Motion Attribution for Video Generation
Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a motion-centric, gradient-based data attribution framework that scales to modern, large, high-quality video datasets and models. We use this to study which fine-tuning clips improve or degrade temporal dynamics. Motive isolates temporal dynamics from static appearance via motion-weighted loss masks, yielding efficient and scalable motion-specific influence computation. On text-to-video models, Motive identifies clips that strongly affect motion and guides data curation that improves temporal consistency and physical plausibility. With Motive-selected high-influence data, our method improves both motion smoothness and dynamic degree on VBench, achieving a 74.1% human preference win rate compared with the pretrained base model. To our knowledge, this is the first framework to attribute motion rather than visual appearance in video generative models and to use it to curate fine-tuning data.
Code (0)
등록된 구현이 없습니다.
Tasks
Video GenerationSimilar Papers 제목 키워드 기반
A Multi-task Neural Approach for Emotion Attribution, Classification and Summarization
Emotional content is a crucial ingredient in user-generated videos. However, the sparsity of emotional expressions in the videos poses an obstacle to visual emotion analysis. In this paper, we propose a new neural approa…
ClassificationEmotion RecognitionGeneral ClassificationHeterogeneous Knowledge Transfer in Video Emotion Recognition, Attribution and Summarization
Emotion is a key element in user-generated videos. However, it is difficult to understand emotions conveyed in such videos due to the complex and unstructured nature of user-generated content and the sparsity of video fr…
Emotion RecognitionTransfer LearningVideo Emotion RecognitionZero-Shot LearningExtending Information Bottleneck Attribution to Video Sequences
We introduce VIBA, a novel approach for explainable video classification by adapting Information Bottlenecks for Attribution (IBA) to video sequences. While most traditional explainability methods are designed for image …
DeepFake DetectionFace SwappingOptical Flow EstimationVideo ClassificationSource Camera Verification from Strongly Stabilized Videos
Image stabilization performed during imaging and/or post-processing poses one of the most significant challenges to photo-response non-uniformity based source camera attribution from videos. When performed digitally, sta…
Video GenerationSWIFT: Sliding Window Reconstruction for Few-Shot Training-Free Generated Video Attribution
Recent advancements in video generation technologies have been significant, resulting in their widespread application across multiple domains. However, concerns have been mounting over the potential misuse of generated c…
Video Generation