Contrastive Language-Image Pre-training (CLIP), a simple yet effective pre-training
paradigm, successfully introduces text supervision to vision models. It has shown promising …

Conversation agents fueled by Large Language Models (LLMs) are providing a new way to
interact with visual data. While there have been initial attempts for image-based …

Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks
(DNNs) training, and they usually train a DNN for each single visual recognition task …

Pre-trained vision-language (VL) models such as CLIP have shown excellent generalization
ability to downstream tasks. However, they are sensitive to the choice of input text prompts …

Prompt learning has emerged as an efficient alternative for fine-tuning foundational models,
such as CLIP, for various downstream tasks. Conventionally trained using the task-specific …

Pre-trained vision-language models (VLMs) learn to align vision and language
representations on large-scale datasets, where each image-text pair usually contains a bag …

Open-vocabulary scene understanding aims to localize and recognize unseen categories
beyond the annotated label space. The recent breakthrough of 2D open-vocabulary …

Large-scale multi-modal training with image-text pairs imparts strong generalization to CLIP
model. Since training on a similar scale for videos is infeasible, recent approaches focus on …

Open-vocabulary detection (OVD) is an object detection task aiming at detecting objects
from novel categories beyond the base categories on which the detector is trained. Recent …

Abstract Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-
language tasks, such as image captioning and question answering, but lack the essential …