TMT: Adapting CLIP to Infrared Imagery via Text-Derived Modality Knowledge Transfer
cs.CV
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/wanginsten/TMT
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Kimi K2.5: Visual Agentic Intelligence
- un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP
- Efficient Estimation of Word Representations in Vector Space
- T-CLIP: Enabling Thermal Perception for Contrastive Language-Image Pretraining
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understanding
- Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs