迈向紧凑的手语翻译：帧率与模型大小的权衡
Towards Compact Sign Language Translation: Frame Rate and Model Size Trade-offs
AI总结：
本文提出一种紧凑的77M参数 pipeline，结合MMPose骨骼姿态提取与单线性投影到T5-small，通过调整输入帧率实现效率权衡，减少计算复杂度且保持翻译质量。
摘要：
手语翻译（SLT）将手语视频转换为口语文本，连接聋人与听障社区。当前无 gloss 方法依赖于大型编码器-解码器模型，限制了部署。我们提出了一种紧凑的77M参数管道，结合MMPose骨骼姿态提取与单线性投影到T5-small。通过调整输入帧率，我们揭示了实际的效率权衡：在12 fps时，模型将序列长度减半，实现编码器二次自注意力计算复杂度降低75%，同时仅导致BLEU-4小幅下降（9.53 vs. 10.06在How2Sign上24 fps时）。我们的系统比先前的T5-base系统小约3倍，证明了轻量级架构可以在没有分层编码器或大规模模型的情况下保持竞争力。
英文摘要：
Sign Language Translation (SLT) converts sign language videos into spoken-language text, bridging communication between Deaf and hearing communities. Current gloss-free approaches rely on large encoder-decoder models, limiting deployment. We propose a compact 77M-parameter pipeline that couples MMPose skeletal pose extraction with a single linear projection into T5-small. By varying the input frame rate, we expose a practical efficiency trade-off: at 12 fps the model halves its sequence length, achieving a 75% reduction in encoder quadratic self-attention computational complexity while incurring only a modest BLEU-4 drop (9.53 vs. 10.06 at 24 fps on How2Sign). Our system is roughly 3x smaller than prior T5-base systems, demonstrating that a lightweight architecture can remain competitive without hierarchical encoders or large-scale models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
