Print Friendly, PDF & Email

The program below is provisional and will be updated as planning proceeds.

Please check this page regularly.

Program times are listed in AEDT. To convert program times to your timezone, CLICK HERE

Click a tab below to navigate to a particular day, or scroll down the page to view the whole program.

Monday 30 November 2020

Plenary Session
Session Chair – Lianhua Chi
08:30 – 10:00

Live: Conference Opening

Professor Paul Bonnington, DICTA 2020 Co-Chair
Professor Tom Drummond, DICTA 2020 Co-Chair
Dr. Zongyuan Ge, DICTA 2020 Co-Chair

Live: Keynote Address

Less is More: Visual Search without Image and User Ownership at the Edge

Professor Shaogang Gong, Queen Mary University of London 

10:05 – 10:21

Pre- Record: APRS Early Career Researcher Award – Finalist Presentation

Context modelling for human action recognition and anticipation

Dr Qiuhong Ke, The University of Melbourne

10:30 – 11:00 Break
Pre-Record Oral Session 1: Recognition
11:00 – 11:11

Contour Detection of Multiple Moving Objects in Unconstrained Scenes using Optical Strain

Maria Oliver-Parera, Julien Muzeau, Patrica Ladret, Pascal Bertolino

11:15 – 11:27

$\Mcal^2$-Net: A Multi-scale Multi-level Feature Enhanced Network for Object Detection in Optical Remote Sensing Images

Xinhai Ye, Fengchao Xiong, Jianfeng Lu, Haifeng Zhao, Jun Zhou

11:30 – 11:41

Efficient Brain Tumor Segmentation with Dilated Multi-fiber Network and Weighted Bi-directional Feature Pyramid Network

Thanh Hau Nguyen, Zhiyong Wang

11:45 – 11:57

W-A net: Leveraging Atrous and Deformable Convolutions for Efficient Text Detection

Zoya Khan, Sukhad Anand

12:00 – 12:11

Attentive Inception Module based Convolutional Neural Network for Image Enhancement

Purbaditya Bhattacharya, Udo Zoelzer

12:15 – 12:24

Network-based structure flow estimation

Shu Liu, Nick Barnes, Haolei Ye, Robert Mahony

12:30 – 13:00 Lunch Break
Plenary Session
13:00 – 13:31

Pre- Record: APRS Early Career Researcher Award – Finalist Presentation

Lightweight Neural Architectures for Efficient Deep Learning

Dr Chang Xu, The University of Sydney

13:32 – 13:55

Pre- Record: APRS Early Career Researcher Award – Finalist Presentation

Towards Data-Efficient Visual Segmentation

Dr Yunchao Wei, The University of Technology Sydney

Live Paper Discussion Session 1
14:00 – 15:00

Contour Detection of Multiple Moving Objects inUnconstrained Scenes using Optical Strain

Maria Oliver-Parera, Julien Muzeau, Patrica Ladret, Pascal Bertolino

$\Mcal^2$-Net: A Multi-scale Multi-level Feature Enhanced Network for Object Detection in Optical Remote Sensing Images

Xinhai Ye, Fengchao Xiong, Jianfeng Lu, Haifeng Zhao, Jun Zhou

Efficient Brain Tumor Segmentation with Dilated Multi-fiber Network and Weighted Bi-directional Feature Pyramid Network

Thanh Hau Nguyen, Zhiyong Wang

W-A net: Leveraging Atrous and Deformable Convolutions for Efficient Text Detection

Zoya Khan, Sukhad Anand

Attentive Inception Module based Convolutional Neural Network for Image Enhancement

Purbaditya Bhattacharya, Udo Zoelzer 

Network-based structure flow estimation

Shu Liu, Nick Barnes, Haolei Ye, Robert Mahony

Evolutionary Attention Network for Medical Image Segmentation

Tahereh Hassanzadeh, Daryl Essam, Sarker Ruhul

HCI for Elderly, Measuring Visual Complexity of Webpages Based on Machine Learning

Zahra Sadeghi, Elaheh Homayounvala, Mostafa Borhani

Visualizing and Understanding Inherent Image Features in CNN-based Glaucoma Detection

Dhaval Vaghjiani, Sajib K Saha, Yann Connan, Shaun Frost

Synthetic Data for the Analysis of Archival Documents: Handwriting Determination

Christian Bartz, Laurenz Seidel, Duy-Hung Nguyen, Joseph Bethge, Haojin Yang, Meinel Christoph

Vis-CRF: A Simplified Filtering Model for Vision

Nasim Nematzadeh, David M W Powers, Trent Lewis

Evaluation of U-Net CNN Approaches for Human Neck MRI Segmentation

Abdullah Al Suman, Yash Khemchandani, Md Asikuzzaman, Alexandra Louise Webb

Base-Package Recommendation Framework Based on Consumer Behaviours in IPTV Platform

Kuruparan Shanmugalingam, Ruwinda Ranganayake, Chanaka Gunawardhana, Rajitha Navarathna

Dynamic Decision Boundary for One-class Classifiers applied to non-uniformly Sampled Data

Riccardo La Grassa, Ignazio Gallo, Nicola Landro

Pseudo Supervised Solar Panel Mapping based on Deep Convolutional Networks with Label Correction Strategy in Aerial Images

Jue Zhang, Xiuping Jia, Jiankun Hu

Fruit Detection in the Wild: The Impact of Varying Conditions and Cultivar

Michael Halstead, Simon Denman, Clinton Fookes, Chris McCool

Density-Based Vehicle Counting with Unsupervised Scale Selection

Petr Dobe, Jakub Pa Hel, Vojt Ch Bartl, Roman Juránek, Adam Herout

PS8-Net: A Deep Convolutional Neural Network to Predict the Eight-State Protein Secondary Structure

Md Aminur Rab Ratul, Maryam Tavakol Elahi, Mohammad Hamed M.H Mozaffari, Won-Sook Lee

Moving object detection for humanoid navigation in cluttered dynamic indoor environments using a confidence tracking approach

Prabin Kumar Rath,  Alex Ramirez-Serrano,  Dilip Kumar Pratihar

Dual image and mask synthesis with GANs for semantic segmentation in optical coherence tomography 

Jason Kugelman, David Alonso-Caneiro, Scott A. Read, Stephen J. Vincent, Fred K. Chen, and Michael J.Collins

Live Networking Session
15:00 – 15:30 Delegate Speed Networking Event

Tuesday 1 December

Plenary Session
Session Chair – Mehrtash Harandi
09:00 – 10:00

Live: Welcome to Day 2

Dr. Zongyuan Ge, DICTA 2020 Co-Chair

Live: Keynote Address

The Role of Symmetry in Human and Computer Vision

Professor Sven Dickinson, University of Toronto 

10:00 – 10:31

Pre-Record: APRS Early Career Researcher Award – Finalist Presentation

Learning under label noise

Dr Tongliang Liu, The University of Sydney

10:30 – 11:00 Break
Pre-Record Oral Session 2: Applications
11:00 – 11:15

Multi-species Seagrass Detection and Classification from Underwater Images

Scarlett Raine, Ross Marchant, Peyman Moghadam, Frederic Maire, Brett Kettle, Brano Kusy

11:15 – 11:35

Fusing Visual Features and Metadata to Detect Flooding in Flickr Images

Rabiul Islam Jony,  Alan Woodley, Dimitri Perrin

11:35 – 11:43

A-DeepPixBis: Attentional Angular Margin for Face Anti-Spoofing

Md. Sourave Hossain, Labiba Rupty, Koushik Roy, Md Hasan, Shirshajit Sen Gupta, Nabeel Mohammed

11:45 – 12:00

Dual-Stage Domain Adaptive Mitosis Detection for Histopathology Images

Veena Dodballapur, Yang Song, Heng Huang, Mei Chen, Wojciech Chrzanowski, Weidong Cai

12:00 – 12:09

Tuna Nutriment Tracking using Trajectory Mapping in Application to Aquaculture Fish Tank

Muhamad Hilmil Muchtar Aditya Pradana, Keiichi Horio

12:15 – 12:24

Exploring Intensity Invariance in Deep Neural Networks for Brain Image Registration

Hassan Mahmood, Asim Iqbal, Syed Islam

12:30 – 13:00 Lunch Break
Plenary Session
Session Chair: Zongyuan Ge
13:00 – 14:00

Live: Keynote Address

Creating robots that see

Professor Peter Corke, Queensland University of Technology 

Live Paper Discussion Session 2
14:00 – 15:00

Multi-species Seagrass Detection and Classification from Underwater Images

Scarlett Raine, Ross Marchant, Peyman Moghadam, Frederic Maire, Brett Kettle, Brano Kusy

Fusing Visual Features and Metadata to Detect Flooding in Flickr Images

Rabiul Islam Jony,  Alan Woodley, Dimitri Perrin

A-DeepPixBis: Attentional Angular Margin for Face Anti-Spoofing

Md. Sourave Hossain, Labiba Rupty, Koushik Roy, Md Hasan, Shirshajit Sen Gupta, Nabeel Mohammed

Dual-Stage Domain Adaptive Mitosis Detection for Histopathology Images

Veena Dodballapur, Yang Song, Heng Huang, Mei Chen, Wojciech Chrzanowski, Weidong Cai

Tuna Nutriment Tracking using Trajectory Mapping in Application to Aquaculture Fish Tank

Muhamad Hilmil Muchtar Aditya Pradana, Keiichi Horio

Exploring Intensity Invariance in Deep Neural Networks for Brain Image Registration

Hassan Mahmood, Asim Iqbal, Syed Islam

UNET-Based Multi-Task Architecture for Brain Lesion Segmentation

Ava Assadi Abolvardi, Len Hamey, Kevin Ho-Shon

Recurrent Motion Neural Network for Low Resolution Drone Detection

Hamish C Pratt, Bernard JE Evans, Thomas Rowntree, Ian Reid, Steven Wiederman

Using Environmental Context to Synthesis Missing Pixels

Thaer Ali, Alan Woodley

FANet: Feature Aggregation Network for Semantic Segmentation

Tanmay Singha, Duc-Son Pham, Aneesh Krishna

Temporal 3D RetinaNet for fish detection

Zhou Shen, Chuong Nguyen

Secure Fingerprint Authentication with Homomorphic Encryption

Wencheng Yang, Song Wang, Kan Yu, James J Kang, Mike Johnstone

Recent Data Augmentation Strategies for Deep Learning in Plant Phenotyping and Their Significance

Douglas PS Gomes, Lihong Zheng

A Novel Signature Watermarking Scheme for Identity Protection

Sunpreet Sharma, Ju Jia Zou, Gu Fang

PlaneCalib: Automatic Camera Calibration by Multiple Observations of Rigid Objects on Plane

Vojt Ch Bartl, Roman Juránek, Jakub Pa Hel, Adam Herout

Learning Affordance Segmentation: An Investigative Study

Chau Nguyen Duc Minh, Syed Zulqarnain Gilani, Syed Islam, David Suter

An improved method for pylon extraction and vegetation encroachment analysis in high voltage transmission lines using LiDAR data

Nosheen Munir

Generalised Zero-shot Learning with Multi-modal Embedding Spaces

Rafael Felix, Michele Sasdelli, Ben Harwood, Gustavo Carneiro

A 3D-2D Registration Method for Stereo Scan Overlay on Structure from Motion Model

Deepak Rajamohan, Matthew Garratt, Mark Pickering

Automatic Assessment of Open Street Maps Database Quality using Aerial Imagery

Boris Repasky

Multitask Learning for Video-based Surgical Skill Assessment

Zhiteng Jian, Wenxi Yue, Qiuxia Wu, Wei Li, Zhiyong Wang, Vincent Lam

Live Networking Session
15:00 – 15:30 Delegate Speed Networking Event
APRS AGM
15:00 – 16:00

All DICTA attendees and APRS Members are invited to attend the APRS AGM. This session will be delivered directly via Zoom Meetings. 

Zoom Details

Please click the below URL to start or join. 

https://monash.zoom.us/j/83646816412?pwd=V1VrK0pvVUVoSFNlVWFQazlnWm1jdz09 

Or, go to https://monash.zoom.us/join and enter meeting ID: 836 4681 6412 and password: 235982

Wednesday 2 December 2020

Plenary Session
Session Chair – Leo Wu
09:00 – 10:00

Live: Welcome to Day 3

Professor Tom Drummond, DICTA 2020 Co-Chair

Live: Keynote Address

Learning for Human-Robot Interaction

Professor Dana Kulić, Monash University 

10:00 – 10:31

Pre-Record: APRS Early Career Researcher Award – Finalist Presentation

Vision-and-Language Navigation

Dr Qi Wu, The University of Adelaide

10:30 – 10:50 Break
Pre-Record Oral Session 3: Vision and Learning
 10:50 – 10:59

WEmbSim: A Simple yet Effective Metric for Image Captioning

Naeha Sharif, Lyndon White, Mohammed Bennamoun, Wei Liu, Syed Afaq Ali Shah

 11:00 – 11:15

Monocular Rotational Odometry with Incremental Rotation Averaging and Loop Closure

Chee Kheng Chng, Alvaro Parra, Tat-Jun Chin, Yasir Latif

 11:15 – 11:32

Space-Time Skeletal Analysis with Jointly Dual-Stream ConvNet for Action Recognition

Thien Huynh-The, Cam-Hao Hua, Nguyen Anh Tu, Dong-Seong Kim

 11:35 – 11:45

3D Reconstruction of Edge Line by ICP-based Matching with Geometric Constraints

Kojiro Takeyama

 11:45 – 11:57

Max-Variance Convolutional Neural Network Model Compression

Tanya Boone Sifuentes, Antonio Robles-Kelly, Asef Nazari

 12:00 – 12:15

Branch Profiles for Shape Analysis

Zayed Asiri, Brianna Martin, Murk Bottema

 12:15 – 12:27

MixCaps: Capsules With Iteration Free Routing

Ifty M. Rezwan, Mirza B Ahmed, Shazzad S Sourav, Ezab Quader, Arafat Hossain, Nabeel Mohammed

12:30 – 13:00 Lunch Break
Plenary Session
Session Chair – Lingqiao Liu
13:00 – 14:00

Live: Keynote Address

Deep Generative Prior

Associate Professor Chen Change Loy, Nanyang Technological University 

Session Chair – Zongyuan Ge
14:00 – 15:00

Live: APRS and Best Paper Awards Presentations – Presented by APRS President Zhiyong Wang

Live APRS Early Career Researcher Award – Finalist Q&A – Facilitated by Zongyuan Ge

Live: Closing Remarks

Live Paper Discussion Session 3
15:00 – 16:00

WEmbSim: A Simple yet Effective Metric for Image Captioning

Naeha Sharif, Lyndon White, Mohammed Bennamoun, Wei Liu, Syed Afaq Ali Shah

Monocular Rotational Odometry with Incremental Rotation Averaging and Loop Closure

Chee Kheng Chng, Alvaro Parra, Tat-Jun Chin, Yasir Latif

Space-Time Skeletal Analysis with Jointly Dual-Stream ConvNet for Action Recognition

Thien Huynh-The, Cam-Hao Hua, Nguyen Anh Tu, Dong-Seong Kim

3D Reconstruction of Edge Line by ICP-based Matching with Geometric Constraints

Kojiro Takeyama

Max-Variance Convolutional Neural Network Model Compression

Tanya Boone Sifuentes, Antonio Robles-Kelly, Asef Nazari

Branch Profiles for Shape Analysis

Zayed Asiri, Brianna Martin, Murk Bottema

MixCaps: Capsules With Iteration Free Routing

Ifty M. Rezwan, Mirza B Ahmed, Shazzad S Sourav, Ezab Quader, Arafat Hossain, Nabeel Mohammed

Object based remote sensing using Sentinel data

Connor McLaughlin, Alan Woodley, Shlomo Geva, Timothy Chappell, Wayne Kelly, Wageeh Boles, Dimitri Perrin, Lance De Vine, Holly Hutson

Automated Pneumoconiosis Detection on Chest X-Rays Using Cascaded Learning with Real and Synthetic Radiographs

Dadong Wang

SL3D – Single Look 3D Object Detection based on RGB-D Images

Gopi Krishna Erabati, Helder Araujo

Pixel-RRT*: A Novel Skeleton Trajectory Search Algorithm for Hepatic Vessels

Jianfeng Zhang

One-Shot learning based classification for segregation of plastic waste

Shivaank Agarwal, Ravindra Gudi, Paresh Saxena

Miss Yoga: A Yoga Assistant Mobile Application Based on Keypoint Detection

Renhao Huang, Jiqing Wang, Haodong Lu, Bofei Wang, Haowei Lou

Automated Computational Diagnosis of Peripheral Retinal Pathology in Optical Coherence Tomography (OCT) Scans using Graph Theory

Tyra Lange, Stewart Lake, Karen Reynolds, Murk Bottema

An Improved Discriminator for GAN-Based Trajectory Prediction Models

Renhao Huang, Yang Song, Maurice Pagnucco

CNN to Capsule Network Transformation

Takumi Sato, Kazuhiro Hotta

Strawberry Detection using Mixed Training on Simulated and Real Data

Akansel Cosgun, Sunny Goondram, Dana Kulic

A Survey on Training Free 3D Texture-less Object Recognition Techniques

Piyush Joshi, Ali Rastegarpanah, Rustam Stolkin

Furrow Mapping of Sugarcane Billet Density Using Deep Learning and Object Detection

Jordan P Scott, Andrew Busch

Feature-Extracting Functions for Neural Logic Rule Learning

Shashank Gupta, Antonio Robles-Kelly

3D Reconstruction and Object Detection for HoloLens

Zequn Wu, Tianhao Zhao, Chuong Nguyen

Thursday 3 December 2020

Post Conference Workshops will be delivered directly via Zoom Meetings. Zoom meeting details are provided below with each workshop listing.

Draft agenda Learning and Inference from Complex Data
Facilitator: Shirui Pan
Speakers: Yuan-Fang Li:  Complex Question Answering over Knowledge Graphs, Monash University
Mingming Gong: Causal Inference from Observational Data, The University of MelbourneZoom DetailsPlease click this URL to start or join. https://monash.zoom.us/j/82893657481?pwd=M1c1OTUzTFNsY3lxeW94Q25MV2xRdz09 Or, go to https://monash.zoom.us/join and enter meeting ID: 828 9365 7481 and password: 875632
10.00 – 10.45 Yuan-Fang Li:  Complex Question Answering over Knowledge Graphs, Monash University
10.45 – 11.30 Mingming Gong: Causal Inference from Observational Data, The University of Melbourne
Draft agenda Deep learning hands on tutorial for general audience

Lead instructor: Mitchell Hargreaves, Monash University

Zoom Details

Please click this URL to start or join. https://monash.zoom.us/j/81564801883?pwd=cDVLZ0w0d25DQllsTnBnRStJZVkwZz09
Or, go to https://monash.zoom.us/join and enter meeting ID: 815 6480 1883 and password: 663445

10:00 – 12:00 Introduction to Deep Learning (lecture + workshop)
12:00 – 13:00 Lunch break
13:00 – 15:00 Introduction to Convolutional Neural Networks (lecture + workshop)
15:00 – 15:30 Q&A
Draft agenda Vision-and-Language Grounding

14:00-16:00

Speakers:Qi Wu: Deep Reasoning in Vision and Language, Monash University
Reza Haffari: Neural Machine Translation, Monash University
Xiaojun Chang: Unsupervised Multimodal Machine Translation, Monash University

Zoom Details

Please click this URL to start or join. https://monash.zoom.us/j/89020817177?pwd=cFh2b1R3OUxUS0FGWFc1WGNRVDltdz09 Or, go to https://monash.zoom.us/join and enter meeting ID: 890 2081 7177 and password: 731035