Introduction

Body gestures are an important form to reveal people’s emotions alongside facial expressions and speeches. For special occasions when people intend to control or hide their true feelings, e.g., for social etiquette or other reasons, body gestures are harder to control and thus the more revealing clues of actual feelings compared to the face and the voice. Microgestures (MG) are defined as a special category of body gestures that are indicative of humans’ emotional status. Representative instances include: scratching head, touching nose, and rubbing hands, which are not intended to be shown when communicating with others, but occur spontaneously due to e.g., felt stress or discomfort as shown in Figure 1. The MGs differ from indicative gestures which are performed on purpose for facilitating communications, e.g., using gestures to assist verbal expressions during a discussion. Although research on general body gestures is prevailing, it is largely about human’s macro body movement, lacking the finer level consideration such as the micro-gestures discussed above. As well the studies are mainly concerned with recognizing the movement performed expressively, and the link between gestures and hidden emotions is yet to be explored.

Fig. 1. Micro-gesture examples. A tennis player is talking while spontaneously performing the body gestures in the post-match interview.

Motivated by the above observations, we propose to jointly hold the third MiGA challenge and workshop on micro-gesture analysis for hidden emotion understanding (MiGA) to fill the gap in the current research field. The MiGA workshop and challenge aim to promote research on developing AI methods for MG analysis toward the goal of hidden emotion understanding. As the proposed MiGA will be the second event, we propose to hold it in workshop + challenge mode with a focus on the competition part that builds and provides benchmark datasets and a fair validation platform for researchers working in the MG classification and online recognition for identity-insensitive emotion understanding. The workshop covers a wider scope than the challenge, i.e., any research that provides theoretical and practical support for gesture and micro-gesture analysis and emotion understanding.

The MiGA Challenge is an ongoing annual event featuring multiple challenge tasks each year, with progressively larger-scale datasets. This year, in addition to the two fundamental micro-gesture analysis tasks—classification and online recognition, we are taking MiGA a step further by introducing a new task: behavior-based emotion understanding. The tracks of MiGA will be extended to leverage those identity-insensitive cues to achieve hidden emotion understanding in the future. The challenge will be based on two spontaneous datasets: One is the SMG dataset, introduced in IJCV2023’s paper “SMG: A Micro-Gesture Dataset Towards Spontaneous Body Gestures for Emotional Stress State Analysis.” and the other is the iMiGUE dataset, published in CVPR2021’s paper “iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis.”. For MiGA 2025, we have introduced three challenge tasks (Tracks), and participating teams are welcome to compete in one or more of them. The challenge will be organized on the Kaggle website.

Track 1: Micro-gesture classification from short video clips. The MG datasets were collected from in-the-wild settings. Compared to ordinary action/gesture data, MGs concern more fine-grained and subtle body movements that occur spontaneously in practical interactions. Thus, learning those fine-grained body movement patterns, handling imbalanced sample distribution of MGs, and distinguishing the high heterogeneous MG samples of interclass are the big challenges to be addressed.

Track 2: Multimodality-based online micro-gesture recognition from long video sequences. Unlike any existing online action/gesture recognition datasets in which samples are well aligned/performed in the sequence, MGs samples occur spontaneously in any combination or order, just like seen in daily communicative scenarios. Thus, the task of online micro-gesture recognition requires dealing with more complex body-movement transition patterns (e.g., co- occurrence of multiple MGs, incomplete MGs and complicated transitions between MGs, etc.) and detecting fine-grained MGs from irrelevant/context body movements, which poses new challenges that haven’t been considered in previous gesture research.

Track 3: Multimodality behavior-based emotion recognition from long video sequences. In this track, participants will try to predict whether a tennis player won or lost the match based on their body behaviors from the video recordings of the public interview press. Unlike any existing body behavior-based emotion recognition datasets in which emotions or behaviors are acted or performed intentionally, our task is about recognizing subjects’ hidden emotions based on body behaviors directly from in-the-wild interview press. Thus, the task of behavior-based emotion recognition requires dealing with more complex challenges, e.g., modeling reliable emotion-behavior probabilistic with suitable algorithms, mining fine-grained MGs from irrelevant/context body movements to achieve reliable emotion analysis, which hasn’t been considered in previous gesture research.

The rules and guidelines for the competition/challenge

1. Datasets

Datasets for the proposed challenge are available. The MiGA challenge is planned as a continuous annual event. Two benchmark datasets published on IJCV 2023 and CVPR 2021 are available and will be used for the challenge. The first one is the SMG dataset published in IJCV2023 Spontaneous Micro-Gesture (SMG) dataset consists of 3,692 samples of 17 MGs. The MG clips are annotated from 40 long video sequences (10-15 minutes) with 821,056 frames in total. The datasets were collected from 40 subjects while narrating a fake and real story to elicit the emotional states. The participants are recorded collected by Kinect resulting in four modalities, RGB, 3D skeletal joints, depth and silhouette. In this workshop, we allow participants to use the skeleton, RGB or both modalities. Details about SMG dataset

The second dataset is iMiGUE published in CVPR2021. Micro-Gesture Understanding and Emotion analysis (iMiGUE) dataset consists of 32 MGs plus one non-MG class collected from post-match press conferences videos of famous tennis players. The dataset consists of 18,499 samples of MGs to detect negative and positive emotions. The MG clips are annotated from 359 long video sequences (0.5-26 minutes) with 3,765,600 frames in total. The dataset contains RGB modality and 2D skeletal joints collected from Open-Pose. In this workshop, we allow participants to use the skeleton, RGB or both modalities. Details about iMiGUE dataset

Note that: 1) not all data are used for the challenge. 2) part of the data will be selected and tailored for different challenge tasks, please follow the Kaggle competition links to obtain and process the datasets.

2. Evaluation

We deploy a cross-subject evaluation protocol. For MG classification track, 13,936 and 3,692 MG clips from iMiGUE and SMG datasets will be used for training and validating, and the remaining 4,563 MG clips from iMiGUE will be used for testing. For MG online recognition track, 252 and 40 long sequences from iMiGUE and SMG datasets will be used for training and validating, and the remaining 104 long sequences from iMiGUE will be used for testing.

MG classification track: We report Top-1 accuracy on the testing setes on the iMiGUE dataset. Submissions will be ranked based on Top-1 accuracy on the overall split (if Top-1 results are the same, then Top-5 will be used to compare the results).

MG online recognition track: We jointly evaluate the detection and classification performances of algorithms by using the F1 score measurement defined below: F1 =2*Precision*Recall/(Precision+Recall), given a long video sequence that needs to be evaluated, P recision is the fraction of correctly classified MGs among all gestures retrieved in the sequence by algorithms, while Recall (or sensitivity) is the fraction of MGs that have been correctly retrieved over the total amount of annotated MGs.

Behavior-based emotion prediction track: We evaluate the submitted algorithms with a binary classification (win/lose) accuracy. The algorithm needs to predict the correct emotion state (positive/negative) corresponding to the match results (win/lose) of the tennis players based on their body behaviors during the interview press. Submissions will be ranked on the basis of the accuracy on the testing set.

Submission format for three tracks. Participants must submit their predictions in the a single .csv file on the Kaggle platform, more detailed instuctions for each track can be found on Kaggle. The results will be evaluated on the server and displayed on the ranking list in real-time. The organization team has the right to examine the participants source code to ensure the reproducibility of the algorithms. The final results and ranking will be confirmed and announced by organizers.

Participation guidelines

Please visit the Kaggle websites to join the competitions:

The 3rd MiGA-IJCAI Challenge Track 1: Micro-gesture Classification

The 3rd MiGA-IJCAI Challenge Track 2: Micro-gesture Online Recognition

The 3rd MiGA-IJCAI Challenge Track 3: Behavior-based Emotion Prediction

Final results will be announced

The rankings for the MiGA 2025 challenge will be published after the competition concludes. Once all submissions have been thoroughly reviewed, the final standings will be determined and announced. Stay tuned for updates!

Important Dates (might slightly adjust later)

The timeline for the competition will be organized as follows:
• Mar. 30th, 2025. Call for Challenge online. (or earlier, based on the notification date)
• Apr. 05, 2025. Release of training data.
• May. 11, 2025. Release of testing data.
• May. 16, 2025. Final test submission deadline.
• May. 19, 2025. Release of challenge results.
• May. 24, 2025. Paper submission deadline.
• May. 31, 2025. Notification to authors.
• Jun. 07, 2025. Camera-ready deadline.