相关论文: SpeechCLIP: Integrating Speech with Pre-Trained Vi…

There is growing interest in models that can learn from unlabelled speech paired with visual context. This setting is relevant for low-resource speech processing, robotics, and human language acquisition research. Here we study how a…

Contrastive Language-Image Pre-training (CLIP) has become the standard for cross-modal image-text representation learning. Improving CLIP typically requires additional data and retraining with new loss functions, but these demands raise…

Contrastive language-image pre-training (CLIP) serves as a de-facto standard to align images and texts. Nonetheless, the loose correlation between images and texts of web-crawled data renders the contrastive objective data inefficient and…

Transductive zero-shot learning with vision-language models leverages image-image similarities within the dataset to achieve better classification accuracy compared to the inductive setting. However, there is little work that explores the…

Despite the recent success of image-text contrastive models like CLIP and SigLIP, these models often struggle with vision-centric tasks that demand high-fidelity image understanding, such as counting, depth estimation, and fine-grained…

We present Fast Language-Image Pre-training (FLIP), a simple and more efficient method for training CLIP. Our method randomly masks out and removes a large portion of image patches during training. Masking allows us to learn from more…

Contrastive Language-Image Pre-training (CLIP) has drawn increasing attention recently for its transferable visual representation learning. However, due to the semantic gap within datasets, CLIP's pre-trained image-text alignment becomes…

Vision-language models like CLIP show impressive ability to align images and text, but their training on short, concise captions makes them struggle with lengthy, detailed descriptions. Recent advances mitigate this challenge by leveraging…

Contrastive pretraining of image-text foundation models, such as CLIP, demonstrated excellent zero-shot performance and improved robustness on a wide range of downstream tasks. However, these models utilize large transformer-based encoders…

Supervised or weakly supervised methods for phrase localization (textual grounding) either rely on human annotations or some other supervised models, e.g., object detectors. Obtaining these annotations is labor-intensive and may be…

Human-centric visual analysis plays a pivotal role in diverse applications, including surveillance, healthcare, and human-computer interaction. With the emergence of large-scale unlabeled human image datasets, there is an increasing need…

While Contrastive Language-Image Pre-training (CLIP) has advanced open-vocabulary predictions, its performance on semantic segmentation remains suboptimal. This shortfall primarily stems from its spatial-invariant semantic features and…

CLIP is a seminal multimodal model that maps images and text into a shared representation space through contrastive learning on billions of image-caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate…

Due to the lack of paired samples and the low signal-to-noise ratio of functional MRI (fMRI) signals, reconstructing perceived natural images or decoding their semantic contents from fMRI data are challenging tasks. In this work, we…

We describe a protocol to study text-to-video retrieval training with unlabeled videos, where we assume (i) no access to labels for any videos, i.e., no access to the set of ground-truth captions, but (ii) access to labeled images in the…

Zero-shot action recognition relies on transferring knowledge from vision-language models to unseen actions using semantic descriptions. While recent methods focus on temporal modeling or architectural adaptations to handle video data, we…

Vision-language (V+L) pretraining models have achieved great success in supporting multimedia applications by understanding the alignments between images and text. While existing vision-language pretraining models primarily focus on…

Vision-language pretraining on large datasets of images-text pairs is one of the main building blocks of current Vision-Language Models. While with additional training, these models excel in various downstream tasks, including visual…

CLIP models learn transferable multi-modal features via image-text contrastive learning on internet-scale data. They are widely used in zero-shot classification, multi-modal retrieval, text-to-image diffusion, and as image encoders in large…

Existing semantic segmentation approaches are often limited by costly pixel-wise annotations and predefined classes. In this work, we present CLIP-S$^4$ that leverages self-supervised pixel representation learning and vision-language models…