Research map / Video / Video segmentation and tracking
Learning Spatio-Temporal Features With Partial Expression Sequences for On-the-Fly Prediction
Wissam Baddar, Yong Ro
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add estimated expression-intensity supervision (E2) to sequence classification training (E1) (ablation) | LSTM spatio-temporal features · MMI and Oulu-CASIA, partial-sequence prediction | recognition rate | Improved |
| Add perceived-expression feature clustering (E3) to E1+E2 (ablation) | LSTM spatio-temporal features · MMI, 7 expression classes | recognition rate (%): 78.29 -> 78.96 | Improved |
| Add perceived-expression feature clustering (E3) to E1+E2 (ablation) | LSTM spatio-temporal features · Oulu-CASIA, 7 expression classes | recognition rate (%): 82.15 -> 82.86 | Improved |
| Train with E1+E2+E3 rather than the conventional LSTM objective E1 alone (ablation) | LSTM spatio-temporal features · MMI and Oulu-CASIA, partial-sequence prediction | recognition rate | Improved |
| Use the proposed spatio-temporal feature learning method instead of existing methods | MMI, sequence-level prediction · MMI | recognition rate | Improved |
| Use the proposed spatio-temporal feature learning method instead of previous spatio-temporal methods | Oulu-CASIA, sequence-level prediction · Oulu-CASIA | recognition rate | Improved |
Closest papers by meaning
- A Novel Dynamic Model Capturing Spatial and Temporal Patterns for Facial Expression Analysis (TPAMI 2019 · similarity 0.86)
- Mode Variational LSTM Robust to Unseen Modes of Variation: Application to Facial Expression Recognition (AAAI 2019 · similarity 0.85)
- EmWorld: Emotion World Model with Latent State Evolution for Scenario-Incremental Dynamic Facial Expression Recognition (ICML 2026 · similarity 0.85)
- Intensity-Aware Loss for Dynamic Facial Expression Recognition in the Wild (AAAI 2023 · similarity 0.84)
- How Video Meetings Change Your Expression (ECCV 2024 · similarity 0.84)
- Video Language Model Pretraining with Spatio-temporal Masking (CVPR 2025 · similarity 0.83)
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.
