To meet the needs of our users, we are constantly evolving our DeepVA product. The latest version is packed with new features and enhancements that give you greater customizability and improved performance. Read now about our updates that make DeepVA even more powerful and user-friendly.
Enhanced options for Face Recognition: choice of multiple models on the horizon
Face Recognition is getting a significant functionality upgrade: in the future, it will be possible to select multiple models during a face recognition pass. While currently, this option is only accessible via the API, this feature will soon be available in the user interface as well. Users will be able to select up to five models for more accurate face recognition.
New module for visual mining: Subtitle Detection
Our latest upgrade includes an innovative new module for visual mining — the Subtitle Detection. This module not only detects burned-in subtitles in the video but also analyzes their position, language, and text content. The exact area of the subtitle in the frame can be displayed as a heat map. This feature offers a wide range of applications, such as placing subtitles in a different language without obscuring subtitles already burned into the video.
What else is new? Bug Fixes & Co.
- Fix for a problem with Speech Recognition, when punctuation ends up in the next token instead of the current token
- Improve some minor performance issues in DeepVA worker deployments by limiting resources
Try the latest version of DeepVA and experience the power of AI-driven analytics with advanced customization and improved performance. Discover the limitless possibilities and get deeper insights with DeepVA’s cutting-edge features.
All DeepVA changelog updates are available here: https://docs.deepva.com/changelog/
