Author

Ti-Xun Wang

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Sep 2026

Benchmarking Pre-Trained Vision-Language Models for Bidirectional Image-Text Retrieval on MS-COCO: BERT+ResNet, CLIP, and BLIP

Results show a clear gap between independently combined unimodal encoders and pre-trained vision-language models, while longer captions are associated with higher text-to-image recall and plausible false negatives.

Ti-Xun Wang · Applied and Computational En... · 0 citations