Tag
This paper proposes ODE-based Transformer decoders using Runge-Kutta integration methods to improve iterative refinement for sign language translation, achieving better BLEU scores than the IPSLT baseline without increasing model size.
DualAnchor is a training framework for gloss-free sign language translation that uses token-level prior anchoring to preserve LLM language priors and optimal transport alignment to improve lexical fidelity, achieving strong results on PHOENIX-2014T and CSL-Daily.
VTaMo introduces explicit multi-granularity video-text alignment for sign language translation using optimal transport and contrastive learning, achieving state-of-the-art performance on four benchmarks.
This paper presents a sentence-level sign language translation system fine-tuned with QLoRA on a subset of How2Sign, achieving BLEU 15.9. Its main contribution is a hardware-aware streaming pipeline using a Raspberry Pi 4B client and a CPU/GPU backend, reducing mean latency by 27.71%.