Research map / Vision-language and multimodal / Cross-modal learning
Generative Partial Visual-Tactile Fused Object Clustering
Tao Zhang, Yang Cong, Gan Sun, Jiahua Dong, Yuyang Liu, Zhengming Ding
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 conditional cross-modal clustering GANs (ablation) | GPVTF · PHAC-2, LMT, and GelFabric (missing rate 0.1) | clustering performance | Improved |
| add fusion KL-divergence losses (ablation) | GPVTF · PHAC-2, LMT, and GelFabric (missing rate 0.1) | clustering performance | Improved |
| set the visual-tactile fusion weight α to 0.2 on PHAC-2 and GelFabric, and 0.1 on LMT (ablation) | GPVTF · PHAC-2, GelFabric, and LMT | clustering performance | Mixed |
| set β to 1 (ablation) | GPVTF · PHAC-2, GelFabric, and LMT | ACC | Improved |
| set φ₁ and φ₂ to 0.01 (ablation) | GPVTF · PHAC-2, GelFabric, and LMT | clustering performance | Improved |
| use GPVTF instead of VTFC | visual-tactile fused object clustering · PHAC-2, LMT, and GelFabric (missing rate 0.1) | ACC and NMI: PHAC-2: 51.41±0.63 -> 53.30±0.69 ACC; 70.85±0.32 -> 74.47±0.18 NMI. LMT: 43.94±0.16 -> 54.81±1.36 ACC; 51.03±0.22 -> 80. | Improved |
Closest papers by meaning
- Tactile-Augmented Radiance Fields (CVPR 2024 · similarity 0.85)
- PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation (NeurIPS 2026 · similarity 0.85)
- Universal Visuo-Tactile Video Understanding for Embodied Interaction (NeurIPS 2025 · similarity 0.85)
- A Touch, Vision, and Language Dataset for Multimodal Alignment (ICML 2024 · similarity 0.84)
- AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors (ICLR 2025 · similarity 0.83)
- TextToucher: Fine-Grained Text-to-Touch Generation (AAAI 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.
