Research map / Video / Video segmentation and tracking
Self-Emphasizing Network for Continuous Sign Language Recognition
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add SSEM and TSEM | ResNet18-based CSLR · PHOENIX14 Test | WER: 22.3 -> 21.0 | Mixed |
| Add SSEM and TSEM | ResNet18-based CSLR · PHOENIX14-T Test | WER: 22.8 -> 20.7 | Mixed |
| Add SSEM and TSEM | ResNet18-based CSLR · CSL-Daily Test | WER: 32.3 -> 30.7 | Helped |
| Add SSEM and TSEM | ResNet18-based CSLR · CSL Test | WER: 3.5 -> 0.8 | Helped |
| Use three spatial branches instead of no SSEM (ablation) | SSEM on ResNet18 · PHOENIX14 Test | WER: 22.3 -> 21.4 | Helped |
| Increase spatial branches from N=1 to N=2 and N=3 (ablation) | SSEM on ResNet18 · PHOENIX14 Test | WER: 22.0 -> 21.8 -> 21.4 | Helped |
| Increase spatial branches from N=3 to N=4 (ablation) | SSEM on ResNet18 · PHOENIX14 Test | WER: 21.4 -> 21.7 | Hurt |
| Use temporal kernel K_t=7 or K_t=11 instead of K_t=9 (ablation) | SSEM on ResNet18 · PHOENIX14 Test | WER: 21.4 -> 21.6; 21.4 -> 21.8 | Hurt |
| Replace the multi-scale branches with a larger spatial kernel (ablation) | SSEM on ResNet18 · PHOENIX14 Test | WER: 21.4 -> 22.0 | Hurt |
| Apply attention maps directly without centering or a residual connection (ablation) | SSEM on ResNet18 · PHOENIX14 Test | WER: 22.3 -> 23.4 | Hurt |
| Use centered attention maps and a residual connection (ablation) | SSEM on ResNet18 · PHOENIX14 Test | WER: 22.3 -> 21.4 | Helped |
| Add adjacent-frame difference features to appearance features (ablation) | TSEM with SSEM · PHOENIX14 Test | WER: 21.2 -> 21.0 | Helped |
Closest papers by meaning
- TCNet: Continuous Sign Language Recognition from Trajectories and Correlated Regions (AAAI 2024 · similarity 0.91)
- SignGraph: A Sign Sequence is Worth Graphs of Nodes (CVPR 2024 · similarity 0.88)
- VSNet: Focusing on the Linguistic Characteristics of Sign Language (CVPR 2025 · similarity 0.88)
- Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment (NeurIPS 2026 · similarity 0.86)
- A Wireframe-Based Approach for Classifying and Acquiring Proficiency in the American Sign Language (Student Abstract) (AAAI 2024 · similarity 0.86)
- KD-MSLRT: Lightweight Sign Language Recognition Model Based on Mediapipe and 3D to 1D Knowledge Distillation (AAAI 2025 · similarity 0.86)
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.