← Audio captioning

Papers with Code · CC BY-SA 4.0

AudioCaps

아카이브 평가 18건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
MQ-Cap	CIDEr 0.845 SPIDEr 0.519 SPICE 0.194 BLEU-4 0.301 METEOR 0.266	Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning 2024-10-14	연결 없음
SLAM-AAC	CIDEr 0.841 SPIDEr 0.518 SPICE 0.194 METEOR 0.268 FENSE 0.668 SPIDEr-FL 0.515	SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs 2024-10-12	코드 1
LAVCap	CIDEr 0.849 SPIDEr 0.517 SPICE 0.185 BLEU-4 0.297 METEOR 0.262 ROUGE-L 0.510	LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport 2025-01-16	코드 1 · 코드 2
EnCLAP++-large	CIDEr 0.823 SPIDEr 0.510 SPICE 0.197 METEOR 0.269 FENSE 0.665	EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance 2024-09-02	코드 1
AutoCap	CIDEr 0.832 SPIDEr 0.507 SPICE 0.182 METEOR 0.253 ROUGE-L 0.518 ROUGE 0.518	Taming Data and Transformers for Audio Generation 2024-06-27	코드 1
LOAE	CIDEr 0.816 SPIDEr 0.505 SPICE 0.193 METEOR 0.267 FENSE 0.664 Sentence-BERT 0.664	Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding 2024-06-19	코드 1
EnCLAP++-base	CIDEr 0.815 SPIDEr 0.501 SPICE 0.188 METEOR 0.257 FENSE 0.661	EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance 2024-09-02	코드 1
EnCLAP-large	CIDEr 0.8029 SPIDEr 0.4954 SPICE 0.1879 METEOR 0.2554	EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning 2024-01-31	코드 1
CNext-trans	CIDEr 0.8061 SPIDEr 0.4951 SPICE 0.1841 METEOR 0.2527 FENSE 0.6431 SPIDEr-FL 0.4945 #params (M) 40	연결 없음 논문 날짜 미기재	연결 없음
EnCLAP-base	CIDEr 0.7795 SPIDEr 0.4829 SPICE 0.1863 METEOR 0.2473	EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning 2024-01-31	코드 1
AL-MixGen + Multi-TTA	CIDEr 0.769 SPIDEr 0.475 SPICE 0.181	연결 없음 논문 날짜 미기재	연결 없음
Rethink-ACT (AST + TF + MIL)	CIDEr 0.764 SPIDEr 0.472 SPICE 0.180 BLEU-4 0.285 METEOR 0.242 ROUGE-L 0.504	Rethinking Transfer and Auxiliary Learning for Improving Audio Captioning Transformer 2023-08-20	연결 없음
AL-MixGen	CIDEr 0.755 SPIDEr 0.466 SPICE 0.177	Exploring Train and Test-Time Augmentations for Audio-Language Learning 2022-10-31	연결 없음
BART + YAMNet + PANNs	CIDEr 0.753 SPIDEr 0.465 SPICE 0.176	AUTOMATED AUDIO CAPTIONING BY FINE-TUNING BART WITH AUDIOSET TAGS 2021-11-15	코드 1
CNN+Transformer	CIDEr 0.693 SPIDEr 0.426 SPICE 0.159	Audio Captioning Transformer 2021-07-21	코드 1
TopDown-AlignedAtt (1NN)	CIDEr 0.593 SPIDEr 0.369 SPICE 0.144	AudioCaps: Generating Captions for Audios in The Wild 2019-06-01	연결 없음
VAST	CIDEr 0.781 BLEU-4 0.295 METEOR 0.247 ROUGE-L 0.509	VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset 2023-05-29	코드 1 · 코드 2
VALOR	CIDEr 0.741 BLEU-4 0.270 METEOR 0.231 ROUGE-L 0.494	VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset 2023-04-17	코드 1