GitHub

ObjEmbed: Towards Universal Multimodal Object Embeddings

Aligning objects with corresponding textual descriptions is a fundamental challenge and a realistic requirement in vision-language understanding. While recent multimodal embedding models excel at ...
IEEE

RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-Training

Abstract: Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. MLLMs ...
GitHub

Otary — elegant, readable, and powerful image and 2D geometry Python library.

Unification: Otary offers a cohesive solution for image and geometry manipulation, letting you work seamlessly without switching tools. Readability: Self-explanatory by design. Otary’s clean, readable ...
IEEE

Retrieval-augmented Pseudo-image Guided Alignment and Text Domain-aware Memory Recall for Continual Zero-shot Captioning

Abstract: Zero-shot captioning aims to describe visual content without additional paired image-text data by leveraging the potential of Visual Language Models (VLMs). Although text-only training ...