Visual Question Answering On Msvd Qa 1

評価指標

Accuracy

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	Accuracy	Paper Title	Repository
MuLTI	0.547	MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling	-
OmniVL	0.510	OmniVL:One Foundation Model for Image-Language and Video-Language Tasks	-
HMEMA	0.337	Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering
DualVGR	0.390	DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering
VAST	0.60	VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
HCRN	0.361	Hierarchical Conditional Relation Networks for Video Question Answering
Clover	0.524	Clover: Towards A Unified Video-Language Alignment and Fusion Model
All-in-one-B	0.483	All in One: Exploring Unified Video-Language Pre-training
AIO+MIF	0.467	Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models
InternVideo	0.555	InternVideo: General Video Foundation Models via Generative and Discriminative Learning
VideoCoCa	0.569	VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners	-
All-in-one+	0.438	Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models
X2-VLM (base)	0.528	X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
ST-VQA	0.313	TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering
MaMMUT (ours)	.602	MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks
UMT-L (ViT-L/16)	0.552	Unmasked Teacher: Towards Training-Efficient Video Foundation Models
LRCE	0.478	Lightweight Recurrent Cross-modal Encoder for Video Question Answering
Co-Mem	0.317	Motion-Appearance Co-Memory Networks for Video Question Answering	-
X2-VLM (large)	0.546	X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
VIOLET + MELTR	0.517	MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models

0 of 36 row(s) selected.