Research map / Label-efficient and robust learning / Self-supervised and contrastive
Your head is there to move you around: Goal-driven models of the primate dorsal pathway
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 |
|---|---|---|---|
| train 3D ResNet to predict self-motion on AirSim instead of action recognition on Kinetics400 | 3D ResNet · MST (packlab-mst) | normalized R: .224 -> .454 | Helped |
| self-motion objective instead of action recognition | 3D ResNet · V1 (pvc1) | normalized R: .471 -> .364 | Hurt |
| train CPC on AirSim self-motion videos instead of UCF101 (ablation) | CPC network · MST (packlab-mst) | normalized R: .190 -> .292 | Helped |
| train CPC on AirSim instead of UCF101 (ablation) | CPC network · MT (mt2) | normalized R: .241 -> .360 | Helped |
| supervised self-motion objective instead of CPC on AirSim (ablation) | AirSim-trained network · MST (packlab-mst) | normalized R: .292 -> .454 | Helped |
| add motion energy (gabor with motion vs gabor_nomotion) (ablation) | Gabor pyramid · MST (packlab-mst) | normalized R: .248 -> .394 | Helped |
| change input scale to 0.66X or 1.5X (ablation) | DorsalNet layer mapping for V1 · best matching layer | mean layer assignment: 1.0 at 0.66X, 1.1 at 1X, 1.3 at 1.5X | No clear effect |
Closest papers by meaning
- STSBench: A Large-Scale Dataset for Modeling Neuronal Activity in the Dorsal Stream of Primate Visual Cortex (NeurIPS 2025 · similarity 0.90)
- Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception (NeurIPS 2024 · similarity 0.85)
- Sparse components distinguish visual pathways & their alignment to neural networks (ICLR 2025 · similarity 0.85)
- Flexible Context-Driven Sensory Processing in Dynamical Vision Models (NeurIPS 2024 · similarity 0.85)
- NEvo: Neural-Guided Evolutionary Video Synthesis for Dynamic Visual Selectivity (NeurIPS 2026 · similarity 0.85)
- Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations (ICLR 2025 · 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.