# CardiacCLIP: Video-based CLIP Adaptation for LVEF Prediction in a Few-shot Manner

arXiv: https://arxiv.org/abs/2509.17065 · HTML: https://mlsanity.com/paper/2509.17065/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 21 Sep 2025.

## Builds on (most cited first, 17 of 17)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Fine-tuned CLIP Models are Efficient Video Learners](https://mlsanity.com/paper/2212.03640/) (2022)
- [Balanced MSE for Imbalanced Visual Regression](https://mlsanity.com/paper/2203.16427/) (2022)
- [C-Mixup: Improving Generalization in Regression](https://mlsanity.com/paper/2210.05775/) (2022)
- [FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition](https://mlsanity.com/paper/2402.03241/) (2024)
- [GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation](https://mlsanity.com/paper/2309.11145/) (2023)
- [Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting](https://mlsanity.com/paper/2107.12619/) (2021)
- [Teach CLIP to Develop a Number Sense for Ordinal Regression](https://mlsanity.com/paper/2408.03574/) (2024)
- [Adaptive Contrast for Image Regression in Computer-Aided Disease Assessment](https://mlsanity.com/paper/2112.11700/) (2021)
- [A step towards understanding why classification helps regression](https://mlsanity.com/paper/2308.10603/) (2023)
- [Cyclical Self-Supervision for Semi-Supervised Ejection Fraction Prediction from Echocardiogram Videos](https://mlsanity.com/paper/2210.11291/) (2022)
- [CardiacNet: Learning to Reconstruct Abnormalities for Cardiac Disease Assessment from Echocardiogram Videos](https://mlsanity.com/paper/2410.20769/) (2024)
- [Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent Coding](https://mlsanity.com/paper/2410.20752/) (2024)

## Abstract (arXiv)

Echocardiography is a vital non-invasive modality for cardiac assessment, with left ventricular ejection fraction (LVEF) serving as a key indicator of heart function. Existing LVEF estimation methods depend on large-scale annotated video datasets, which are costly and limit adaptability across various clinical settings. Recent vision-language models for echocardiography, such as EchoCLIP, apply image-to-text pretraining but fail to capture crucial temporal dynamics and localized cardiac structures essential for accurate diagnosis. To address these challenges, we propose CardiacCLIP, a video-based framework that enhances LVEF prediction through attention-based frame aggregation and multi-resolution input scaling. Specifically, we introduce MFL (Multi Frame Learning), a novel attention-based mechanism for selectively fusing informative frames, and EchoZoom, a multi-scale feature extraction strategy that refines spatial representations of cardiac structures. As a novel adaptation of CLIP models for few-shot echocardiogram video analysis, our approach significantly improves diagnostic accuracy, reducing MAE by 2.07 on the EchoNet-Dynamic dataset under 1-shot setting. The code is available at https://github.com/xmed-lab/CardiacCLIP.