09:00 -09:15 AM Welcome and opening remarks, Dr. Anthony Hoogs | Kitware Inc.
09:15-09:45 AM Data Challenge Winners: Chu-Song Chen、Chien-Hung Chen、You-Yue Huang、Ping-Wei Huang、Jia-Jung Shao
IIS & CITI, Academia Sinica; MOST Joint Research Center for AI Technology and All Vista Healthcare
9:45-10:15 AM Paper Presentation 1
Title: Detection of Marine Animals in a New Underwater Dataset with Varying Visibility
Malte Pedersen, Joakim Bruslund Haurum, Rikke Gade, Niels Madsen, Thomas B. Moeslund (Aalborg University)
10:15-10:30 AM Dr. Derya Akkaynak | Princeton University
Title: Brief Intro to Sea-thru (A New Physics-Based Method to Remove Water From Underwater Images); Implications for Underwater Exploration, Conservation, and Computer Vision
10:30 AM Coffee Break
11:00-11:45 AM (Invited Talk) Dr. Randy Cutter | Randy Cutter, NOAA Southwest Fisheries Science Center
Title: Underwater Surveys, Imagery, and Advances in Automated Analysis for NOAA Fisheries
11:45-12:15 PM Paper Presentation 2
Title: Exemplar based Underwater Image Enhancement augmented by Wavelet Corrected Transforms
Adarsh Jamadandi (B.V.Bhoomaraddi college of Engineering), Uma Mudenagudi (KLE Technological University)
12:15 Lunch Break
1:30-2:10 PM (Invited Talk) Dr. David Kriegman | UC San Diego
Title: CoralNet: Computer Vision for Benthic Image Analysis
2:20-3:00PM (Invited Talk) Dr. Chuck Stewart | Rensselaer Polytechnic Institute
Title: Wildlife Population Analysis Using Wildbook: Computer Vision Challenges, Algorithms, and Applications
*****Important Note: For Dr. Chuck Stewart's talk, we will join the "Fine-Grained Visual Categorization" Workshop in Seaside Ballroom A. ****
3:00 PM Coffee Break
3:30-4:00 PM Paper Presentation 3
Title: Deep Learning for Semantic Segmentation of Coral Reef Images Using Multi-View Information
Suchendra Bhandarkar, Brian Hopkinson, Andrew C King (University of Georgia)
4:00 PM Closing Remarks
Manual annotation of imagery is the largest bottleneck to studying many important problems in the underwater domain. This workshop will convene experts and researchers from both marine science and computer vision communities to learn about the challenges, current work, and opportunities in marine imagery analysis. The workshop is currently accepting papers involving computer vision applied to aquatic environmental monitoring, including:
Please see our CMT page for paper submissions. The page limit is 8 pages, not including references, following the standard CVPR format. Each paper will be reviewed by at least two members of the program committee.
We provide annotated videos from the National Oceanic and Atmospheric Administration (NOAA) that show many species of fish, shellfish, underwater plants, and other biota, and we are looking for algorithms that will achieve the highest detection and classification accuracy of organisms in the provided videos! Please see the data challenge for details. Submissions will be evaluated against a test sequence withheld until the end of the competition, and the winners invited to the conference. Please note that you do not have to submit a paper to the workshop to participate in the data challenge.