International Publications

[P] Active Learning for Finely-Categorized Image-Text Retrieval by Selecting Hard Negative Unpaired Samples

[Paper]

[J] C2I-CAT: Class-to-Image Cross Attention Transformer for Out-of-Distribution Detection

[C] STXD: Structural and Temporal Cross-Modal Distillation for Multi-View 3D Object Detection

[J] How Much a Model Be Trained by Passive Learning Before Active Learning?

[J] Congestion-aware Bayesian Loss for Crowd Counting

[C] Class-Attentive Diffusion Network for Semi-supervised Classification

[P] Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels

[C] Associative Variational Auto-encoder with Distributed Latent Spaces and Associators

[C] Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification

[C] Real-time Scheme for 3-Dimensional Localizing and Tracking of People in Multiple Camera Settings

[C] Effect of Learning Rate to Generalization Power