Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Learning Unseen Emotions from Gestures via Semantically-Conditioned Zero-Shot Perception with Adversarial Autoencoders
Abhishek Banerjee, Uttaran Bhattacharya, Aniket Bera
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 |
|---|---|---|---|
| Use SC-AAE instead of CADA-VAE | GZSL emotion recognition · MPI EBEDB seen and unseen emotion classes | harmonic mean: 33.27% -> 58.43% | Improved |
| Use FS-GER instead of STEP | fully supervised emotion recognition · MPI EBEDB seen emotion classes | accuracy: 70.38% -> 77.61% | Improved |
| Set δ to 1.5 while γ is 1 (ablation) | SC-AAE · MPI EBEDB seen and unseen emotion classes | harmonic mean | Improved |
| Vary γ while keeping δ at 1.5 (ablation) | SC-AAE · MPI EBEDB seen and unseen emotion classes | harmonic mean | No clear effect |
| Use latent embedding size d=16 (ablation) | SC-AAE · MPI EBEDB seen and unseen emotion classes | harmonic mean | Improved |
Closest papers by meaning
- Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation (CVPR 2024 · similarity 0.86)
- Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion (CVPR 2024 · similarity 0.85)
- EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning (CVPR 2024 · similarity 0.85)
- $E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset (NeurIPS 2024 · similarity 0.85)
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · similarity 0.84)
- Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach (ICLR 2026 · similarity 0.84)
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.
