ETRI-Knowledge Sharing Plaform



논문 검색
구분 SCI
연도 ~ 키워드


학술대회 Self-Conditional Crowd Activity Detection Network with Multi-label Classification Head
Cited 0 time in scopus Download 3 time Share share facebook twitter linkedin kakaostory
송순용, 배희철
International Conference on Information and Communication Technology Convergence (ICTC) 2022, pp.1875-1878
22ZR1100, 자율적으로 연결·제어·진화하는 초연결 지능화 기술 연구, 박준희
In this paper, we proposed new head network architecture in deep neural networks to classify categories for crowd activity. The proposed network was motivated by multi-label classification and conditional generative adversarial networks. In the head network, latent features were transformed into multi-label embedding vectors using pre-trained deep neural networks. The multi-label embedding vectors were regarded as the probability of relevant objects' existence. Then irrelevant embedding components were eliminated by the threshold layer. The refined multi-label embedding vectors are combined with pure latent feature vectors. Finally, a last linear layer predicted crowd activities. The proposed models configured ResNet back-bones with pre-trained weights. In terms of mean accuracy performances, our proposed models showed 1.55% higher in the best case, whereas 0.38% less in the worst case by comparing with baseline models.
KSP 제안 키워드
Activity Detection, Deep neural network(DNN), Feature Vector, Label embedding, Linear Layer, Network Architecture, conditional generative adversarial networks, latent features, multi-label classification, worst-case