Dataset Groups Activity Stream SoundNet The dataset is used for learning general and effective models for both audio and video analysis from self-supervised temporal synchronization. BibTex: @dataset{Yusuf_Aytar_and_Carl_Vondrick_and_Antonio_Torralba_2024, abstract = {The dataset is used for learning general and effective models for both audio and video analysis from self-supervised temporal synchronization.}, author = {Yusuf Aytar and Carl Vondrick and Antonio Torralba}, doi = {10.57702/rxj2grx3}, institution = {No Organization}, keyword = {'audio features', 'audio-visual', 'large-scale dataset', 'self-supervised learning', 'temporal synchronization', 'video analysis'}, month = {dec}, publisher = {TIB}, title = {SoundNet}, url = {https://service.tib.eu/ldmservice/dataset/soundnet}, year = {2024} }
