Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
RS-Net: Context-Aware Relation Scoring for Dynamic Scene Graph Generation
Hae-Won Jo, Yeong-Jun Cho
Dynamic Scene Graph Generation (DSGG) models how object relations evolve over time in videos. However, existing methods are trained only on annotated object pairs and lack guidance…
cs.CV2024
Object Re-identification via Spatial-temporal Fusion Networks and Causal Identity Matching
Hye-Geun Kim, Yong-Hyuk Moon, Yeong-Jun Cho
Object re-identification (ReID) in large camera networks faces numerous challenges. First, the similar appearances of objects degrade ReID performance, a challenge that needs to be…