AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features from Multi-Modal Embeddings

Benchmark Model Rank Results
gzsl-video-classification-on-activitynet-gzsl-mainAVGZSLNet–HM: 6.44ZSL: 5.40
gzsl-video-classification-on-ucf-gzsl-mainAVGZSLNet–HM: 18.05ZSL: 13.65
gzsl-video-classification-on-vggsound-gzsl-mainAVGZSLNet–HM: 5.83ZSL: 5.28