- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper addresses the unordered problem in the VQ method, which is widely used in the T2M field. It utilized a part-aware methodology and conducted MotionMilltion benchmarks and evaluations alongside HumanML3D and KIT-ML, which are commonly used in this field.
Critical strengths
- The problem is intuitive.
- It is intuitively reasonable to think that using the commonly used cross-entropy when training with VQ is a problem, as it applies the same penalty regardless of whether the motion is close or far.
Critical weaknesses
- Lack of Prior Research
- There is a lack of comparative analysis and comparison with existing part-aware methodologies such as ParCo (ECCV 2024), LGTM (SIGGRAPH 2024), BiPO (WACV 2026), and ParTY (CVPR 2026) when using the Part-aware Tokenizer.
- Experimental Results Fail to Support the Claims
- To my knowledge, FID is the most important metric for comparing the quality of generated motion in this field. R-Precision and MultiModal Dist serve to assist in performance evaluation; high scores on these metrics alone cannot support the claim that a model performs well. In particular, R-Precision and MultiModal Dist perform better than Real Motion, making it impossible to make a rational judgment based solely on these metrics. Furthermore, the fact that MultiModality—which demonstrates diversity—shows the lowest performance among the comparative papers is a significant issue, suggesting that the generative model is not fulfilling its role and may be overfitted.
- Exaggeration of Efficiency Claims
- While the model claims efficiency through comparison with the MotionMillion-7B model, there is no comparison with Light-T2M, an existing model in this field that also claims efficiency. In particular, performance is poor in FID, a metric more important than Light-T2M, and an analysis of this is required.
- Absence of User Study
- User study is essential for assessing the quality of human motion, but this paper lacks such an evaluation.
Questions for authors
-
Please identify the differences between this model and the part-aware tokenizer methodologies used in existing part-aware methodologies, and if possible, conduct comparative experiments and analyses.
-
Since R-Precision and MultiModal Dist show higher performance than Real Motion, please add an analysis regarding whether the claimed model's performance is superior.
-
The MultiModality is significantly low; please add an analysis regarding this.
-
Please measure and compare FLOPs, model parameters, and latency with existing models in the Text-to-Motion field.
-
There have been many recent assessments that the feature extractor is biased. Please conduct evaluation experiments using the evaluation tool used in MARDM and TMR.
-
Please conduct user study with at least 20 users.