ChatPPG.
Join free
First page or project page of “FIRMED: A Peak-Centered Multimodal Dataset with Fine-Grained Annotation for Emotion Recognition (Tang et al., ACM MM 2026)” (opens in a new tab)

Paperdoi:10.1145/3767308.3838644

FIRMED: A Peak-Centered Multimodal Dataset with Fine-Grained Annotation for Emotion Recognition (Tang et al., ACM MM 2026)

Venue listed2026Added Nov 6, 2026

  • HT
  • SX
  • XX
  • CL
  • BL
  • ZT
  • DZ

Authors: Hao Tang, Songyun Xie, Xinzhou Xie, Can Liao, Bohan Li, Zhongyu Tian, Dalu Zheng

ACM Multimedia 2026 (DOI 10.1145/3767308.3838644)

Publisher (opens in a new tab) Cite
First page or project page of “FIRMED: A Peak-Centered Multimodal Dataset with Fine-Grained Annotation for Emotion Recognition (Tang et al., ACM MM 2026)” (opens in a new tab)

Hao Tang et al., "FIRMED: A Peak-Centered Multimodal Dataset with Fine-Grained Annotation for Emotion Recognition", doi:10.1145/3767308.3838644, CC BY-NC-ND 4.0

TL;DR

Peak-centered multimodal emotion dataset (n=35) with synchronized EEG, ECG, GSR, PPG, and face video under an immediate-recall annotation paradigm (event-centered timestamps + intensity). Claims +3.8 pp average gain vs whole-trial labels across eight EEG classifiers; further gains with multimodal fusion (OpenAlex abstract).

  • Form factor: lab multimodal (video-induced)

Abstract

Traditional video-induced physiological datasets usually rely on whole-trial labels, which introduce temporal label noise in dynamic emotion recognition. We present FIRMED, a peak-centered multimodal dataset based on an immediate-recall annotation paradigm, with synchronized EEG, ECG, GSR, PPG, and facial recordings from 35 participants. FIRMED provides event-centered timestamps, emotion labels, and intensity annotations, and its annotation quality is supported by subjective and physiological validation. Benchmark experiments show that FIRMED consistently outperforms whole-trial labeling, yielding an average gain of 3.8 percentage points across eight EEG-based classifiers, with further improvements under multimodal fusion. FIRMED provides a practical benchmark for temporally localized supervision in multimodal affective computing.

Verbatim from Semantic Scholar (opens in a new tab) · Abstract via Semantic Scholar; © the authors/publisher

Results on ChatPPG leaderboards

All leaderboards

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

Tasks & signals

Tasks

Stress

Signals

PPGECGEDAEEG

Keywords

AffectEmotionACM MMT AFFECT

How it works

How Method works: Setup → Method → TargetSetup: Signals (eeg, ecg, eda, ppg); Form factor (lab multimodal (video-induced)). Method: Method. Target: Stress.SetupSignals: eeg, ecg, eda, ppgSignalseeg, ecg, eda, ppgForm factor: lab multimodal (video-induced)Form factorlab multimodal (video-induced)MethodMethodTargetStressStress

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Tang, H., Xie, S., Xie, X., Liao, C., Li, B., Tian, Z., & Zheng, D. (2026). FIRMED: A Peak-Centered Multimodal Dataset with Fine-Grained Annotation for Emotion Recognition (Tang et al., ACM MM 2026). ACM Multimedia 2026. https://doi.org/10.1145/3767308.3838644
Tang, Hao, Songyun Xie, Xinzhou Xie, Can Liao, Bohan Li, Zhongyu Tian, and Dalu Zheng. 2026. "FIRMED: A Peak-Centered Multimodal Dataset with Fine-Grained Annotation for Emotion Recognition (Tang et al., ACM MM 2026)." ACM Multimedia 2026. https://doi.org/10.1145/3767308.3838644.
Tang, H., Xie, S., Xie, X., Liao, C., Li, B., Tian, Z. and Zheng, D. (2026) 'FIRMED: A Peak-Centered Multimodal Dataset with Fine-Grained Annotation for Emotion Recognition (Tang et al., ACM MM 2026)', ACM Multimedia 2026. doi: 10.1145/3767308.3838644.
Tang, Hao, et al. "FIRMED: A Peak-Centered Multimodal Dataset with Fine-Grained Annotation for Emotion Recognition (Tang et al., ACM MM 2026)." ACM Multimedia 2026, 2026. https://doi.org/10.1145/3767308.3838644.
H. Tang et al., "FIRMED: A Peak-Centered Multimodal Dataset with Fine-Grained Annotation for Emotion Recognition (Tang et al., ACM MM 2026)," ACM Multimedia 2026, 2026, doi: 10.1145/3767308.3838644.
@article{tang2026firmed,
  title         = {{FIRMED: A Peak-Centered Multimodal Dataset with Fine-Grained Annotation for Emotion Recognition (Tang et al., ACM MM 2026)}},
  author        = {Tang, Hao and Xie, Songyun and Xie, Xinzhou and Liao, Can and Li, Bohan and Tian, Zhongyu and Zheng, Dalu},
  year          = {2026},
  journal       = {ACM Multimedia 2026},
  doi           = {10.1145/3767308.3838644}
}

Added to the ChatPPG research hub

Same tasks, data and authors

Papers

Datasets