Research map / Video / Video segmentation and tracking
Adaptive Image-to-Video Scene Graph Generation via Knowledge Reasoning and Adversarial Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 knowledge reasoning from commonsense sequences of static relationships (ablation) | Image-to-video scene graph generation · VidVRD | dynamic relationship tagging P@1: 0.00 -> 13.64 | Helped |
| Add knowledge reasoning from commonsense sequences of static relationships (ablation) | Image-to-video scene graph generation · VidOR | dynamic relationship tagging P@1: 0.00 -> 7.77 | Helped |
| Add hierarchical adversarial learning at image and instance levels (ablation) | Image-to-video scene graph generation · VidVRD | object detection mAP: 36.70 -> 49.40 | Helped |
| Add hierarchical adversarial learning at image and instance levels (ablation) | Image-to-video scene graph generation · VidOR | object detection mAP: 20.42 -> 28.13 | Helped |
| Add image-level adversarial learning (ablation) | Image-to-video scene graph generation · VidVRD | object detection mAP: 45.17 -> 49.40 | Helped |
| Add instance-level adversarial learning (ablation) | Image-to-video scene graph generation · VidVRD | object detection mAP: 41.29 -> 49.40 | Helped |
| Add image-level adversarial learning (ablation) | Image-to-video scene graph generation · VidOR | object detection mAP: 26.52 -> 28.13 | Helped |
| Add instance-level adversarial learning (ablation) | Image-to-video scene graph generation · VidOR | object detection mAP: 27.69 -> 28.13 | Helped |
| Use image-trained VidVRD method rather than the proposed image-to-video method | Video scene graph generation · VidVRD | dynamic relationship tagging P@1: 13.64 -> 0.00 | Hurt |
Closest papers by meaning
- A Closer Look at Dynamic Scene Graph Generation in the Era of Multimodal Large Language Models (NeurIPS 2026 · similarity 0.89)
- DiffVsgg: Diffusion-Driven Online Video Scene Graph Generation (CVPR 2025 · similarity 0.88)
- Scene Graph-Grounded Image Generation (AAAI 2025 · similarity 0.88)
- DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation (CVPR 2024 · similarity 0.88)
- HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation (CVPR 2025 · similarity 0.88)
- Towards Unbiased and Robust Spatio-Temporal Scene Graph Generation and Anticipation (CVPR 2025 · similarity 0.88)
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.