AVECL-UMONS DATABASE FOR AUDIO-VISUAL EVENT CLASSIFICATION AND LOCALIZATION

AVECL-UMONS is a dataset for audio-visual event classification and localization in the context of office environments. The dataset is composed of 11 event classes recorded at several realistic positions in two different rooms. The dataset comprises two types of sequences according to the number of events in the sequence. 2662 unilabel sequences and 2724 multilabel sequences are recorded corresponding to a total of 5.24 hours. The dataset is complementary to the SECL-UMons dataset (also available on zenodo). The SECL-UMons dataset includes recordings made with a microphone array while AVECL-UMONS includes recordings made with 4 webcams.