Visual Recognition
Mobarakol Islam, Lalithkumar Seenivasan, Hongliang Ren +1
Despite impressive accuracy, deep neural networks are often miscalibrated and tend to overly confident predictions. Recent techniques like temperature scaling (TS) and label smooth…
Class-Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report Generation
Mengya Xu, Mobarakol Islam, Chwee Ming Lim +1
Generating surgical reports aimed at surgical scene understanding in robot-assisted surgery can contribute to documenting entry tasks and post-operative analysis. Despite the impre…