Visual Question Answering On Msrvtt 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
vid-TLDR (UMT-L)	0.470	vid-TLDR: Training Free Token merging for Light-weight Video Transformer
UMT-L (ViT-L/16)	0.471	Unmasked Teacher: Towards Training-Efficient Video Foundation Models
CLIPBERT	0.374	Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling
All-in-one+	0.395	Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models
Flamingo (32-shot)	0.310	Flamingo: a Visual Language Model for Few-Shot Learning
FrozenBiLM+	0.470	Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models
All-in-one-B	0.443	All in One: Exploring Unified Video-Language Pre-training
HBI	0.462	Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
Co-Mem	0.32	Motion-Appearance Co-Memory Networks for Video Question Answering	-
VideoCoCa	0.463	VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners	-
ST-VQA	0.309	TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering
Clover	0.441	Clover: Towards A Unified Video-Language Alignment and Fusion Model
ALPRO	0.421	Align and Prompt: Video-and-Language Pre-training with Entity Prompts
Co-Tokenization	.457	Video Question Answering with Iterative Video-Text Co-Tokenization	-
VLAB	0.496	VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending	-
HMEMA	0.33	Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering
X2-VLM (base)	0.45	X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
AIO+MDF	0.438	Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models
JustAsk+	0.418	Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models
LRCE	0.42	Lightweight Recurrent Cross-modal Encoder for Video Question Answering

0 of 34 row(s) selected.