Flickr30k
Introduced by Young et al. in From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions
The Flickr30k dataset contains 31,000 images collected from Flickr, together with 5 reference sentences provided by human annotators.
Source: Guiding Long-Short Term Memory for Image Caption GenerationBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
Flickr30k
|
X2-VLM
|
|||
|
Flickr30k
|
InternVL-G
|
|||
|
Flickr30K 1K test
|
X-VLM
|
|||
|
Flickr30k
|
InternVL-G-FT
|
|||
|
Flickr
|
GCN+GAugM
|
|||
|
Flickr30k Captions test
|
Unified VLP
|
|||
|
Flickr30k
|
BLIP-2 ViT-G
|
|||
|
Flickr30k
|
GBS Ensemble + 12-in-1
|
|||
|
Flickr30k
|
CapDec
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
