paper-with-me

Papers

REACT 2024: the Second Multiple Appropriate Facial Reaction Generation Challenge

2024-01-10 · Siyang Song, Micol Spitale, Cheng Luo, Cristina Palmero, German Barquero, Hengde Zhu, Sergio Escalera, Michel Valstar, Tobias Baur, Fabien Ringeval, Elisabeth Andre, Hatice Gunes

In dyadic interactions, humans communicate their intentions and state of mind using verbal and non-verbal cues, where multiple different facial reactions might be appropriate in response to a specific speaker behaviour. Then, how to develop a machine learning (ML) model that can automatically generate multiple appropriate, diverse, realistic and synchronised human facial reactions from an previously unseen speaker behaviour is a challenging task. Following the successful organisation of the first REACT challenge (REACT 2023), this edition of the challenge (REACT 2024) employs a subset used by the previous challenge, which contains segmented 30-secs dyadic interaction clips originally recorded as part of the NOXI and RECOLA datasets, encouraging participants to develop and benchmark Machine Learning (ML) models that can generate multiple appropriate facial reactions (including facial image sequences and their attributes) given an input conversational partner's stimulus under various dyadic video conference scenarios. This paper presents: (i) the guidelines of the REACT 2024 challenge; (ii) the dataset utilized in the challenge; and (iii) the performance of the baseline systems on the two proposed sub-challenges: Offline Multiple Appropriate Facial Reaction Generation and Online Multiple Appropriate Facial Reaction Generation, respectively. The challenge baseline code is publicly available at https://github.com/reactmultimodalchallenge/baseline_react2024.

📄 PDF Abstract BibTeX arXiv:2401.05166

Code (2)

reactmultimodalchallenge/baseline_react2024 공식 구현 pytorch
lingjivoo/reactface pytorch

Similar Papers 제목 키워드 기반

Reversible Graph Neural Network-based Reaction Distribution Learning for Multiple Appropriate Facial Reactions Generation

2023-05-24 · Tong Xu, Micol Spitale, Hao Tang, Lu Liu 외

Generating facial reactions in a human-human dyadic interaction is complex and highly dependent on the context since more than one facial reactions can be appropriate for the speaker's behaviour. This has challenged exis…

Graph Neural Network

ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactions

2023-05-25 · Cheng Luo, Siyang Song, Weicheng Xie, Micol Spitale 외

In dyadic interaction, predicting the listener's facial reactions is challenging as different reactions could be appropriate in response to the same speaker's behaviour. Previous approaches predominantly treated this tas…

REACT2023: the first Multi-modal Multiple Appropriate Facial Reaction Generation Challenge

2023-06-11 · Siyang Song, Micol Spitale, Cheng Luo, German Barquero 외

The Multi-modal Multiple Appropriate Facial Reaction Generation Challenge (REACT2023) is the first competition event focused on evaluating multimedia processing and machine learning techniques for generating human-approp…

Multiple Appropriate Facial Reaction Generation in Dyadic Interaction Settings: What, Why and How?

2023-02-13 · Siyang Song, Micol Spitale, Yiming Luo, Batuhan Bal 외

According to the Stimulus Organism Response (SOR) theory, all human behavioral reactions are stimulated by context, where people will process the received stimulus and produce an appropriate reaction. This implies that i…

ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model

2025-10-06 · Luo Cheng, Song Siyang, Yan Siyuan, Yu Zhen 외 arxiv

The automatic generation of diverse and human-like facial reactions in dyadic dialogue remains a critical challenge for human-computer interaction systems. Existing methods fail to model the stochasticity and dynamics in…