Functions
scroll to learn more or view by subtopic
The listing below showcases the most recently published content associated with various AI and visual intelligence functions.
View all Posts
Scalable Video Search: Cascading Foundation Models
This article was originally published at Tenyks’ website. It is reprinted here with the permission of Tenyks. Video has become the lingua franca of the digital age, but its ubiquity presents a unique challenge: how do we efficiently extract meaningful information from this ocean of visual data? In Part 1 of this series, we navigate
Digica Collaborates with Toradex to Enhance Interactive Robotics with AI-driven Object Recognition on Torizon
March 7, 2025 – Digica, a leader in AI-driven solutions, is excited to announce its collaboration with Toradex to develop an advanced robotics system featuring real-time object recognition and dynamic change of user interface display. This collaboration integrates cutting-edge computer vision technology with interactive robotics, pushing the boundaries of human-machine interaction. Toradex, a leading provider
Zero-Shot AI: The End of Fine-tuning as We Know It?
This article was originally published at Tenyks’ website. It is reprinted here with the permission of Tenyks. Models like SAM 2, LLaVA or ChatGPT can do tasks without special training. This has people wondering if the old way (i.e., fine-tuning) of training AI is becoming outdated. In this article, we compare two models: YOLOv8 (fine-tuning)
3LC: What is It and Who is It For?
This blog post was originally published at 3LC’s website. It is reprinted here with the permission of 3LC. AI performance isn’t just about better architectures or more compute – it’s about better data. Even perfectly labeled datasets can hold hidden inefficiencies that limit accuracy. See how teams use 3LC to refine datasets, optimize labeling strategies,
Vision Language Model Prompt Engineering Guide for Image and Video Understanding
This blog post was originally published at NVIDIA’s website. It is reprinted here with the permission of NVIDIA. Vision language models (VLMs) are evolving at a breakneck speed. In 2020, the first VLMs revolutionized the generative AI landscape by bringing visual understanding to large language models (LLMs) through the use of a vision encoder. These
SAM 2 + GPT-4o: Cascading Foundation Models via Visual Prompting (Part 2)
This article was originally published at Tenyks’ website. It is reprinted here with the permission of Tenyks. In Part 2 of our Segment Anything Model 2 (SAM 2) Series, we show how foundation models (e.g., GPT-4o, Claude Sonnet 3.5 and YOLO-World) can be used to generate visual inputs (e.g., bounding boxes) for SAM 2. Learn
Nearly $1B Flows into Automotive Radar Startups
According to IDTechEx‘s latest report, “Automotive Radar Market 2025-2045: Robotaxis & Autonomous Cars“, newly established radar startups worldwide have raised nearly US$1.2 billion over the past 12 years; approximately US$980 million of which is predominantly directed toward the automotive sector. Through more than 40 funding rounds, these companies have driven the implementation and advancement of
New AI Model Offers Cellular-level View of Cancerous Tumors
This blog post was originally published at NVIDIA’s website. It is reprinted here with the permission of NVIDIA. Researchers studying cancer unveiled a new AI model that provides cellular-level mapping and visualizations of cancer cells, which scientists hope can shed light on how—and why—certain inter-cellular relationships triggers cancers to grow. BioTuring, a San Diego-based startup,
Top-tier ADAS Systems: Exploring Automotive Radar Technology
Radars have had a place within the automotive sector for over two decades, beginning with the first use for adaptive cruise control and many other developments taking place since. IDTechEx‘s “Automotive Radar Market 2025-2045: Robotaxis & Autonomous Cars” report explores the latest developments in radar technology within the automotive sector. ADAS safety systems ADAS (advanced
SAM 2 + GPT-4o: Cascading Foundation Models via Visual Prompting (Part 1)
This article was originally published at Tenyks’ website. It is reprinted here with the permission of Tenyks. In Part 1 of this article we introduce Segment Anything Model 2 (SAM 2). Then, we walk you through how you can set it up and run inference on your own video clips. Learn more about visual prompting
