Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 5 of 5 for “"CLIP Embeddings"”.
-
On Language as an Interface for Controlling Image Generation
… of vision-language foundation models, such as CLIP and DALL·E, has significantly advanced the use of natural language for image generation and manipulation. These models learn broad alignments between visual and textual representations, enabling flexible and general-purpose multimodal …
-
Explainable Affective Computing with a CLIP-based Approach
… of large language models, epitomized by OpenAI's CLIP, has spurred significant advancements in various domains of artificial intelligence. One such domain, relatively under-investigated, is affective computing—the study and development of systems that can recognize and respond to human emotions …
-
Behind the Scenes: Evaluating Computer Vision Embedding Techniques for Discovering Similar Photo Backgrounds
… studies evaluating four different types of image embeddings – Inception, CLIP, MAE, and pHash – across a variety of metrics and techniques. We find that a workflow using CLIP embeddings combined with a background classifier and simulated user feedback performs best. We also discuss implications …
-
Language-Driven Robotics: Dynamic Closed-Loop Control for Complex Manipulation
… and efficient 3D representation technique, with CLIP embeddings to provide semantic understanding of the scene. Using Grounded-SAM2 for segmentation and Gaussian-based clustering for dynamic object detection, the system achieves high segmentation accuracy. Object tracking is handled with …
-
ADVANCEMENTS IN IMAGE SEGMENTATION: FROM SUPERVISED LEARNING TO ZERO-SHOT FOUNDATION MODELS
… and prototype-based similarity matching using CLIP embeddings. This training-free approach achieves robust segmentation across brain MRI, fetal ultrasound, and chest X-ray without task-specific fine tuning, reducing the performance gap between zero-shot and supervised models. Collectively, …