相关论文: SigLIP 2: Multilingual Vision-Language Encoders wi…

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still…

Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating long-form and context-rich descriptions. State-of-the-art evaluation metrics involve…

Medical vision-and-language pre-training (Med-VLP) has received considerable attention owing to its applicability to extracting generic vision-and-language representations from medical images and texts. Most existing methods mainly contain…

Vision-language pretraining has advanced image-text alignment, yet progress in radiology remains constrained by the heterogeneity of clinical reports, including abbreviations, impression-only notes, and stylistic variability. Unlike…

Multi-modal Large Language Models (MLLMs) have made significant strides in expanding the capabilities of Large Language Models (LLMs) through the incorporation of visual perception interfaces. Despite the emergence of exciting applications…

Recent advances in vision-language models (VLMs) trained on web-scale image-text pairs have enabled impressive zero-shot transfer across a diverse range of visual tasks. However, comprehensive and independent evaluation beyond standard…

Pre-trained vision-language models (VLMs), such as CLIP, have exhibited remarkable performance across various downstream tasks by aligning text and images in a unified embedding space. However, due to the imbalanced distribution of…

Beginning with VisualGLM and CogVLM, we are continuously exploring VLMs in pursuit of enhanced vision-language fusion, efficient higher-resolution architecture, and broader modalities and applications. Here we propose the CogVLM2 family, a…

The fusion of vision and language has brought about a transformative shift in computer vision through the emergence of Vision-Language Models (VLMs). However, the resource-intensive nature of existing VLMs poses a significant challenge. We…

Currently, vision encoder models like Vision Transformers (ViTs) typically excel at image recognition tasks but cannot simultaneously support text recognition like human visual recognition. To address this limitation, we propose UNIT, a…

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 leverage CLIP for cross-modal retrieval to condition…

Treating texts as images, combining prompts with textual labels for prompt tuning, and leveraging the alignment properties of CLIP have been successfully applied in zero-shot multi-label image recognition. Nonetheless, relying solely on…

Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP, establish the correlation between texts and images, achieving remarkable success on various downstream tasks with fine-tuning. In existing fine-tuning methods, the…

Previous works show that noisy, web-crawled image-text pairs may limit vision-language pretraining like CLIP and propose learning with synthetic captions as a promising alternative. Our work continues this effort, introducing two simple yet…

Perception is a fundamental task in the field of computer vision, encompassing a diverse set of subtasks that can be systematically categorized into four distinct groups based on two dimensions: prediction type and instruction type.…

Advances in self-supervised encoders have improved Visual Speech Recognition (VSR). Recent approaches integrating these encoders with LLM decoders improves transcription accuracy; however, it remains unclear whether these gains stem from…

The recent large-scale vision-language pre-training (VLP) of dual-stream architectures (e.g., CLIP) with a tremendous amount of image-text pair data, has shown its superiority on various multimodal alignment tasks. Despite its success, the…

Recent 3D CT vision-language models align volumes with reports via contrastive pretraining, but typically rely on limited public data and provide only coarse global supervision. We train a 3D CT vision-language model on 98k report-volume…

We present Distill CLIP (DCLIP), a fine-tuned variant of the CLIP model that enhances multimodal image-text retrieval while preserving the original model's strong zero-shot classification capabilities. CLIP models are typically constrained…

Supervised visual captioning models typically require a large scale of images or videos paired with descriptions in a specific language (i.e., the vision-caption pairs) for training. However, collecting and labeling large-scale datasets is…