activity
20192024
most citedGlobal-Reasoned Multi-Task Learning Model for Surgical Scene Understanding

41 citations · 76 across the 27 of their papers we have counts for

collaborators

13 papers

cs.AI2022

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…

eess.IV2022

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…

eess.IV2022

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…

eess.IV202241 cited

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…

cs.CV20219 cited

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…

cs.CV2021

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…