5 papers · 1 filter
Modality Mixer Exploiting Complementary Information for Multi-modal Action Recognition
Sumin Lee, Sangmin Woo, Muhammad Adi Nugroho +1
Due to the distinctive characteristics of sensors, each modality exhibits unique physical properties. For this reason, in the context of multi-modal action recognition, it is impor…
Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification
Seokeon Choi, Sumin Lee, Youngeun Kim +2
Visible-infrared person re-identification (VI-ReID) is an important task in night-time surveillance applications, since visible cameras are difficult to capture valid appearance in…
SRG: Snippet Relatedness-based Temporal Action Proposal Generator
Hyunjun Eun, Sumin Lee, Jinyoung Moon +3
Recent temporal action proposal generation approaches have suggested integrating segment- and snippet score-based methodologies to produce proposals with high recall and accurate b…
Learning to Align Multi-Camera Domains using Part-Aware Clustering for Unsupervised Video Person Re-Identification
Youngeun Kim, Seokeon Choi, Taekyung Kim +2
Most video person re-identification (re-ID) methods are mainly based on supervised learning, which requires cross-camera ID labeling. Since the cost of labeling increases dramatica…
A Global-Local Emebdding Module for Fashion Landmark Detection
Sumin Lee, Sungchan Oh, Chanho Jung +1
Detecting fashion landmarks is a fundamental technique for visual clothing analysis. Due to the large variation and non-rigid deformation of clothes, localizing fashion landmarks s…