Research map / Vision-language and multimodal / Cross-modal learning
Perception Coordination Network: A Framework for Online Multi-Modal Concept Acquisition and Binding
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 |
|---|---|---|---|
| PCN instead of IKR1 | recall system · Closed, V recalls other | recall accuracy (%): 69.10±4.17% -> 83.98±3.02% | Helped |
| PCN instead of IKR1 | recall system · Closed, A recalls other | recall accuracy (%): 63.48±3.52% -> 86.24±3.30% | Helped |
| PCN instead of MMSOM | recall system · Closed, V recalls other | recall accuracy (%): 76.31±4.25% -> 83.98±3.02% | Helped |
| PCN instead of MMSOM | recall system · Closed, A recalls other | recall accuracy (%): 65.41±5.27% -> 86.24±3.30% | Helped |
| PCN instead of GHF-ART | recall system · Closed, V recalls other | recall accuracy (%): 81.92±3.16% -> 83.98±3.02% | Helped |
| PCN instead of GHF-ART | recall system · Closed, G recalls other | recall accuracy (%): 85.11±2.17% -> 90.35±2.74% | Helped |
| PCN instead of MMSOM | recall system · Open-ended, A recalls other | recall accuracy (%): 50.11±3.53% -> 88.07±2.78% | Helped |
| PCN instead of MMSOM | recall system · Open-ended, V recalls other | recall accuracy (%): 63.64±4.04% -> 84.83±3.26% | Helped |
| PCN instead of IKR1 | recall system · Open-ended, A recalls other | recall accuracy (%): 70.57±5.25% -> 88.07±2.78% | Helped |
| PCN instead of GHF-ART | recall system · Open-ended, G recalls other | recall accuracy (%): 86.40±2.01% -> 92.09±2.16% | Helped |
| move from closed to open-ended environment | MMSOM · V recalls other | recall accuracy (%): 76.31±4.25% -> 63.64±4.04% | Hurt |
| move from closed to open-ended environment | MMSOM · A recalls other | recall accuracy (%): 65.41±5.27% -> 50.11±3.53% | Hurt |
Closest papers by meaning
- Concept-RuleNet: Grounded Multi-Agent Neurosymbolic Reasoning in Vision Language Models (AAAI 2026 · similarity 0.80)
- Flexible Context-Driven Sensory Processing in Dynamical Vision Models (NeurIPS 2024 · similarity 0.79)
- Cross-modal Associations in Vision and Language Models: Revisiting the Bouba-Kiki Effect (NeurIPS 2025 · similarity 0.79)
- Sparse components distinguish visual pathways & their alignment to neural networks (ICLR 2025 · similarity 0.79)
- Multi-Modal Latent Variables for Cross-Individual Primary Visual Cortex Modeling and Analysis (AAAI 2025 · similarity 0.79)
- MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding (ICML 2025 · similarity 0.79)
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.