40 datasets found

The OMG Emotion Behavior Dataset is a multimodal emotion recognition dataset, consisting of 178 long videos divided into 2725 short utterances of varying length.

The dataset consists of published datasets from available sources containing labelled sentences of natural language (English) with eight emotions.

The dataset consists of published datasets from available sources containing labelled sentences of natural language (English) with eight emotions.

The proposed model predicts the agent's emotion against each interaction with a human or against events to make it more cognitive and socially believable.

RAVDESS (Ryerson Audio-Visual Database of Emotional Speech and Song) dataset contains 24 professional actors (12 female, 12 male) to offer the performance with good quality and...

The EMODB dataset is a German language speech library containing about 535 audio clips, each ranging from 1 to 10 seconds long, covering seven different emotional expressions.

The EmotiW dataset contains videos of 78 students in online classroom setting.

The SAVEE dataset contains 480 acted English utterances recorded by four male actors and consists of seven emotion categories: anger, fear, disgust, happiness, neutral, sadness,...

The Aff-Wild dataset is a large-scale in-the-wild dataset for affect recognition, containing actual videos with a wide range of content.

A multi-task learning framework for emotion recognition and facial image generation

Label distribution learning on auxiliary label space graphs for facial expression recognition.

The dataset consists of a significant collection of 60,000 facial expression images, categorized into eight different classes, including neutral, happy, angry, sad, fear,...

The DISFA dataset is a publicly available spontaneous facial expression dataset which contains 27 subjects (12 females, and 15 males) aged in between [18, 50] and ethnically 3...

EMOCAUSE is an evaluation set for emotion cause word recognition, annotated with emotion cause words on situations in EmpatheticDialogues.

The EmpatheticDialogues dataset is a text dataset for training empathetic AI chatbots, consisting of 25k conversations grounded in emotional situations with emotion labels.

The CREMA-D dataset is an audio-visual dataset for emotion recognition task, each video in which consists of both facial and acoustic emotional expressions.

Karolinska Directed Emotional Faces (KDEF) dataset

Speaker verification systems experience significant performance degradation when tasked with short-duration trial recordings. To address this challenge, a multi-scale feature...

The SEED and SEED-IV databases are used for emotion recognition experiments.

The dataset used for emotion recognition, featuring facial expression images.