Vision systems that see and reason about the compositional nature of visual scenes are
fundamental to understanding our world. The complex relations between objects and their …

Vision-language datasets are vital for both text-to-image (T2I) and image-to-text (I2T)
research. However, current datasets lack descriptions with fine-grained detail that would …

Segment anything model (SAM) developed by Meta AI Research has recently attracted
significant attention. Trained on a large segmentation dataset of over 1 billion masks, SAM is …

The rise of large language models (LLMs) and instruction tuning has led to the current trend
of instruction-tuned large language and vision models (LLVMs). This trend involves either …

Zero-shot referring expression comprehension aims at localizing bounding boxes in an
image corresponding to provided textual prompts which requires:(i) a fine-grained …

Multi-modal large language models (MLLMs), such as GPT-4, exhibit great comprehension
capabilities on human instruction, as well as zero-shot ability on new downstream multi …

Pre-trained vision-language models (VLMs) have achieved high performance on various
downstream tasks which have been widely used for visual grounding tasks in a weakly …

Abstract Recent advancements in Vision-Language Models (VLMs) have marked a
significant leap in bridging the gap between computer vision and natural language …

Abstract Contrastive Language-Image Pretraining (CLIP) models maximize the mutual
information between text and visual modalities to learn representations. This makes the …

Vision-language models (VLMs) are impactful in part because they can be applied to a
variety of visual understanding tasks in a zero-shot fashion, without any fine-tuning. We …