Towards Compact Sign Language Translation: Frame Rate and Model Size Trade-offs
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Sign Language TranslationResults from the Paper
| Rank | Task | Dataset | Model | Metrics |
|---|---|---|---|---|
| #1 | Sign Language Translation | How2Sign | Towards Compact Sign Language Translatio | BLEU: 10.06 |
Similar Papers 제목 키워드 기반
SCALE: Synergized Collaboration of Asymmetric Language Translation Engines
In this paper, we introduce SCALE, a collaborative framework that connects compact Specialized Translation Models (STMs) and general-purpose Large Language Models (LLMs) as one unified translation engine. By introducing …
Continual LearningTranslationTripletCAT-Translate: Building Compact Open-Source Models for Japanese-English Translation
Nowadays, large multilingual translation models demonstrate impressive translation capabilities in the machine translation benchmarks. This raises a practical question to the developers: is it worth developing translatio…
Machine TranslationA Compact and Language-Sensitive Multilingual Translation Method
Multilingual neural machine translation (Multi-NMT) with one encoder-decoder model has made remarkable progress due to its simple deployment. However, this multilingual translation paradigm does not make full use of lang…
DecoderMachine TranslationNMTTranslationCompact Personalized Models for Neural Machine Translation
We propose and compare methods for gradient-based domain adaptation of self-attentive neural machine translation models. We demonstrate that a large proportion of model parameters can be frozen during adaptation with min…
Domain AdaptationMachine TranslationTranslationMultilingual Neural Machine Translation
The advent of neural machine translation (NMT) has opened up exciting research in building multilingual translation systems i.e. translation models that can handle more than one language pair. Many advances have been mad…
Machine TranslationNMTTransfer LearningTranslation