Abstract Multi-modal Large Language Models (MLLMs) tuned on machine-generated
instruction-following data have demonstrated remarkable performance in various multimodal …

In recent research significant attention has been devoted to the open-vocabulary object
detection task aiming to generalize beyond the limited number of classes labeled during …

Computer vision often treats perception as objective, and this assumption gets reflected in
the way that datasets are collected and models are trained. For instance, image descriptions …

Zero-shot image captioning (IC) without well-paired image-text data can be categorized into
two main types: training-free and text-only-training methods. While both types integrate pre …

Despite recent advances in the general visual instruction-following ability of Multimodal
Large Language Models (MLLMs), they still struggle with critical problems when required to …

Image captioning evaluation metrics can be divided into two categories, reference-based
metrics and reference-free metrics. However, reference-based approaches may struggle to …

Image captioning has long been regarded as a fundamental task in visual understanding.
Recently, however, few large vision-language model (LVLM) research discusses model's …

Given a text and its related image, the multimodal relation extraction (MRE) task aims at
predicting the correct semantic relation between two entities in the input text. Though certain …

The development of technology and social media platforms has led to the proliferation of
fake news, including the cheapfakes problem. Cheapfakes can be produced easily and …

Recently, vision-language models like CLIP have advanced the state of the art in a variety of
multi-modal tasks including image captioning and caption evaluation. Many approaches …