Video Captioning on MSVD

16개 결과 · ⬇ CSV · JSON

CIDEr

Rank	Model	CIDEr	BLEU-4	METEOR	ROUGE-L	GS	Extra Training Data	Paper	Code	Year
1	MaMMUT	195.6	–	–	–	–		MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks	lucidrains/mammut-pytorch	2023
2	VLAB	179.8	79.3	51.2	87.9	–	✓	VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending		2023
3	VALOR	178.5	80.7	51.0	87.9	–	✓	VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset	TXH-mercury/VALOR	2023
3	COSA	178.5	76.5	–	–	–	✓	COSA: Concatenated Sample Pretrained Vision-Language Foundation Model	txh-mercury/cosa	2023
5	mPLUG-2	165.8	70.5	48.4	85.3	–		mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video	modelscope/modelscope · x-plug/mplug-owl · alibaba/AliceMind · +1	2023
6	HowToCaption	154.2	70.4	46.4	83.2	–		HowToCaption: Prompting LLMs to Transform Video Annotations at Scale	ninatu/howtocaption	2023
7	HiTeA	146.9	71.0	45.3	81.4	–	✓	HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training		2022
8	Vid2Seq	146.2	–	45.3	–	–	✓	Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning	google-research/scenic · antoyang/VidChapters · KastanDay/video-pretrained-transformer	2023
9	VIOLETv2	139.2	–	–	–	–		An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling	tsujuifu/pytorch_empirical-mvm	2022
10	RTQ	123.4	66.9	–	82.2	–		RTQ: Rethinking Video-language Understanding Based on Image-text Model	SCZwangxiao/RTQ-MM2023 · sczwangxiao/tsgvs-mm2023	2023
11	CoCap (ViT/L14)	121.5	60.1	41.4	78.2	–		Accurate and Fast Compressed Video Captioning	acherstyx/CoCap	2023
12	VASTA (Vatex-backbone)	119.7	59.2	40.65	76.7	–		Diverse Video Captioning by Adaptive Spatio-temporal Attention	zohrehghaderi/vasta	2022
13	IcoCap (ViT-B/16)	110.3	59.1	39.5	76.5	–	✓	IcoCap: Improving Video Captioning by Compounding Images		2023
14	SEM-POS	108.3	60.1	38.5	76.0	607.1		SEM-POS: Grammatically and Semantically Correct Video Captioning		2023
15	VASTA (Kinetics-backbone)	106.4	56.1	39.1	74.5	–		Diverse Video Captioning by Adaptive Spatio-temporal Attention	zohrehghaderi/vasta	2022
16	IcoCap (ViT-B/32)	103.8	56.3	38.9	75.0	–	✓	IcoCap: Improving Video Captioning by Compounding Images		2023