SOTAVerified

AudioCaps

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 64 papers

TitleStatusHype
GLAP: General contrastive audio-text pretraining across domains and languagesCode2
AC/DC: LLM-based Audio Comprehension via Dialogue Continuation—0
IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling—0
Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning—0
AudioTurbo: Fast Text-to-Audio Generation with Rectified Diffusion—0
DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap—0
Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model—0
TAIL: Text-Audio Incremental Learning—0
ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution ErrorsCode0
Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning—0
ADIFF: Explaining audio difference using natural languageCode1
LAVCap: LLM-based Audio-Visual Captioning using Optimal TransportCode1
Language-based Audio Retrieval with Co-Attention Networks—0
ETTA: Elucidating the Design Space of Text-to-Audio ModelsCode2
Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning—0
SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMsCode0
DiffATR: Diffusion-based Generative Modeling for Audio-Text Retrieval—0
EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning PerformanceCode2
Dissecting Temporal Understanding in Text-to-Audio Retrieval—0
Estimated Audio-Caption Correspondences Improve Language-Based Audio RetrievalCode0
Fusing Audio and Metadata Embeddings Improves Language-based Audio Retrieval—0
Improving Text-To-Audio Models with Synthetic CaptionsCode5
MINT: a Multi-modal Image and Narrative Text Dubbing Dataset for Foley Audio Content Planning and GenerationCode0
Bridging Language Gaps in Audio-Text RetrievalCode1
SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound GenerationCode2
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.