Learning Sign Language Recognition under Label Noise: A Study of Noise-Robust Losses for Isolated and Continuous Settings

Paper recorded by Signals 4 on 2026-09-11 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-11 on arXiv · recorded by Signals 4 on 2026-09-14

Category: cs.CV · 计算机视觉 · first seen 2026-09-14

Abstract

In sign language recognition, the isolated (ISLR) classification loss treats a single label as ground truth, as does the frame-level auxiliary classifier over pseudo-labels we add to continuous (CSLR) methods, which lack one. Stylistic variation blurs ISLR annotation and the lack of temporal boundaries in CSLR forces pseudo-labels; both are noisy. We therefore apply symmetric and generalized cross

Read on arXiv →