most citedNegative Samples are at Large: Leveraging Hard-distance Elastic Loss for Re-identification

1 citations · 1 across the 1 of their papers we have counts for

collaborators
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2025

UAV4D: Dynamic Neural Rendering of Human-Centric UAV Imagery using Gaussian Splatting

Jaehoon Choi, Dongki Jung, Christopher Maxey +4

Despite significant advancements in dynamic neural rendering, existing methods fail to address the unique challenges posed by UAV-captured scenarios, particularly those involving m…

cs.CV2022★ 1 cited

Negative Samples are at Large: Leveraging Hard-distance Elastic Loss for Re-identification

Hyungtae Lee, Sungmin Eum, Heesung Kwon

We present a Momentum Re-identification (MoReID) framework that can leverage a very large number of negative samples in training for general re-identification task. The design of t…