Research map / Vision-language and multimodal / Cross-modal learning
Active Perceptual Inference: A Corticothalamic-Inspired Dynamic Nested Recurrent Network for Multimodal Sentiment Analysis with Incomplete Data
Yujuan Zhang, Qing Li, Ziyu Li, Xiuxing Li, Zhuo Wang, Mengrui Xu, Xia Wu
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 multi-round recurrence instead of a single iteration (ablation) | DNRNet · MOSI | Acc-7: 34.94 -> 35.36 | Improved |
| add the Local Perception module (ablation) | DNRNet · MOSI | Acc-7: 34.76 -> 35.36 | Improved |
| add the Global Perception module (ablation) | DNRNet · MOSI | Acc-7: 34.57 -> 35.36 | Improved |
| add the Global Perception module (ablation) | DNRNet · SIMS | Corr: 0.350 -> 0.416 | Improved |
| add confidence-aware loss Lca (ablation) | DNRNet · MOSI | Acc-7: 34.05 -> 35.36 | Improved |
| add reconstruction loss Lrec (ablation) | DNRNet · SIMS | Acc-5: 34.11 -> 35.71 | Improved |
| use DNRNet instead of P-RMF | MOSI · MOSI | Acc-2 (neg/pos): 72.81 -> 74.22 | Improved |
| use DNRNet instead of P-RMF | MOSEI · MOSEI | Acc-2 (neg/pos): 78.14 -> 78.28 | No clear effect |
| use DNRNet instead of CENET for 7-class accuracy | MOSEI · MOSEI | Acc-7: 47.18 -> 46.89 | Hurt |
| use DNRNet instead of LNLN | SIMS · SIMS | F1: 79.43 -> 77.50 | Hurt |
Closest papers by meaning
- Learning Sparse Semantic-Cortical Atoms for Multisubject Naturalistic fMRI Encoding (NeurIPS 2026 · similarity 0.86)
- BrainLM: A foundation model for brain activity recordings (ICLR 2024 · similarity 0.84)
- Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems (NeurIPS 2025 · similarity 0.84)
- Sparsing Law: Towards Large Language Models with Greater Activation Sparsity (ICML 2025 · similarity 0.84)
- Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference (NeurIPS 2025 · similarity 0.84)
- BrainVista: Modeling Naturalistic Brain Dynamics as Multimodal Next-Token Prediction (NeurIPS 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.
