Image Captioning On Nocaps Entire

CIDEr

METEOR

ROUGE-L

SPICE

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	B1	B2	B3	B4	CIDEr	METEOR	ROUGE-L	SPICE	Paper Title	Repository
firethehole	80.77	65.55	48.14	30.2	97.61	30.07	58.25	14.74	-	-
cxy_nocaps_training	78.75	59.36	37.56	19.72	78.48	25.13	52.54	11.57	-	-
GIT, Single Model	88.1	74.81	57.68	37.35	123.39	32.5	63.12	15.94	GIT: A Generative Image-to-text Transformer for Vision and Language
vinvl_yuan_cbs	79.32	60.95	39.5	20.3	79.04	25.44	53.8	11.9	-	-
Lyrics	-	-	-	-	126.8	-	-	-	Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects	-
Neural Baby Talk	72.33	52.42	30.83	14.73	53.36	21.52	48.87	9.15	-	-
ClipCap (Transformer)	-	-	-	-	65.83	-	-	10.86	ClipCap: CLIP Prefix for Image Captioning
Human	76.64	56.46	36.37	19.48	85.34	28.15	52.83	14.67	-	-
ViTCAP-CIDEr-136.7-ENC-DEC-ViTbfocal10-test-CBS	81.03	64.62	45.26	26.52	87.56	27.36	56.7	12.81	-	-
evertyhing	78.92	61.6	41.52	23.52	86.0	26.31	54.75	12.1	-	-
FudanWYZ	82.95	67.45	49.58	31.38	106.81	30.32	59.18	14.56	-	-
IEDA-LAB	83.25	67.3	48.41	29.27	98.08	28.92	58.56	13.9	-	-
CoCa - Google Brain	87.01	73.71	56.88	37.71	120.55	32.29	62.52	15.47	-	-
Neural Baby Talk + CBS	73.42	52.12	29.35	12.88	61.48	22.06	48.74	9.69	-	-
FudanFVL	83.9	68.77	50.84	32.17	108.29	30.64	59.82	14.72	-	-
Yu-Wu	67.85	47.37	25.76	11.96	46.18	19.84	46.61	8.35	-	-
VinVL (Microsoft Cognitive Services + MSR)	81.59	65.15	45.04	26.15	92.46	27.57	56.96	13.07	VinVL: Revisiting Visual Representations in Vision-Language Models
camel XE	77.97	60.27	40.68	23.48	75.88	26.15	54.3	11.89	-	-
B2	73.04	54.08	33.88	17.69	47.69	21.85	49.97	9.42	-	-
MD	82.43	66.25	47.18	28.2	93.0	28.09	57.57	13.35	-	-

0 of 39 row(s) selected.