Cross-modal retrieval

Benchmarks

Dataset Name	SOTA Method	Metric
Wikipedia	GNAH	mAP43.1	64	23d ago
Pascal Sentence	APKH	mAP59.2	64	23d ago
MIR Flickr	APKH	mAP87.4	64	23d ago
AEA 553 events (test)	SigLIP 2	Top-5 Recall54.6	48	3mo ago
Wikipedia (Average)	APKH	mAP39.6	32	23d ago
NUS-WIDE (Average)	APKH	mAP43.4	32	23d ago
Wikipedia (Unseen)	APKH	mAP35.9	32	23d ago
Pascal Sentence (Unseen)	APKH	mAP33.7	32	23d ago
NUS-WIDE (Unseen)	APKH	mAP31.6	32	23d ago
MIR Flickr (Unseen)	APKH	mAP73	32	23d ago
Pascal Sentence (Seen)	APKH	mAP60.2	32	23d ago
NUS-WIDE (Seen)	GNAH	mAP55.7	32	23d ago
MIR Flickr (Seen)	APKH	mAP87.6	32	23d ago
Cross-dataset Average MIR, NUS, PAS, WIKI	APKH	mAP50.3	32	23d ago
RSICD (test)	Full-FT GeoRSCLIP	Image-to-Text R@121.13	32	4mo ago
Clotho (test)	CART	R@146.4	29	4mo ago
RSITMD (test)	HarMA	R@1 (Image-to-Text)32.74	28	4mo ago
Flickr30k (test)	RCAR	Image-to-text Recall@182.3	25	4mo ago
MSR-VTT (test)		R@5 (V→T)64.9	23	1mo ago
AudioCaps (test)	OmniBind	R@159.1	23	4mo ago
CheXpert Plus		Recall@113.83	20	1mo ago
MIMIC-CXR		Recall@122.137	20	1mo ago
MSCOCO 1K	MURAL-LARGE	Mean Recall (ja)91.6	16	4mo ago
InstVL video (Global)	InstAP	T2V R@194.5	12	3mo ago
InstVL video (Instance)	InstAP	T2V Recall@160.63	12	3mo ago

Showing 25 of 64 rows