Description
Book Synopsis.- Landmark-Based Screening: Femoral Head Coverage and Graf Classification
in Infant Developmental Dysplasia of the Hip.
.- MVTN: A Multiscale Video Transformer Network for Hand Gesture Recognition.
.- One-Shot Image Restoration.
.- Medical Image Segmentation with SAM-generated Annotations.
.- Manipulating and Mitigating Generative Model Biases without Retraining.
.- Fake or JPEG? Revealing Common Biases in Generated Image Detection
Datasets.
.- Generated Bias: Auditing Internal Bias Dynamics of Text-To-Image Generative
Models.
.- A semiotic methodology for assessing the compositional effectiveness of generative
text-to-image models (Midjourney and DALLoE).
.- A Framework for Critical Evaluation of Text-to-Image Models: Integrating
Art Historical Analysis, Artistic Exploration, and Critical Prompt Engineering.
.- Civiverse: A Dataset for Analyzing User Engagement with Open-Source
TTI-Models.
.- Exploring the Boundaries of Content Moderation in Text-to-Image Generation.
.- Rethinking HTG Evaluation: Bridging Generation and Recognition.
.- Evaluation Framework for Feedback Generation Methods in Skeletal Movement
Assessment.
.- FaceOracle: Chat with a Face Image Oracle.
.- Makeup-Guided Facial Privacy Protection via Untrained Neural Network
Priors.
.- How to Squeeze An Explanation Out of Your Model.
.- How were you created? Explaining synthetic face images generated by diffusion
models.
.- Frequency Matters: Explaining Biases of Face Recognition in the Frequency
Domain.
.- How green is continual learning, really? Analyzing the energy consumption
in continual training of vision foundation models.
.- Architecture-Agnostic Unsupervised Gradient Regularization For
Parameter-Efficient Transfer Learning.
.- Foundation Model or Finetune? Evaluation of few-shot semantic segmentation
for river pollution.
.- Personalizing Multimodal Large Language Models for Image Captioning: An
Experimental Analysis.
.- Improved Baselines for Data-efficient Perceptual Augmentation of LLMs.
.- Watt for What: Rethinking Deep Learning’s Energy-Performance Relationship.
