Xinhao Mei
6 papers
· 2022–2023
· 2 conferences
· across top CS/AI conferences
Achievements
π§
Keyword Pioneer
π
Conference Polyglot
(2)
π
Cross-Pollinator
(5)
π
Renaissance Researcher
(7)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(20)
Conferences
INTERSPEECH (5)
ICML (1)
Top co-authors
Keywords
audio representation
(2)
multimodal learning
(2)
machine translation
(1)
image captioning
(1)
cross-modal retrieval
(1)
audio-text retrieval
(1)
semantic hierarchy
(1)
audio source separation
(1)
feature fusion
(1)
evaluation metric
(1)
latent diffusion model
(1)
visual feature
(1)
transformer decoder
(1)
zero-shot generation
(1)
audio captioning
(1)
triplet loss
(1)
end-to-end neural network
(1)
mean average precision
(1)
natural language description
(1)
text-to-audio generation
(1)
Papers
Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention
INTERSPEECH 2023
Ontology-aware Learning and Evaluation for Audio Tagging
INTERSPEECH 2023
Separate What You Describe: Language-Queried Audio Source Separation
INTERSPEECH 2022
On Metric Learning for Audio-Text Cross-Modal Retrieval
INTERSPEECH 2022