Related papers: CLIP-Guided Unsupervised Semantic-Aware Exposure C…

Contrastive vision-language models like CLIP have shown great progress in transfer learning. In the inference stage, the proper text description, also known as prompt, needs to be carefully designed to correctly classify the given images.…

CLIP achieves strong zero-shot image-text retrieval by aligning global vision and text representations, yet it falls behind on fine-grained tasks even when fine-tuned on long, detailed captions. In this work, we propose $\beta$-CLIP, a…

The well-aligned attribute of CLIP-based models enables its effective application like CLIPscore as a widely adopted image quality assessment metric. However, such a CLIP-based metric is vulnerable for its delicate multimodal alignment. In…

Low-light conditions have an adverse impact on machine cognition, limiting the performance of computer vision systems in real life. Since low-light data is limited and difficult to annotate, we focus on image processing to enhance low-light…

Text-guided image editing has recently experienced rapid development. However, simultaneously performing multiple editing actions on a single image, such as background replacement and specific subject attribute changes, while maintaining…

Driven by large-scale contrastive vision-language pre-trained models such as CLIP, recent advancements in the image-text matching task have achieved remarkable success in representation learning. Due to image-level visual-language…

Text-guided image editing finds applications in various creative and practical fields. While recent studies in image generation have advanced the field, they often struggle with the dual challenges of coherent image transformation and…

Person image generation aims to perform non-rigid deformation on source images, which generally requires unaligned data pairs for training. Recently, self-supervised methods express great prospects in this task by merging the disentangled…

Modern Web systems such as social media and e-commerce contain rich contents expressed in images and text. Leveraging information from multi-modalities can improve the performance of machine learning tasks such as classification and…

In text-video retrieval, recent works have benefited from the powerful learning capabilities of pre-trained text-image foundation models (e.g., CLIP) by adapting them to the video domain. A critical problem for them is how to effectively…

Significant progress has been achieved on the improvement and downstream usages of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention is paid to the interpretation of CLIP. We propose a…

Large-scale pre-trained vision-language models like CLIP demonstrate remarkable zero-shot performance across diverse tasks. However, fine-tuning these models to improve downstream performance often degrades robustness against distribution…

Vision-language models like CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions because of their training focus on short and concise captions. We present…

Vision-language models (VLMs) like CLIP excel in zero-shot learning by aligning image and text representations through contrastive pretraining. Existing approaches to unsupervised adaptation (UA) for fine-grained classification with VLMs…

The use of denoising diffusion models is becoming increasingly popular in the field of image editing. However, current approaches often rely on either image-guided methods, which provide a visual reference but lack control over semantic…

During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks. Nevertheless, acquiring high-quality image-text pairs, where the pairs are entirely exclusive of each other, remains a…

Open-Set Domain Adaptation (OSDA) confronts the dual challenge of aligning known-class distributions across domains while identifying target-domain-specific unknown categories. Current approaches often fail to leverage semantic…

As generative image editing advances, image manipulation localization (IML) must handle both traditional manipulations with conspicuous forensic artifacts and diffusion-generated edits that appear locally realistic. Existing methods…

Leveraging synthetically rendered data offers great potential to improve monocular depth estimation and other geometric estimation tasks, but closing the synthetic-real domain gap is a non-trivial and important task. While much recent work…

Recently, zero-shot multi-label classification has garnered considerable attention for its capacity to operate predictions on unseen labels without human annotations. Nevertheless, prevailing approaches often use seen classes as imperfect…