WACV 2024

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Jan 4-8, 2024 at the Waikoloa Beach Marriott Resort in Waikoloa, Hawaii

The Winter Conference on Applications of Computer Vision (WACV) is one of the most prestigious and selective conferences in the field of computer vision. With an acceptance rate typically below 30%, it is held annually and attracts leading researchers from academia and industry. WACV is a great opportunity to connect with other computer vision researchers and practitioners, and learn about the latest advancements.

Kitware is proud to be a Silver Sponsor of WACV 2024, and will have an in-person exhibit space (TP6). We look forward to showcasing our work in computer vision, and to contributing to the vibrant community of researchers and developers who are working to make computer vision more powerful and accessible. We are also speaking with potential applicants who are interested in joining our team of computer vision experts. Come meet our researchers and see what we’re working on!

If you can’t make it to WACV but would like to set up a meeting to learn more about our expertise, please contact our computer vision team. If you are interested in pursuing a career in Kitware, please complete this form.

Kitware’s Activities and Involvement

WACV emphasizes papers on systems and applications with significant, interesting vision components and is highly selective, with fewer than 30% of submissions accepted. We are proud to have two papers accepted at the main conference this year, in addition to moderating the plenary panel discussion and co-organizing a workshop. Brian Clipp, Ph.D., assistant director of computer vision at Kitware, is also serving as the demo and exhibits co-chair this year.

Concurrent Band Selection and Traversability Estimation from Long-Wave Hyperspectral Imagery in Off-Road Settings
Paper Presentation
Authors: Florence Yellin (Kitware), Scott McCloskey (Kitware), Cole Hill, Eric Smith (Kitware), and Brian Clipp (Kitware)

Autonomous navigation has become increasingly popular in recent years; However, most existing methods focus on on-road navigation and utilize active sensors, such as LiDAR. This paper instead focuses on autonomous off- road navigation using traversability estimation from passive sensors, specifically long-wave (LW) hyperspectral imagery (HSI). We present a method for selecting a subset of hyperspectral bands that are most useful for traversability estimation by designing a band selection module that designs a minimal sensor that measures sparsely-sampled spectral bands while jointly training a semantic segmentation network for traversability estimation.

FishTrack23: An Ensemble Underwater Dataset for Multi-Object Tracking
Paper Presentation
Authors: Matthew Dawkins (Kitware), Jack Prior, Bryon Lewis (Kitware), Robin Faillettaz, Thompson Banez, Mary Salvi (Kitware), Audrey Rollo, Julien Simon, Matthew Campbell, Matthew Lucero, Aashish Chaudhary (Kitware) Benjamin Richards, Anthony Hoogs (Kitware).
View Video | Read Paper

FishTrack23 dataset contains a large number of annotations to aid with training computer vision algorithms. The videos and annotations in the ensemble dataset were collected by NOAA Fisheries, Ifremer, and the California Department of Wildlife. In addition to the data, automated baseline algorithms were trained on the dataset, and integrated into graphical user interfaces (GUIs) to assist with annotating new datasets.

Plenary Panel Discussion with Industry and Government
Panel Discussion | Friday, January 5, 4-5 PM
Anthony Hoogs, Ph.D, Kitware’s vice president of AI, will be a panel moderator, along with Prof. Karl Ricanek from UNC Wilmington, for this plenary discussion between representatives from the U.S. government and industry who have experience in image and video surveillance.

4th Workshop on Real-World Surveillance: Applications and Challenges
Workshop | Sunday, January 7, Full Day
Co-Chair and Organizer: Anthony Hoogs, Ph.D.

Anthony will be the on-site chair for this workshop, which has been held at WACV for the past two years. Computer vision methods trained on public databases demonstrate performance drift when deployed for real-world surveillance, compared to their initial results on research test sets. In this workshop, we will review papers reporting their experimental results on any application of computer vision in real-world surveillance, challenges they have faced, and their mitigation strategies on topics such as:

• Object detection
• Tracking
• Re-identification
• Anomaly detection
• Scene understanding
• Super-resolution
• Multimodal surveillance

Furthermore, the workshop will bring special attention to legal and ethical issues of computer vision applications in real-world scenarios.

Kitware is Hiring

Our computer vision team is dedicated to finding innovative solutions to difficult data analysis and understanding problems using robust R&D techniques and Kitware’s open source platforms. If you are passionate about using computer vision to help make the world a better place, consider a career at Kitware.

Kitware has offices located in Clifton Park, NY, Carrboro, NC, Arlington, VA, and Minneapolis, MN. While our positions support remote, in-office, or hybrid work arrangements, some positions may have work location preferences or restrictions.

Join us in advancing the fields of computer vision and deep learning. Apply today!

If you are interested in working at Kitware, please complete this form.
Note: Most of our positions require U.S. citizenship. Due to the high volume of applicants, we will only send a personal follow-up if we feel your qualifications match our needs. Thank you!

Computer Vision Researcher
Conduct research and develop robust solutions in the areas of object/activity detection/recognition, motion pattern learning, anomaly detection, open-world learning, image forensics, explainable/ethical AI, and more.

3D Computer Vision Researcher
Conduct research and develop solutions for problems related to camera calibration, registration, structure from motion, neural rendering, neural implicit surfaces, surface meshing, and more.

Technical Leader of Computer Vision
Lead research efforts with an emphasis on computer vision supported by AI, machine learning, and deep learning. Have technical expertise and project management skills to lead teams of researchers, developers, and external collaborators to meet challenges in complex research programs. Lead commercial and federal business development activities to win R&D funding.

Natural Language Processing Researcher
Develop robust solutions in the areas of natural language processing, large language models, foundation models, ML, and AI. Conduct research and evaluate algorithms to understand the
textual content of textual and multi-modal data, and/or perform reasoning on extracted data. Leverage recent advances in large language models, with applications to use cases like information extraction, decision-making, understanding written instructions, and disinformation mitigation.

Technical Leader of Natural Language Processing
Lead research efforts with an emphasis on Natural Language Processing supported by Artificial Intelligence, Machine Learning, and Deep Learning and often in connection with Computer Vision.

Computer Vision Research Internships
Collaborate with Kitware computer vision experts for 3-6 months (e.g. Summer 2024), conduct research, and publish results at premier conferences. Open to Ph.D. students in computer vision and related fields.

Machine Learning Engineer
Collaborate with researchers on computer vision projects to design, implement, train, and test machine learning and artificial intelligence systems to solve real-world problems.

Join us in advancing the fields of computer vision and deep learning. Apply today!

If you are interested in working at Kitware, please complete this form.
Note: Most of our positions require U.S. citizenship. Due to the high volume of applicants, we will only send a personal follow-up if we feel your qualifications match our needs. Thank you!