Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.07554 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915101232070656 |
|---|---|
| author | Biyyala, Varun Kathuria, Bharat Chanderprakash Li, Jialu Zhang, Youshan |
| author_facet | Biyyala, Varun Kathuria, Bharat Chanderprakash Li, Jialu Zhang, Youshan |
| contents | Video editing models have advanced significantly, but evaluating their performance remains challenging. Traditional metrics, such as CLIP text and image scores, often fall short: text scores are limited by inadequate training data and hierarchical dependencies, while image scores fail to assess temporal consistency. We present SST-EM (Semantic, Spatial, and Temporal Evaluation Metric), a novel evaluation framework that leverages modern Vision-Language Models (VLMs), Object Detection, and Temporal Consistency checks. SST-EM comprises four components: (1) semantic extraction from frames using a VLM, (2) primary object tracking with Object Detection, (3) focused object refinement via an LLM agent, and (4) temporal consistency assessment using a Vision Transformer (ViT). These components are integrated into a unified metric with weights derived from human evaluations and regression analysis. The name SST-EM reflects its focus on Semantic, Spatial, and Temporal aspects of video evaluation. SST-EM provides a comprehensive evaluation of semantic fidelity and temporal smoothness in video editing. The source code is available in the \textbf{\href{https://github.com/custommetrics-sst/SST_CustomEvaluationMetrics.git}{GitHub Repository}}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_07554 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SST-EM: Advanced Metrics for Evaluating Semantic, Spatial and Temporal Aspects in Video Editing Biyyala, Varun Kathuria, Bharat Chanderprakash Li, Jialu Zhang, Youshan Computer Vision and Pattern Recognition Computation and Language Video editing models have advanced significantly, but evaluating their performance remains challenging. Traditional metrics, such as CLIP text and image scores, often fall short: text scores are limited by inadequate training data and hierarchical dependencies, while image scores fail to assess temporal consistency. We present SST-EM (Semantic, Spatial, and Temporal Evaluation Metric), a novel evaluation framework that leverages modern Vision-Language Models (VLMs), Object Detection, and Temporal Consistency checks. SST-EM comprises four components: (1) semantic extraction from frames using a VLM, (2) primary object tracking with Object Detection, (3) focused object refinement via an LLM agent, and (4) temporal consistency assessment using a Vision Transformer (ViT). These components are integrated into a unified metric with weights derived from human evaluations and regression analysis. The name SST-EM reflects its focus on Semantic, Spatial, and Temporal aspects of video evaluation. SST-EM provides a comprehensive evaluation of semantic fidelity and temporal smoothness in video editing. The source code is available in the \textbf{\href{https://github.com/custommetrics-sst/SST_CustomEvaluationMetrics.git}{GitHub Repository}}. |
| title | SST-EM: Advanced Metrics for Evaluating Semantic, Spatial and Temporal Aspects in Video Editing |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2501.07554 |