Tag: CLIP

A new multimodal AI framework fuses RGB images, segmentation masks, depth maps, and text prompts to estimate robotic gripper pressure ...

Researchers fused the SAM and CLIP vision foundation models into an AI pipeline that segments grapevine powdery mildew pixel by ...

Researchers in India show that training only a 2.4-million-parameter projection module on top of frozen CLIP encoders lifts fashion image-to-text ...

Researchers have unveiled a diffusion-based framework that fuses text, reference images and sketches with sample-adaptive weighting and iterative user feedback, ...

Researchers have introduced HGA-Net, a hypergraph-based adapter that connects related examples within each mini-batch and achieves near-perfect fine-grained recognition with ...

Researchers at Yonsei University have developed a prompt-tuning method that lets the vision-language model CLIP detect and localize industrial defects ...

Researchers in China have developed MSEA, a CLIP-based framework that combines multi-scale convolutions and efficient linear attention to achieve record ...

A new study systematically tests early, late, and hybrid fusion strategies for combining image and text in AI systems that ...

A new comprehensive review analyzes 13 pretrained multimodal AI models from 2020 to 2025, comparing their architectures, datasets, and applications ...

Researchers have developed SRRI, a source-free domain adaptation method that uses CLIP as an external verifier to de-bias pseudo-source domains ...