Signals 4 · free daily AI digest

Investigating Temporal Motion Features for Pose-to-Text Indian Sign Language Translation

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

We investigate the effect of pretrained T5 model scale and explicit motion features on pose-to-text Indian Sign Language Translation (SLT) for the WSLP 2026 Shared Task. Pose sequences are projected into the embedding space of T5 through a lightweight pose encoder, with the complete model fine-tuned to generate English text. The shared task data used for this work consists of a test set with 5,334

Read on arXiv →

#65 most recent of 237 cs.CV papers we have recorded · ↑ newer: SV-Cine: Diagnosis-Conditioned Segmentation of Single Ventricle Physio · ↓ older: Generative Retrieval for Unsupervised Text-Based Person Search
Cite this page: Investigating Temporal Motion Features for Pose-to-Text Indian Sign Language Translation: the #65 most recent of 237 cs.CV papers we have recorded (as of 2026-09-11). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/investigating-temporal-motion-features-for-pose-to-text-indian-sign-language-tra.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions