The PDF version of program schedule can be downloaded here and a Program Summary can be downloaded here.
Program times are listed in Australian Eastern Standard Time Brisbane (GMT+10).8:30-9:00 | Registration |
9:00-10:30 |
Workshop 1 – Deep Learning with Images using MATLAB - a Hands-on Workshop
– Part 1
Dr Emmanuel Blanchard, MathWorks |
10:30-10:45 | Morning Tea |
10:45-12:00 |
Workshop 1 – Deep Learning with Images using MATLAB - a Hands-on Workshop
–
Part 2
Dr Emmanuel Blanchard, MathWorks |
12:00-13:00 | Lunch |
13:00-15:00 |
Workshop 2 – Deep Learning for Medical Image Analysis
Dr Yasmeen George, Deakin University Dr Syed Islam, Edith Cowan University |
15:00-15:15 | Afternoon Tea |
15:15-16:45 |
Workshop 3 – Fundamentals of Deep Learning – Cloud-based GPU
deployment and testing – Part 1
Dr Abdul Bais, University of Regina Dr Syed Afaq Shah, Murdoch University |
16:45-17:00 | Break |
17:00-18:15 |
Workshop 3 – Fundamentals of Deep Learning – Cloud-based GPU
deployment and testing – Part 2
Dr Abdul Bais, University of Regina Dr Syed Afaq Shah, Murdoch University |
8:00-8:45 | Registration |
8:45-9:00 | Conference Opening |
9:00-10:00 | Keynote 1 – Jeremy Howard, fast.ai, Australia |
10:00-10:30 | Morning Tea |
10:30-12:10 | Oral Session 1 – Award Candidate Session (20minutes each) |
12:10-13:10 | Group photo & Lunch |
13:10-14:10 | Keynote 2 – Stefan Hrabar, Emesent, Australia |
14:10-14:50 | Poster Session 1 Short Presentation – Online 3 Minute Each |
14:50-15:05 | Poster Session 1 Q&A – 4 Rooms |
14:50-15:20 | Afternoon Tea |
15:20-16:35 | Oral Session 2 – Remote Sensing (15 minutes each) |
16:35-17:15 | Poster Session 2 Short Presentation – 3 Minute Each |
17:15-17:30 | Poster Session 2 Q&A – 4 Rooms |
18:00-20:00 | Reception |
8:30-9:00 | Registration |
9:00-10:00 | Keynote 3 – Professor Mohammad Bennamoun, The University of Western Australia, Australia |
10:00-10:30 | Morning Tea |
10:30-11:50 | Oral Session 3 – Medical Imaging (15 minutes each) |
11:50-13:00 | Lunch |
13:00-13:45 | Oral Session 4 – Machine Learning (15 minutes each) |
13:45-14:25 | Poster Session 3 Short Presentation – Online 3 Minute Each |
14:25-14:40 | Poster Session 3 Q&A – 4 Rooms |
14:30-15:00 | Afternoon Tea |
15:00-15:45 | Oral Session 5 – 3D Data Processing (15 minutes each) |
15:45-16:20 | Poster Session 4 Short Presentation – Online 3 Minute Each |
16:20-16:35 | Poster Session 4 Q&A – 4 Rooms |
16:35-17:35 | APRS AGM |
18:00-22:30 | Skypoint Tour + Banquet + Award Ceremony |
8:30-9:00 | Registration |
9:00-10:00 | Keynote 4 – Tao Mei, JD.COM, China |
10:00-10:30 | Morning Tea |
10:30-11:45 | Oral Session 6 – Computer Vision (15 minutes each) |
11:45-13:00 | Lunch |
13:00-14:45 | Oral Session 7 – Detection and Classification (15 minutes each) |
14:45-15:15 | Afternoon Tea |
15:15-16:30 | Oral Session 8 - Applications |
16:30-16:50 | APRS Early career researcher award talk |
16:50-16:55 | Conference Closing |
8:00-8:45 |
Registration |
8:45-9:00 |
Conference Opening |
9:00-10:00 |
Keynote 1
What We've Learned about Creating Accurate
Image Models Quickly and Easily
|
10:00-10:30 |
Morning Tea – Ballroom Pre-Function Area |
10:30-12:10 |
Oral Session 1 – Award Candidate Session |
10:30-10:50 |
Quantum Annealing Formulation for Binary Neural
Networks
|
10:50-11:10
|
Semi-Supervised 3D Hand Shape and Pose Estimation
with Label Propagation
|
11:10-11:30
|
View Synthesis with Multi-scale Cost Aggregation
and Confidence Prior
|
11:30-11:50
|
Learning To Segment Dominant Object Motion From
Watching Videos
|
11:50-12:10 |
A Seq2seq-based Model with Global Semantic Context
for Scene Text Recognition
|
12:10-13:10 |
Group Photo and Lunch (Catch Restaurant) |
13:10-14:10 |
Keynote 2
Using autonomous drones to map and explore
underground mines
|
14:10-14:50 |
Poster Session 1 – 3-Minutes Spotlight |
1 |
Semantic Attribute Enriched Storytelling from a
Sequence of Images
|
2 |
Efficient DNN-Based Classification of Whole Slide
Gram Stain Images for Microbiology
|
3 |
Single-image object classification based on
illuminette construction from shadow imaging
|
4 |
Resource Constrained Human Presence Detection for
Indirect Time-of-Flight Sensors
|
5 |
Deep Learning Based Stereo Cost Aggregation on a Small Dataset Rongcheng Wu (UNSW); Changming Sun (CSIRO Data61); Zhaoying Liu (Beijing University of Technology); Arcot Sowmya (UNSW) |
6 |
Fully Convolutional Neural Network with Relation
Aware Context Information for Image
Parsing
|
7 |
Indoor Semantic Scene Understanding using Multi-modality Fusion Muraleekrishna Gopinathan (Edith Cowan University); Giang Ha Truong (Edith Cowan University); Jumana Abu-Khalaf (Edith Cowan University) |
8 |
Automatic Sheep Behaviour Analysis using Mask R-CNN JingSong Xu (University of Technology Sydney); Qiang Wu (University of Technology Sydney); Jian Zhang (UTS); Amy Tait (University of New England) |
9 |
Improved Spatio-temporal Action Localization for Surveillance Videos Morgan Liang (University of New South Wales); Xun Li (University of New South Wales); Sandersan Onie (University of New South Wales); Mark Larsen (University of New South Wales); Arcot Sowmya (University of New South Wales) |
10 |
A Multi-View DCNN Based Method for Breast Cancer Screening Nouha Derbel (University of Sfax); Hédi TMAR (University of Sfax); Adel Mahfoudhi (University of Sfax) |
11 |
EAR-NET: Error Attention Refining Network For Retinal Vessel Segmentation Jun Wang (King's College London); Yang Zhao (The University of Adelaide); Linglong Qian (King's College London); Xiaohan Yu (Griffith University); Yongsheng Gao (Griffith University) |
14:50-15:05 |
Poster Session 1 – Q&A |
14:50-15:20 |
Afternoon Tea – Ballroom Pre-Function Area |
15:20-16:35 |
Oral Session 2 – Remote Sensing |
15:20-15:35 |
High Definition LiDAR mapping of Perth
CBD
|
15:35-15:50 |
Reduction of Feature Contamination for
Hyper-Spectral Image Classification
|
15:50-16:05 |
Cross-Modality Visual Question Answering for Remote
Sensing
|
16:05-16:20 |
AF-Net: All-scale Feature Fusion Network for Road
Extraction from Remote Sensing Images
|
16:20-16:35 |
Burnt Forest Estimation from Sentinel-2 Imagery of
Australia using Unsupervised Deep Learning
|
16:35-17:15 |
Poster Session 2 – 3-Minutes Spotlight |
1 |
GuideNet: Learning Inter-Vertebral Guides in DXA
Lateral Spine Images
|
2 |
Seagrass Detection from Underwater Digital Images
using Faster R-CNN with NASNet
|
3 |
ODAR: A Lightweight Object Detection Framework for
Autonomous Driving Robots
|
4 |
Self-supervision, Remote Sensing and Abstraction:
Representation Learning across 3 million locations
|
5 |
Building Boundary Extraction from LiDAR Point Cloud
Data
|
6 |
Extraction of Forest Power lines From LiDAR point
cloud Data
|
7 |
Detection of Malleefowl Mounds from Point Cloud
Data
|
8 |
IoT-based Plant Health Analysis using Optical
Sensors in Precision Agriculture
|
9 |
Mask-Guided Feature Extraction and Augmentation for
Ultra-Fine-Grained Visual Categorization
|
10 |
Social E-commerce Tax Evasion Detection:
UsingMulti-modal Deep Neural Networks
|
11 |
Multi-Stratification Feature Selection for Multiple
Brain regions application
|
12 |
QuantYOLO: A High-Throughput and Power-Efficient
Object Detection Network for Resource and Power Constrained
UAVs
|
17:15-17:30 |
Poster Session – 2 Q&A |
18:00-20:00 |
Welcome Reception – Ballroom Pre-Function Area |
8:30-9:00 |
Registration |
9:00-10:00 |
Keynote 3
Computer and Robot Vision
|
10:00-10:30 |
Morning Tea – Ballroom Pre-Function Area |
10:30-11:50 |
Oral Session 3 – Medical Imaging |
10:30-10:45 |
Brain MRI Motion Artifact Reduction using 3D
Conditional Generative Adversarial Networks on Simulated
Motion
|
10:45-11:00 |
Two-stage U-Net++ for Medical Image
Segmentation
|
11:00-11:15 |
Slim-YOLO: A Simplified Object Detection Model for
the Detection of Pigmented Iris Freckles as a Potential Biomarker for
Cutaneous
Melanoma
|
11:15-11:30 |
OCT Retinal Image-To-Image Translation: Analysing
the Use of Cyclegan to Improve Retinal Boundary Semantic
Segmentation
|
11:30-11:45 |
Resetting the Baseline: CT-Based COVID-19
Diagnosis with Deep Transfer Learning is not as Accurate as Widely
Thought
|
11:50-13:00 |
Lunch – Catch Restaurant |
13:00-13:45 |
Oral Session 4 – Machine Learning |
13:00-13:15 |
Automatic Pruning for Quantized Neural
Networks
|
13:15-13:30 |
Streaming Multi-layer Ensemble Selection using
Dynamic Genetic Algorithm
|
13:30-13:45 |
License Plate Detection and Recognition System for
All Types of Bangladeshi Vehicles Using Multi-step Deep Learning
Model
|
13:45-14:25 |
Poster Session 3 – 3-Minutes Spotlight |
1 |
Three-Dimensional Tumour Microenvironment
Reconstruction and Tumour-Immune Interactions’ Analysis
|
2 |
Texture Enhanced Statistical Region Merging with
Application to Automatic Knee Bones Segmentation from CT
|
3 |
HEp-2 Specimen Cell Detection and Classification
Using Very Deep Convolutional Neural Networks-Based Cell
Shape
|
4 |
Elimination of Central Artefacts of L-SPECT with
Modular Partial Ring Detectors by Shifting Center of Scanning
|
5 |
Multi-Dataset Benchmarks for Masked Identification
using Contrastive Representation Learning
|
6 |
Protecting Deep Cerebrospinal Fluid Cell Image
Processing Models with Backdoor and Semi-Distillation
|
7 |
Overlapping Cell Nuclei Segmentation in Digital
Histology Images using Intensity-based Contours
|
8 |
Image Data Augmentation for Improving Performance
of Deep Learning-Based Model in Pathological Lung Segmentation
|
9 |
Use of Uncertainty Quantification as a Surrogate
for Layer Segmentation Error in Stargardt’s Disease Retinal OCT
Images
|
10 |
OCT Chorio-Retinal Segmentation with Adversarial
Loss
|
11 |
Similarity Learning based Few Shot Learning for ECG
Time Series Classification
|
12 |
GAN-based Spatial Transformation Adversarial Method
for Disease Classification on CXR Photographs by Smartphones
|
14:25-14:40 |
Poster Session 3 – Q&A |
14:30-15:00 |
Afternoon Tea – Ballroom Pre-Function Area |
15:00-15:45 |
Oral Session 5 – 3D Data Processing |
15:00-15:15 |
3D Morphable Ear Model: A Complete Pipeline from
Ear Segmentation to Statistical Modeling
|
15:15-15:30 |
Full Series Algorithm of Automatic Building
Extraction and Modelling From LiDAR Data
|
15:30-15:45 |
Edge Aware Commonality Modeling based Reference
Frame for 360 Degree Video Coding
|
15:45-16:20 |
Poster Session 4 – 3-Minutes Spotlight |
1 |
Lumbar Spine CT synthesis from MR images using
CycleGAN
|
2 |
Towards Automated Performance Assessment for
Laparoscopic Box Trainer using Cross-Stage Partial Network
|
3 |
Rapid Segmentation of Thoracic Organs using U-Net
Architecture
|
4 |
Video-Based Cattle Identification and Action
Recognition
|
5 |
Combining Data Augmentation and Domain Distance
Minimisation to Reduce Domain Generalisation Error
|
6 |
A Comparison of Saliency Methods for Deep Learning
Explainability
|
7 |
A Chaos Theory Approach to Understand Neural
Network Optimization
|
8 |
Robust Re-identification of Manta Rays from Natural
Markings by Learning Pose Invariant Embeddings
|
9 |
A Generative Deep Learning Approach for Forensic
Facial Reconstruction
|
10 |
Incremental Learning of Object Detector with
Limited Training Data
|
11 |
The Role of Machine Learning in Game
Development Domain - A Review of Current Trends and Future
Directions
|
12 |
Point Cloud Registration with Self-supervised
Feature Learning and Beam Search
|
16:20-16:35 |
Poster Session 4 – Q&A |
16:35-17:35 |
APRS AGM |
18:00-22:30 |
Skypoint Tour + Banquet + Award Ceremony |
8:30-9:00 |
Registration |
9:00-10:00 |
Keynote 4
Towards Deep Visual Understanding: from Perception
to Cognition
|
10:00-10:30 |
Morning Tea – Ballroom Pre-Function Area |
10:30-11:45 |
Oral Session 6 – Computer Vision |
10:30-10:45 |
SimilarityGAN: Using Similarity to Loosen
Structural Constraints in Generative Adversarial Models
|
10:45-11:00 |
Identifying Bikers Without Helmets Using Deep
Learning Models
|
11:00-11:15 |
A Novel Class-wise Forgetting Detector in Continual
Learning
|
11:15-11:30 |
Putting Current State Object Detectors to the Test:
Towards Industry Applicable Leather Surface Defect Detection
|
11:30-11:45 |
Semi-supervised Learning via Conditional Rotation
Angle Estimation
|
11:45-13:00 |
Lunch – Catch Restaurant |
13:00-14:45 |
Oral Session 7 – Detection and Classification |
13:30-13:45 |
Modeling Human Skeleton Joint Dynamics for Fall
Detection
|
13:45-14:00 |
A Compositional Feature Embedding and Similarity
Metric for Ultra-Fine-Grained Visual Categorization
|
14:00-14:15 |
Domain Adaptation for Plant Organ Detection with
Style Transfer
|
14:15-14:30 |
Flood Detection in Social Media Using Multimodal
Fusion on Multilingual Dataset
|
14:30-14:45 |
Multi-Resolution ResNet for Road and Bridge Crack
Detection
|
14:45-15:15 |
Afternoon Tea – Ballroom Pre-Function Area |
15:15-16:30 |
Oral Session 8 – Applications |
|
SCMNet: Shared Context Mining Network for Real-time
Semantic Segmentation
|
|
Edge-enhanced Instance Segmentation of Wrist CT via
a Semi-Automatic Annotation Database Construction Method
|
|
Attention-based Long-term Modeling for Deep Visual
Odometry
|
|
RE-Net: A Convolutional Neural Network for Retinal
Vessel Segmentation
|
|
Deep Adaptive Few Example Learning for Microscopy
Image Cell Counting
|
16:30-16:50 |
APRS Early career researcher award talk |
16:50-16:55 |
Conference Closing |