The zero-shot performance of existing vision-language models (VLMs) such as CLIP is
limited by the availability of large-scale aligned image and text datasets in specific domains …

Zero-shot anomaly detection (ZSAD) methods detect anomalies without prior access to
known normal or abnormal samples within target categories. Existing methods typically rely …

Pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability
to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques …

Due to deteriorating environmental conditions and increasing human activity, conservation
efforts directed towards wildlife is crucial. Motion-activated camera traps constitute an …

Electrocardiograms (ECGs) are non-invasive diagnostic tools crucial for detecting cardiac
arrhythmic diseases in clinical practice. While ECG Self-supervised Learning (eSSL) …

Compositional zero-shot learning (CZSL) task aims to recognize unseen compositional
visual concepts, eg, sliced tomatoes, where the model is learned only from the seen …

Zero-shot inference is a powerful paradigm that enables the use of large pretrained models
for downstream classification tasks without further training. However, these models are …

With the advent of large language models (LLMs), numerous software service providers
(SSPs) are dedicated to developing LLMs customized for code generation tasks, such as …

Current approaches for open-vocabulary scene graph generation (OVSGG) use vision-
language models such as CLIP and follow a standard zero-shot pipeline--computing …

Abstract The Segment Anything Model (SAM) and CLIP are remarkable vision foundation
models (VFMs). SAM a prompt-driven segmentation model excels in segmentation tasks …