AI Paper Atlas

Research map / Video / Video segmentation and tracking

TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation

DONGXU LI, Chenchen Xu, Xin Yu, Kaihao Zhang, Benjamin Swift, Hanna Suominen, Hongdong Li

NeurIPS 2020 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 79 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use multi-scale segment attention instead of the Conv2d-RNN baselineSign language translation on RWTH-PHOENIX-Weather 2014T · RWTH-PHOENIX-Weather 2014T testBLEU-4: 9.58 -> 13.41Improved
Jointly model local and non-local video context rather than applying attentions sequentially (ablation)TSPNet · RWTH-PHOENIX-Weather 2014T testBLEU-4: 12.97 -> 13.41Improved
Add multiple segment scales {8, 12, 16} rather than using one scale (ablation)TSPNet-Joint · RWTH-PHOENIX-Weather 2014T testBLEU-4: 11.61 -> 13.41Improved
Include 16-frame segments in the multi-scale representation (ablation)TSPNet-Joint · RWTH-PHOENIX-Weather 2014T testBLEU-4: 10.40 -> 13.41Improved
Add 24-frame segments to the multi-scale representation (ablation)TSPNet-Joint · RWTH-PHOENIX-Weather 2014T testBLEU-4Hurt
Replace hierarchical segment aggregation with position-wise pooling (ablation)TSPNet-Joint · RWTH-PHOENIX-Weather 2014T testBLEU-4: 13.41 -> 11.13Hurt
Replace hierarchical segment aggregation with position-wise fully connected aggregation (ablation)TSPNet-Joint · RWTH-PHOENIX-Weather 2014T testBLEU-4: 13.41 -> 11.80Hurt
Allow unrestricted attention across segments instead of restricting attention to semantically relevant neighborhoods (ablation)TSPNet-Joint · RWTH-PHOENIX-Weather 2014T testBLEU-4: 13.41 -> 9.35Hurt
Fine-tune I3D on WSLR datasets (ablation)TSPNet-Joint · RWTH-PHOENIX-Weather 2014T testBLEU-4: 11.23 -> 13.41Improved
Share positional-embedding weights across scales instead of learning separate layers (ablation)TSPNet-Joint · RWTH-PHOENIX-Weather 2014T testBLEU-4: +0.08 BLEU-4Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy