HyperAIHyperAI

Command Palette

Search for a command to run...

Cross-modal Retrieval

Retrieving content across different modalities, such as finding images from text queries or finding text from image queries.

Leaderboard

46 models total

Benchmarks

Things EEG2
THINGS-MEG
THINGS-EEG
Flickr30K
chebi-20
Winoground
COCO
imagenet-r
minidomainnet
MEG
NICO++
Large Time Lags Location (LTLL)
FreeDom (CLIP-L/14)
VATEX
OVEN
InfoSeek
IGLUE
KVQA
LLaVA
Feint6K
MSR-VTT
E-VQA
DTD^2
OKVQA
Cola
MMEB
PCDes
SugarCREPE
AVSpeech
DiDeMo
ITCPR dataset
Word4Per (fuse)
PatternCom
WeiCom (RemoteCLIP)
ArxivQA
PHOENIX-2014T
PlotQA
ReactZyme
RSTPReid
NaturalBench
SlideVQA
MSVD
MSRVTT
ChartQA
MSCOCO
COCO-FG
InfoVQA
Urban-1K
ICFG-PEDES
Flickr-FG
Flickr-30K
time-synchronized lyrics and dance motions dataset
M-BEIR
VGBench
DocVQA
CUHK-PEDES
COCO-5K
TRUMANS+
WavText5K
TACoS
Weather
MassRET-20k
M^3C
ActivityNet-Captions
ANet
Charades-STA
EEG-3D
HUMANISE+
Kinetics-GEB+
LERF
LSMDC
Objaverse
MAD
ActivityNet
MassSpecGym
msrvtt-qa
MSVD-Indonesian
NegRefCOCOg
NSD Whole-brain
NSDGeneral