Saved in:
Bibliographic Details
Main Authors: Vuong, Trinh T. L., Bui, Doanh C., Kwak, Jin Tae
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.13216
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916329303310336
author Vuong, Trinh T. L.
Bui, Doanh C.
Kwak, Jin Tae
author_facet Vuong, Trinh T. L.
Bui, Doanh C.
Kwak, Jin Tae
contents In this paper, we present our solutions for a spectrum of automation tasks in life-saving intervention procedures within the Trauma THOMPSON (T3) Challenge, encompassing action recognition, action anticipation, and Visual Question Answering (VQA). For action recognition and anticipation, we propose a pre-processing strategy that samples and stitches multiple inputs into a single image and then incorporates momentum- and attention-based knowledge distillation to improve the performance of the two tasks. For training, we present an action dictionary-guided design, which consistently yields the most favorable results across our experiments. In the realm of VQA, we leverage object-level features and deploy co-attention networks to train both object and question features. Notably, we introduce a novel frame-question cross-attention mechanism at the network's core for enhanced performance. Our solutions achieve the $2^{nd}$ rank in action recognition and anticipation tasks and $1^{st}$ rank in the VQA task.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13216
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle QuIIL at T3 challenge: Towards Automation in Life-Saving Intervention Procedures from First-Person View
Vuong, Trinh T. L.
Bui, Doanh C.
Kwak, Jin Tae
Computer Vision and Pattern Recognition
In this paper, we present our solutions for a spectrum of automation tasks in life-saving intervention procedures within the Trauma THOMPSON (T3) Challenge, encompassing action recognition, action anticipation, and Visual Question Answering (VQA). For action recognition and anticipation, we propose a pre-processing strategy that samples and stitches multiple inputs into a single image and then incorporates momentum- and attention-based knowledge distillation to improve the performance of the two tasks. For training, we present an action dictionary-guided design, which consistently yields the most favorable results across our experiments. In the realm of VQA, we leverage object-level features and deploy co-attention networks to train both object and question features. Notably, we introduce a novel frame-question cross-attention mechanism at the network's core for enhanced performance. Our solutions achieve the $2^{nd}$ rank in action recognition and anticipation tasks and $1^{st}$ rank in the VQA task.
title QuIIL at T3 challenge: Towards Automation in Life-Saving Intervention Procedures from First-Person View
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.13216