QR Kod

Text-Guided Sports Highlights: A CLIP-Based Framework for Automatic Video Summarization

We present a text-guided framework for automatic sports video summarization that leverages Contrastive Language–Image Pretraining to classify frames as highlight or non-highlight from natural-language descriptions. The pipeline generates multiple highlight/non-highlight sentence pairs with a...

Ful tanımlama

Kaydedildi:
Asıl Yazarlar: Marcos Rodrigo, Carlos Cuevas, Narciso Garcia
Materyal Türü: Artigo
Dil:Inglês
Baskı/Yayın Bilgisi: IEEE 2025-01-01
Seri Bilgileri:IEEE Access
Konular:
Video summarization
vision language models
CLIP
highlight detection
deep learning
artificial intelligence
Online Erişim:https://ieeexplore.ieee.org/document/11298698/
Etiketler: Etiketle
Etiket eklenmemiş, İlk siz ekleyin!

Benzer Materyaller