HyperAI초신경

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

한국어

HyperAI초신경

Audio Captioning On Clotho

평가 지표

BLEU-4

CIDEr

METEOR

ROUGE-L

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	BLEU-4	CIDEr	METEOR	ROUGE-L	Paper Title	Repository
VALOR	16.2	0.423	17.4	38.2	VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset	-
RNN-GRU-EncDec + VGGish + Word2Vec	-	0.18	-	-	Audio Captioning using Gated Recurrent Units	-
VAST	19	0.519	19.3	40.8	VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset	-
Ensemble-RL	-	0.468	-	-	THE SJTU SYSTEM FOR DCASE2021 CHALLENGE TASK 6: AUDIO CAPTIONING BASED ON ENCODER PRE-TRAINING AND REINFORCEMENT LEARNING
Ensemble	-	0.400	-	-	THE DCASE 2021 CHALLENGE TASK 6 SYSTEM: AUTOMATED AUDIO CAPTIONING WITH WEAKLY SUPERVISED PRE-TRAING AND WORD SELECTION METHODS	-
Ensemble	-	0.319	-	-	The NTT DCASE2020 Challenge Task 6 system: Automated Audio Captioning with Keywords and Sentence Length Estimation	-
Qwen-Audio	-	0.441	-	-	Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models	-
SLAM-AAC	-	0.515	0.197	-	SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs	-
LOAE	-	0.513	0.197	-	Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding	-
Audio Flamingo (Pengi trainset)	17.4	0.489	18.7	39.4	Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities	-

0 of 10 row(s) selected.

Audio Captioning On Clotho | SOTA | HyperAI초신경