CVPR 2019 accepted papers by research area
1,294 papers were accepted at CVPR 2019 (+315 vs 2018). Here is how they split across 19 research areas, and which topics gained the most ground.
See CVPR 2019 in the interactive map
Submitting to CVPR? Checklist →
Research areas
| Area | Papers | Share | Change in share vs 2018 |
|---|---|---|---|
| Detection and segmentation | 239 | 18.5% | +3.5 pts |
| 3D vision | 209 | 16.2% | -2.5 pts |
| Label-efficient and robust learning | 206 | 15.9% | +0.6 pts |
| Image generation | 141 | 10.9% | -1.9 pts |
| Video | 117 | 9.0% | -1.9 pts |
| Architectures and efficiency | 106 | 8.2% | +0.2 pts |
| Vision-language and multimodal | 68 | 5.3% | steady |
| Point clouds | 53 | 4.1% | +0.5 pts |
| Graph learning | 36 | 2.8% | +1.5 pts |
| Adversarial robustness and security | 35 | 2.7% | +0.9 pts |
| Learning theory and algorithms | 28 | 2.2% | -1.5 pts |
| Probabilistic and scientific modeling | 23 | 1.8% | +0.6 pts |
| Multi-agent systems and games | 10 | 0.8% | +0.2 pts |
| Optimization | 8 | 0.6% | steady |
| Continual learning | 6 | 0.5% | +0.3 pts |
| Reinforcement learning | 3 | 0.2% | -0.2 pts |
| Time series | 3 | 0.2% | steady |
| Federated learning and privacy | 2 | 0.2% | steady |
| Large language models | 1 | 0.1% | steady |
Fastest-growing topics at CVPR 2019
Change in share of CVPR papers from 2018 to 2019, topics with at least 10 papers.
- CNN features (Detection and segmentation): 72 → 124 papers
- Open-set and few-shot detection (Detection and segmentation): 41 → 76 papers
- Knowledge and temporal graphs (Graph learning): 5 → 23 papers
- Neural architecture search (Architectures and efficiency): 2 → 12 papers
- Zero-/few-shot and meta-learning (Label-efficient and robust learning): 18 → 33 papers
- Cross-modal learning (Vision-language and multimodal): 2 → 11 papers
- Variational and generative sampling (Probabilistic and scientific modeling): 3 → 12 papers
- Shape and surface completion (Point clouds): 6 → 14 papers
- Domain adaptation and generalization (Label-efficient and robust learning): 31 → 47 papers
- Attacks on text and graphs (Adversarial robustness and security): 9 → 15 papers
More venues
Same year: ICML 2019 · NeurIPS 2019 · ICLR 2019 · AAAI 2019 · ICCV 2019 · TPAMI 2019 · IJCV 2019 · JMLR 2019
CVPR in other years: 2016 · 2017 · 2018 · 2020 · 2021 · 2022 · 2023 · 2024 · 2025 · 2026
