Existing vision-text contrastive learning like CLIP aims to match the paired image and
caption embeddings while pushing others apart, which improves representation …

This paper presents contrastive-tuning, a simple method employing contrastive training to
align image and text models while still taking advantage of their pre-training. In our empirical …

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 …

Image-text matching, as a fundamental task, bridges the gap between vision and language.
The key of this task is to accurately measure similarity between these two modalities. Prior …

Contrastive learning-based video-language representation learning approaches, eg, CLIP,
have achieved outstanding performance, which pursue semantic interaction upon pre …

Recent developments in multimodal training methodologies, including CLIP and ALIGN,
obviate the necessity for individual data labeling. These approaches utilize pairs of data and …

Large-scale single-stream pre-training has shown dramatic performance in image-text
retrieval. Regrettably, it faces low inference efficiency due to heavy attention layers …

Current state-of-the-art image-text matching methods implicitly align the visual-semantic
fragments, like regions in images and words in sentences, and adopt cross-attention …

Most video-and-language representation learning approaches employ contrastive learning,
eg, CLIP, to project the video and text features into a common latent space according to the …

Image-text matching, a bridge connecting image and language, is an important task, which
generally learns a holistic cross-modal embedding to achieve a high-quality semantic …