7 datasets found

Tags: image-text retrieval

Filter Results

  • LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Imag...

    Image-text retrieval (ITR) is a task to retrieve the relevant images/texts, given the query from another modality. The conventional dense retrieval paradigm relies on encoding...

  • XmediaNet

    The XmediaNet dataset is a large-scale image-text dataset for cross-modal retrieval.

  • Pascal-Sentence

    The Pascal-Sentence dataset contains image-text pairs for cross-modal retrieval.

  • Conceptual Captions

    The dataset used in the paper "Scaling Laws of Synthetic Images for Model Training". The dataset is used for supervised image classification and zero-shot classification tasks.

  • SBU Captions

    The SBU Captions dataset is a large-scale image-text dataset used for vision-language pre-training.

  • Visual Genome

    The Visual Genome dataset is a large-scale visual question answering dataset, containing 1.5 million images, each with 15-30 annotated entities, attributes, and relationships.

  • MSCOCO

    Human Pose Estimation (HPE) aims to estimate the position of each joint point of the human body in a given image. HPE tasks support a wide range of downstream tasks such as...