Research map / Video / Video-language understanding
Bridging Video Content and Comments: Synchronized Video Description with Temporal Summarization of Crowdsourced Time-Sync Comments
Linli Xu, Chao Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add temporal regularization and previous-summary basis (SJTTR -> T-SJTTR) (ablation) | SJTTR · QPS-EP06 / LYB-EP26 | ROUGE-1 F: 0.3682 -> 0.3758; 0.3913 -> 0.4095 | Improved |
| add topic reconstruction jointly with text reconstruction (DSDR -> SJTTR) (ablation) | DSDR · LYB-EP26 | ROUGE-1 F: 0.3511 -> 0.3913 | Improved |
| replace text reconstruction with topic-only reconstruction (TopicDSDR vs DSDR) | DSDR · LYB-EP26 | ROUGE-1 F: 0.3511 -> 0.3052 | Hurt |
| larger segment size | all methods · LYB-EP26 | ROUGE-1 F | Hurt |
| vary rho between text and topic reconstruction (ablation) | T-SJTTR · LYB-EP26 | F-measure | No clear effect |
| very small gamma (strong temporal influence) (ablation) | T-SJTTR · LYB-EP26 | F-measure | Hurt |
Closest papers by meaning
- Reading the Videos: Temporal Labeling for Crowdsourced Time-Sync Videos Based on Semantic Embedding (AAAI 2016 · similarity 0.91)
- Query-Focused Video Summarization: Dataset, Evaluation, and a Memory Network Based Approach (CVPR 2017 · similarity 0.86)
- Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark (AAAI 2025 · similarity 0.84)
- Video Summarization with Large Language Models (CVPR 2025 · similarity 0.84)
- Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding (CVPR 2025 · similarity 0.84)
- Scaling Up Video Summarization Pretraining with Large Language Models (CVPR 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
