The Winter Conference on Applications of Computer Vision (WACV) is known as the Institute of Electrical and Electronics Engineers (IEEE) and the Technical Committee on Pattern Analysis and Machine Intelligence (PAMI-TC) premier meeting on applications of computer vision. This conference provides in-depth information on cutting edge research advances in algorithms and applications of computer vision technology. WACV attendees include academia, industry, and government representatives. Workshops, tutorials, and main sessions will promote collaboration, research and development, and insight into computer vision applications and technology.
Kitware is proud to continue our long-standing support by being a Silver sponsor of WACV 2021. In addition to our sponsorship, Anthony Hoogs, Kitware’s senior director of computer vision, is an area chair for the conference. He is also co-chairing the Third International Workshop on Human Activity Detection in Multi-camera, Continuous, Long-duration Video the day before the conference.
Human Activity Detection Workshop
The Third International Workshop on Human Activity Detection in Multi-camera, Continuous, Long-duration Video (HADCV’21) will be presented virtually on Tuesday, January 5 from 11 am – 3:15 pm EST. HADCV’21 will concentrate on human activity detection in multi-camera, continuous video streams. The ability to detect human activities is an important task in computer vision due to its wide range of applications, including public safety, eldercare/childcare, human-computer interaction, and more. This workshop aims to bring together diverse stakeholders to help advance human activity detection technology in multi-camera video streaming environments. HADCV’21 will primarily focus on activity detection algorithms, performance evaluation and characterization, and large dataset collections for activity detection. Research findings from the ActEV Challenge will also be presented.
Paper Presentation on Activity Recognition Dataset
Kitware will also be presenting the paper, A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection, written by Kellie Corona, Katie Osterdahl, Roddy Collins, Anthony Hoogs, in the main conference program. This paper introduces MEVA, a new, large-scale dataset for human activity recognition that is the basis for the ActEV Challenge. This dataset contains over 9,300 hours of untrimmed, continuous video, far more than any other published dataset for video analytics. It’s scripted to include diverse, simultaneous activities along with natural background activity. Our Computer Vision (CV) Team annotated 144 hours for 37 activity types, marking bounding boxes of actors and props. The resulting data includes video from 38 RGB and thermal IR cameras, 42 hours of UAV footage, as well as GPS tracks for the actors. Additional derived data includes camera models geo-registering the outdoor cameras and a dense 3D point cloud model of the outdoor scene. WACV hasn’t released the presentation schedule yet, so please check back soon for more information.
Kitware’s Computer Vision Team
Kitware is a leader in developing and advancing state-of-the-art technologies and capabilities for automated image and video analytics. As an early adopter of deep learning, this plays an essential role in everything we do. We are dedicated to researching and creating innovative techniques and technologies valuable to the computer vision community and our customers. Some of our key capabilities include:
- Complex activity, event, and threat detection
- Object detection and tracking
- Image and video scene understanding
- Cyber-physical systems
- Dataset Collection and Annotation
- Image and video forensics
- Deep learning
- Interactive, do-it-yourself artificial intelligence
- 3D vision and super resolution
Kitware’s CV Team is dedicated to advancing research and technology development, and we are looking for talented individuals to join us. To view our current open positions and to learn more about what it’s like to work at Kitware, please visit kitware.com/careers.