Official Review · ICLR 2025

This paper focuses on analyzing the strengths and limitations of existing video diffusion models for different video understanding tasks. A probing framework is proposed to extract the video feature representations from existing pre-trained models and learn lightweight task heads for different downstream video understanding tasks. Comprehensive experiments across six models and four downstream video tasks are conducted and some findings are demonstrated. 1) The investigation of different characteristics of image-/video-based diffusions is interesting and meaningful for the video-understanding community; 2) The proposed probing framework is technically sound and the experimental results are comprehensive. 3) The paper is well-written, making it easy to follow and understand. 1) Although many findings are demonstrated by the comprehensive results, **the reviewer finds these findings are well-known consensus in the video understanding community**. For example, modeling the human motion or object dynamics is important for analyzing the videos, it is straightforward that most video-based diffusions contribute their models to this problem. Therefore, for instance, the findings "video diffusion models demonstrate exceptional proficiency in capturing motion patterns and temporal dynamics" that the paper try to demonstrate, **cannot provide new insights to the community**; 2) The used video action recognition datasets, i.e., UCF and HMDB, actually do not require modeling too much temporal/dynamic semantics for recognition. To make the demonstration more convincing, the reviewer thinks experiments should be conducted on the action datasets that require effective temporal dynamics modeling (e.g., something v2, Kinetics). minor issues: 1) the symbol zT in line #231 should be corrected; 2) the sentence in line #289~290 should be revised; please see the weaknesses section.