Research map / Vision-language and multimodal / Human and embodied modeling
Leveraging Textual Compositional Reasoning for Robust Change Captioning
Kyu Ri Park, Jiyoung Park, Seong Tae Kim, Hong Joo Lee, Jung Uk 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 CORTEX | SCORER · CLEVR-Change (total) | CIDEr: 126.8 -> 128.8 | Improved |
| add CORTEX | DIRL · CLEVR-Change (total) | CIDEr: 125.3 -> 130.7 | Improved |
| add CORTEX | DIRL · Spot-the-Diff | CIDEr: 40.9 -> 49.5 | Improved |
| add CORTEX | SMART · Spot-the-Diff | METEOR: 13.5 -> 12.2 | Hurt |
| add CORTEX | SCORER · CLEVR-DC | CIDEr: 83.7 -> 88.7 | Improved |
| add RTE text module (ablation) | DIRL · CLEVR-Change (total) | CIDEr: 125.3 -> 128.5 | Improved |
| add ITDA on top of RTE (ablation) | DIRL · CLEVR-Change (total) | CIDEr: 128.5 -> 130.7 | Improved |
| add static alignment loss Lsa (ablation) | DIRL+CORTEX · CLEVR-Change (total) | CIDEr: 127.9 -> 128.4 | Improved |
| add dynamic alignment loss Lda (ablation) | DIRL+CORTEX · CLEVR-Change (total) | CIDEr: 127.9 -> 128.9 | Improved |
| use compositional prompt instead of generic descriptions (ablation) | CORTEX (DIRL) · CLEVR-Change (total) | CIDEr: 129.5 -> 130.7 | Improved |
| use InternVL2 instead of LLaVA (ablation) | CORTEX (DIRL) · CLEVR-Change (total) | CIDEr: 130.0 -> 130.7 | Improved |
| use VLM on single images as auxiliary context instead of direct paired prediction (ablation) | CORTEX (DIRL) · Spot-the-Diff | CIDEr: 12.3 -> 49.5 | Improved |
Closest papers by meaning
- VisMin: Visual Minimal-Change Understanding (NeurIPS 2024 · similarity 0.88)
- Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions (NeurIPS 2025 · similarity 0.87)
- Natural Language Inference Improves Compositionality in Vision-Language Models (ICLR 2025 · similarity 0.87)
- Region-aware Difference Distilling with Attribute-guided Contrastive Regularization for Change Captioning (AAAI 2025 · similarity 0.87)
- Beyond Bag-of-Words: Diagnosing Compositional Binding Failures in Vision-Language Models (NeurIPS 2026 · similarity 0.86)
- Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding (CVPR 2024 · similarity 0.86)
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.
