About the Challenge
The CUHK-X Multimodal Human Activity Challenge is the first large-scale international competition that excludes RGB data entirely — models learn human dynamics information from depth, infrared, thermal, IMU, mmWave radar, and skeleton modalities. This privacy-preserving design mirrors the deployment reality of healthcare, smart home, and elderly-care systems, where visual privacy must be preserved at every stage of training, validation, and inference.
Hosted by the AIoT Lab at The Chinese University of Hong Kong on Kaggle across two parallel tracks, with finals held alongside UbiComp 2026 in Shanghai. The Small Model Track targets efficient, edge-deployable HAR; the Large Model Track pushes multimodal LLMs on VQA covering action understanding and reasoning. Total prize pool: USD $20,000.
Challenge Format
Two independent parallel tracks, each with its own Kaggle leaderboard, prize pool, and evaluation criteria.
Small Model Track
HAR · LightweightEfficient multimodal Human Activity Recognition
Targeted at resource-constrained edge deployment in smart home and healthcare scenarios — applications such as Alzheimer's monitoring, fall detection, and elderly care, where models must run on low-power devices with limited memory and compute.
Participants build lightweight multimodal models that fuse depth, infrared, and thermal imagery, IMU streams, mmWave radar, and skeleton keypoints to classify 40 daily activities under strict cross-subject evaluation. Traditional architectures (CNN, RNN, Transformer) are encouraged; large pretrained foundation models are not permitted — placing the spotlight on architecture design, sensor fusion, and inference efficiency.
Large Model Track
VQA · HAU & HARnLVLMs on depth & non-RGB modalities
Pushes the frontier of Large Vision-Language Models on non-RGB modalities.
Participants tackle Human Action Understanding (HAU) and Human Action Reasoning (HARn) through privacy-preserving video Visual Question Answering. There is no parameter limit, encouraging exploration of prompt design, modality alignment, and fine-tuning at scale.
Three-Stage Competition · Both Tracks
Kaggle Open Competition
- Submit prediction CSVs to Kaggle
- Public leaderboard for reference; private leaderboard decides ranking
- Certificate awards: Excellence (Top 15%), Distinction (Top 30%), Successful Participation
- Top 15 teams per track advance to Verification & Evaluation
Verification & Evaluation
- Top 15 submit the verification package (code, weights, inference script, README, final submission, signed honor declaration) by Sep 18, 23:59 UTC
- Organizing Committee reproduces each solution from the submitted code, model artifacts, configuration, and setup instructions
- Organizer-run private-data evaluation on organizer-controlled private data (30% of final scoring)
- Top 6 teams per track advance to the Grand Finals
Grand Finals UbiComp 2026
- No on-site private-test inference — the private-data evaluation is completed before the finals
- Finalist presentations: 5 minutes + 5 minutes Q&A per team, in English
- Awards ceremony + USD $500 travel grant per attending finalist team
- Remote participation via Zoom supported if travel is not possible
Technical Report and Best Report Award. Following the leaderboard freeze, a broader group of top-ranked teams in each track will be formally invited by the Organizing Committee to submit a technical report for consideration for the Best Report Award. Reports from invited teams are due by 23:59 UTC on October 1, 2026 (07:59 UTC+8 on October 2).
All invited teams remain eligible for the Best Report Award whether or not they advance to the Grand Finals. Award recipients who do not advance will be notified by email and receive an electronic certificate. For finalist teams, the report also contributes to the 20% Technical Report component of final scoring. Selection for the Best Report Award is conducted independently of Grand Finals qualification.