CVPR 2024 accepted papers by research area
2,716 papers were accepted at CVPR 2024 (+357 vs 2023). Here is how they split across 19 research areas, and which topics gained the most ground.
See CVPR 2024 in the interactive map
Research areas
| Area | Papers | Share | Change in share vs 2023 |
|---|---|---|---|
| 3D vision | 631 | 23.2% | +2.4 pts |
| Image generation | 450 | 16.6% | +5.0 pts |
| Vision-language and multimodal | 329 | 12.1% | +4.6 pts |
| Detection and segmentation | 296 | 10.9% | -3.2 pts |
| Video | 271 | 10.0% | -0.1 pts |
| Label-efficient and robust learning | 240 | 8.8% | -5.4 pts |
| Architectures and efficiency | 120 | 4.4% | -0.5 pts |
| Point clouds | 102 | 3.8% | -1.4 pts |
| Adversarial robustness and security | 63 | 2.3% | -0.9 pts |
| Continual learning | 48 | 1.8% | steady |
| Federated learning and privacy | 37 | 1.4% | +0.2 pts |
| Probabilistic and scientific modeling | 28 | 1.0% | -0.2 pts |
| Large language models | 25 | 0.9% | +0.7 pts |
| Multi-agent systems and games | 23 | 0.8% | steady |
| Learning theory and algorithms | 18 | 0.7% | -0.4 pts |
| Graph learning | 17 | 0.6% | -0.6 pts |
| Reinforcement learning | 11 | 0.4% | steady |
| Optimization | 5 | 0.2% | steady |
| Time series | 2 | 0.1% | steady |
Fastest-growing topics at CVPR 2024
Change in share of CVPR papers from 2023 to 2024, topics with at least 10 papers.
- Text-to-image diffusion (Image generation): 28 → 127 papers
- 3D generation (3D vision): 82 → 169 papers
- Multimodal LLMs (Vision-language and multimodal): 0 → 56 papers
- Gaussian splatting (3D vision): 0 → 52 papers
- Fast diffusion sampling (Image generation): 14 → 57 papers
- Video generation (Video): 27 → 66 papers
- CLIP and zero-shot (Vision-language and multimodal): 48 → 88 papers
- Human and embodied modeling (Vision-language and multimodal): 69 → 94 papers
- Cross-modal learning (Vision-language and multimodal): 41 → 59 papers
- Editing and style transfer (Image generation): 57 → 76 papers
More venues
Same year: ICML 2024 · NeurIPS 2024 · ICLR 2024 · AAAI 2024