Research map / Vision-language and multimodal / Human and embodied modeling
Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning
Xiangxi Shi, Xu Yang, Jiuxiang Gu, Shafiq Joty, Jianfei Cai
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 reinforcement attention fine-tuning (RAF) to M-VAM (ablation) | M-VAM · Spot-the-Diff | BLEU4: 10.1 -> 11.1 | Improved |
| add reinforcement attention fine-tuning (RAF) to M-VAM (ablation) | M-VAM · Spot-the-Diff | ROUGE_L: 31.3 -> 33.2 | Improved |
| add reinforcement attention fine-tuning (RAF) to M-VAM (ablation) | M-VAM · Spot-the-Diff | CIDEr: 38.1 -> 42.5 | Improved |
| add reinforcement attention fine-tuning (RAF) to M-VAM (ablation) | M-VAM · Spot-the-Diff | SPICE: 14.0 -> 17.1 | Improved |
| add reinforcement attention fine-tuning (RAF) to M-VAM (ablation) | M-VAM · Spot-the-Diff | METEOR: 12.4 -> 12.9 | Improved |
| add reinforcement attention fine-tuning (RAF) to M-VAM (ablation) | M-VAM · CLEVR-Change (with distractor) | BLEU4: 50.3 -> 51.3 | Improved |
| add reinforcement attention fine-tuning (RAF) to M-VAM (ablation) | M-VAM · CLEVR-Change (with distractor) | CIDEr: 114.9 -> 115.8 | Improved |
| add reinforcement attention fine-tuning (RAF) to M-VAM (ablation) | M-VAM · CLEVR-Change (with distractor) | SPICE: 30.5 -> 30.7 | Improved |
| add reinforcement attention fine-tuning (RAF) to M-VAM (ablation) | M-VAM · CLEVR-Change (without distractor) | BLEU4: 45.5 -> 50.1 | Improved |
| add reinforcement attention fine-tuning (RAF) to M-VAM (ablation) | M-VAM · CLEVR-Change (without distractor) | CIDEr: 117.4 -> 119.1 | Improved |
| add reinforcement attention fine-tuning (RAF) to M-VAM (ablation) | M-VAM · CLEVR-Change (without distractor) | SPICE: 29.4 -> 31.2 | Improved |
| train without distractor image pairs | M-VAM + RAF · CLEVR-Change | SPICE: 30.7 -> 31.2 | Improved |
Closest papers by meaning
- DECIDER: Difference-aware Contrastive Diffusion Model with Adversarial Perturbations for Image Change Captioning (AAAI 2025 · similarity 0.89)
- Region-aware Difference Distilling with Attribute-guided Contrastive Regularization for Change Captioning (AAAI 2025 · similarity 0.89)
- Change3D: Revisiting Change Detection and Captioning from A Video Modeling Perspective (CVPR 2025 · similarity 0.88)
- Revisiting Change Captioning from Self-supervised Global-Part Alignment (AAAI 2025 · similarity 0.86)
- VisMin: Visual Minimal-Change Understanding (NeurIPS 2024 · similarity 0.86)
- VIXEN: Visual Text Comparison Network for Image Difference Captioning (AAAI 2024 · similarity 0.85)
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.
