Flickr-8k

Flickr8k is a dataset that contains images and their corresponding textual descriptions, used to evaluate multimodal speech recognition systems.

Papers using Flickr-8k (3)

Speechclip+: Self-supervised Multi-task Representation Learning For Speech Via CLIP And Speech-image Data2024 · 3 citesSpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data2024VHASR: A Multimodal Speech Recognition System With Vision Hotwords2024