Dataset Groups Activity Stream AudioCaps Audio-text retrieval aims at retrieving a target audio clip or caption from a pool of candidates given a query in another modality. BibTex: @dataset{Chris_Dongjoo_Kim_and_Byeongchang_Kim_and_Hyunmin_Lee_and_Gunhee_Kim_2024, abstract = {Audio-text retrieval aims at retrieving a target audio clip or caption from a pool of candidates given a query in another modality.}, author = {Chris Dongjoo Kim and Byeongchang Kim and Hyunmin Lee and Gunhee Kim}, doi = {10.57702/g3bbps7m}, institution = {No Organization}, keyword = {'AudioCaps', 'AudioSet', 'audio', 'audio captioning', 'audio dataset', 'dataset', 'retrieval', 'text'}, month = {nov}, publisher = {TIB}, title = {AudioCaps}, url = {https://service.tib.eu/ldmservice/dataset/audiocaps}, year = {2024} }
