29 datasets found

The IEMOCAP dataset contains five recording sessions, each with one male speaker and one female speaker.

RECOLA contains audio-visual recordings of spontaneous interactions of 27 French-speaking participants in a remote collaborative task

The E-MASAC dataset is a comprehensive dataset for Emotion Recognition in Conversation (ERC) for code-mixed dialogues, specifically for Hindi-English conversations.

A dataset collected remotely through an interactive smartphone application that was available to the U.S. general population through Google Play and Apple App Store under IRB...

The EmoPain dataset consists of sequential data from multiple modalities and in unconstrained settings where there are bound to be uncertainties (e.g. in form of sensor noise)...

The dataset used for the Emotion Recognition in the Wild Challenge 2017

The SEED dataset contains 15 subjects recorded while watching movie clips designated with a negative/neutral/positive emotion label.

A large-scale city-wise dataset for exploring the relationships among air pollutants and their causal agents over time.

The mug facial expression database is a facial expression dataset containing 882 videos of 52 actors performing 6 different facial expressions.

Emotions recognition using EEG signals: A survey.

EEG-based emotion recognition often requires sufficient labeled training samples to build an effective computational model. Labeling EEG data, on the other hand, is often...

Aff-Wild2 is a large-scale in-the-wild database for affective behavior analysis, containing 564 videos with frame-level annotations for valence-arousal estimation, facial action...

A dataset used for testing the proposed Adaptive DBN model

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.