Research map / Video / Video-language understanding
Character Grounding and Re-Identification in Story of Videos and Text Descriptions
Youngjae Yu, Jongseok Kim, Heeseung Yun, Jiwan Chung, Gunhee Kim
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 body-part embedding to face-only video re-id (ablation) | CiSIN · M-VAD Names video re-id | accuracy: 0.783 -> 0.799 | Improved |
| add simple average-pooled human bbox embedding to face (ablation) | CiSIN · M-VAD Names video re-id | accuracy: 0.783 -> 0.781 | No clear effect |
| add text context (grounding and text matching) to video re-id (ablation) | CiSIN · M-VAD Names video re-id | accuracy: 0.799 -> 0.806 | Improved |
| add face embedding for re-id vs ImageNet ResNet-50 | CiSIN · M-VAD Names video re-id | accuracy: 0.617 -> 0.783 | Improved |
| add motion embedding (ablation) | CiSIN · M-VAD Names grounding | accuracy: 0.606 -> 0.684 | Improved |
| add attribute (gender) module and Text Re-Id joint training (ablation) | CiSIN · M-VAD Names grounding | accuracy: 0.651 -> 0.673 | Improved |
| add Text Re-Id Graph joint training (ablation) | CiSIN · M-VAD Names grounding | accuracy: 0.673 -> 0.684 | Improved |
| add attribute loss and grounding graph to BERT text re-id (ablation) | CiSIN · M-VAD Names text re-id | accuracy: 0.734 -> 0.743 | Improved |
| add Character Grounding graph training (ablation) | CiSIN · M-VAD Names text re-id | accuracy: 0.743 -> 0.754 | Improved |
| add Video Re-Id graph (full joint training) (ablation) | CiSIN · M-VAD Names text re-id | accuracy: 0.754 -> 0.767 | Improved |
| add Text Re-Id graph (ablation) | CiSIN · M-VAD Names text re-id | accuracy: 0.737 -> 0.767 | Improved |
| use joint training instead of separate training (ablation) | CiSIN · LSMDC 2019 Fill-in the Characters | accuracy: 0.653 -> 0.673 | Improved |
Closest papers by meaning
- Comprehensive Visual Grounding for Video Description (AAAI 2024 · similarity 0.85)
- Identity-Text Video Corpus Grounding (AAAI 2025 · similarity 0.84)
- Improving Panoptic Narrative Grounding by Harnessing Semantic Relationships and Visual Confirmation (AAAI 2024 · similarity 0.84)
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (CVPR 2025 · similarity 0.84)
- OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition (CVPR 2024 · similarity 0.84)
- Storybooth: Training-Free Multi-Subject Consistency for Improved Visual Storytelling (ICLR 2025 · 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.
