Multimodal Cross-Attention for Range of Motion Assessment
Bibliographic record
Abstract
Assessing joint motion through multimodal sensing remains challenging when visual cues are unreliable or incomplete. Manual goniometry, though standard in clinical settings, is inherently subjective and time-consuming, while purely vision-based approaches struggle with occlusions, illumination changes, and limited sensitivity to subtle joint displacements. To overcome these challenges, we introduce a multimodal cross-attention framework that integrates RGB-based motion estimation with electromyography (EMG) signals capturing neuromuscular activation. The proposed design employs an Hourglass CNN for spatial feature extraction and a GRU encoder for temporal EMG modeling. Each modality is first calibrated through intra-modal feature refinement and then fused via a pre-normalized residual cross-attention module, enabling stable, bidirectional interaction between vision and muscle activity. This fusion allows the network to dynamically adapt when visual information is degraded and to align spatial and physiological cues for more consistent joint-angle prediction. Experiments demonstrate that the cross-attention model achieves superior accuracy (RMSE 2.51) and exhibits significantly improved robustness under visual occlusion compared to concatenation-based fusion.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".