HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Video Question Answering On Msrvtt Qa

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Accuracy	Paper Title	Repository
FrozenBiLM	47.0	Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
mPLUG-2	48.0	mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
FrozenBiLM (0-shot)	16.7	Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
VIOLETv2	44.5	An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling
Singularity-temporal	43.9	Revealing Single Frame Bias for Video-and-Language Learning
HBI	46.2	Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
VALOR	49.2	VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
Singularity	43.5	Revealing Single Frame Bias for Video-and-Language Learning
VAST	50.1	VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
Mirasol3B	50.42	Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities	-
VindLU	44.6	VindLU: A Recipe for Effective Video-and-Language Pretraining
COSA	49.2	COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
MA-LMM	48.5	MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
EMCL-Net	45.8	Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations

0 of 14 row(s) selected.

Video Question Answering On Msrvtt Qa | SOTA | HyperAI초신경