Visual Question Answering On Msvd Qa 1

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Tableau comparatif

Nom du modèle	Accuracy
multi-efficient-video-and-language	0.547
omnivl-one-foundation-model-for-image	0.510
heterogeneous-memory-enhanced-multimodal	0.337
dualvgr-a-dual-visual-graph-reasoning-unit	0.390
vast-a-vision-audio-subtitle-text-omni-1	0.60
hierarchical-conditional-relation-networks	0.361
clover-towards-a-unified-video-language	0.524
all-in-one-exploring-unified-video-language	0.483
sas-video-qa-self-adaptive-sampling-for	0.467
internvideo-general-video-foundation-models	0.555
video-text-modeling-with-zero-shot-transfer	0.569
open-vocabulary-video-question-answering-a	0.438
x-2-vlm-all-in-one-pre-trained-model-for	0.528
tgif-qa-toward-spatio-temporal-reasoning-in	0.313
mammut-a-simple-architecture-for-joint	.602
unmasked-teacher-towards-training-efficient	0.552
lightweight-recurrent-cross-modal-encoder-for	0.478
motion-appearance-co-memory-networks-for	0.317
x-2-vlm-all-in-one-pre-trained-model-for	0.546
meltr-meta-loss-transformer-for-learning-to	0.517
hitea-hierarchical-temporal-aware-video	0.556
open-vocabulary-video-question-answering-a	0.558
cosa-concatenated-sample-pretrained-vision	0.60
mplug-2-a-modularized-multi-modal-foundation	0.581
vid-tldr-training-free-token-merging-for	0.549
sas-video-qa-self-adaptive-sampling-for	0.469
open-vocabulary-video-question-answering-a	0.495
ma-lmm-memory-augmented-large-multimodal	0.606
valor-vision-audio-language-omni-perception	0.60
align-and-prompt-video-and-language-pre	0.459
noise-estimation-using-density-estimation-for	0.351
video-question-answering-with-iterative-video	.486
an-empirical-study-of-end-to-end-video	0.547
vlab-enhancing-video-language-pre-training-by	0.61
git-a-generative-image-to-text-transformer	0.568
open-vocabulary-video-question-answering-a	0.477