14 datasets found

A dataset for automatic comment generation from source code.

A dataset for automatic comment generation from source code.

The VirusTotal dataset is a collection of malware samples and their corresponding labels.

A dataset of audio-driven talking head videos generated by four generative methods

The dataset used in the paper is a molecule graph dataset, which is used for molecule property prediction and generation tasks.

A comprehensive benchmark for multi-subject driven text-to-video generation, covering a wide range of subject categories and diverse subject pairs.

Editable dance generation from music.

Bailando: 3D dance generation via actor-critic GPT with choreographic memory.

The dataset used in the paper for text-to-3D generation, consisting of 5,000 different prompts and 800,000 generated images.

Visual to sound: Generating natural sound for videos in the wild.

Deep cross-modal audio-visual generation.

The dataset used in the paper for 3D head avatar reconstruction from monocular RGB videos.

AIST++ is a large-scale dance motion dataset built from [31]. It contains 1409 sequences of dance motions, covering 10 different dance genres with hundreds of choreographies.

The MEAD dataset is a large-scale, high-quality emotional audio-visual dataset, which consists of 60 actors, including 8 basic emotions and 3 different emotional-intensity...