# PANDA: A Gigapixel-level Human-centric Video Dataset

arXiv: https://arxiv.org/abs/2003.04852 · HTML: https://mlsanity.com/paper/2003.04852/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Mar 2020.

## Built on by (most cited first, 30 of 45)

- [OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning](https://mlsanity.com/paper/2311.11666/) (2023)
- [Toward Visual Grounding: A Survey](https://mlsanity.com/paper/2412.20206/) (2024)
- [Learning to Downsample for Segmentation of Ultra-High Resolution Images](https://mlsanity.com/paper/2109.11071/) (2021)
- [Reconstructing Groups of People with Hypergraph Relational Reasoning](https://mlsanity.com/paper/2308.15844/) (2023)
- [ESOD: Efficient Small Object Detection on High-Resolution Images](https://mlsanity.com/paper/2407.16424/) (2024)
- [Nonverbal Interaction Detection](https://mlsanity.com/paper/2407.08133/) (2024)
- [SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers](https://mlsanity.com/paper/2506.00830/) (2025)
- [Panoramic Human Activity Recognition](https://mlsanity.com/paper/2203.03806/) (2022)
- [JRDB-Social: A Multifaceted Robotic Dataset for Understanding of Context and Dynamics of Human Interactions Within Social Groups](https://mlsanity.com/paper/2404.04458/) (2024)
- [Crowd3D: Towards Hundreds of People Reconstruction from a Single Image](https://mlsanity.com/paper/2301.09376/) (2023)
- [Efficient High-Resolution Deep Learning: A Survey](https://mlsanity.com/paper/2207.13050/) (2022)
- [MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos](https://mlsanity.com/paper/2507.05675/) (2025)
- [Vision-based Multi-future Trajectory Prediction: A Survey](https://mlsanity.com/paper/2302.10463/) (2023)
- [Self-supervised Social Relation Representation for Human Group Detection](https://mlsanity.com/paper/2203.03843/) (2022)
- [SparseFormer: Detecting Objects in HRW Shots via Sparse Vision Transformer](https://mlsanity.com/paper/2502.07216/) (2025)
- [XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold](https://mlsanity.com/paper/2403.19517/) (2024)
- [SaccadeDet: A Novel Dual-Stage Architecture for Rapid and Accurate Detection in Gigapixel Images](https://mlsanity.com/paper/2407.17956/) (2024)
- [AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning](https://mlsanity.com/paper/2507.12841/) (2025)
- [Learning Human-Object Interaction as Groups](https://mlsanity.com/paper/2510.18357/) (2025)
- [SHD360: A Benchmark Dataset for Salient Human Detection in 360deg Videos](https://mlsanity.com/paper/2105.11578/) (2021)
- [Dynamic Group Detection using VLM-augmented Temporal Groupness Graph](https://mlsanity.com/paper/2509.04758/) (2025)
- [HighlightMe: Detecting Highlights from Human-Centric Videos](https://mlsanity.com/paper/2110.01774/) (2021)
- [SOMPT22: A Surveillance Oriented Multi-Pedestrian Tracking Dataset](https://mlsanity.com/paper/2208.02580/) (2022)
- [PromptMix: Text-to-image diffusion models enhance the performance of lightweight networks](https://mlsanity.com/paper/2301.12914/) (2023)
- [Data-Side Efficiencies for Lightweight Convolutional Neural Networks](https://mlsanity.com/paper/2308.13057/) (2023)
- [HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding?](https://mlsanity.com/paper/2504.18406/) (2025)
- [DyCrowd: Towards Dynamic Crowd Reconstruction from a Large-scene Video](https://mlsanity.com/paper/2508.12644/) (2025)
- [ADG-Pose: Automated Dataset Generation for Real-World Human Pose Estimation](https://mlsanity.com/paper/2202.00753/) (2022)
- [CrowdRec: 3D Crowd Reconstruction from Single Color Images](https://mlsanity.com/paper/2310.06332/) (2023)
- [RCR: Robust Crowd Reconstruction with Upright Space from a Single Large-scene Image](https://mlsanity.com/paper/2411.06232/) (2024)

## Abstract (arXiv)

We present PANDA, the first gigaPixel-level humAN-centric viDeo dAtaset, for large-scale, long-term, and multi-object visual analysis. The videos in PANDA were captured by a gigapixel camera and cover real-world scenes with both wide field-of-view (~1 square kilometer area) and high-resolution details (~gigapixel-level/frame). The scenes may contain 4k head counts with over 100x scale variation. PANDA provides enriched and hierarchical ground-truth annotations, including 15,974.6k bounding boxes, 111.8k fine-grained attribute labels, 12.7k trajectories, 2.2k groups and 2.9k interactions. We benchmark the human detection and tracking tasks. Due to the vast variance of pedestrian pose, scale, occlusion and trajectory, existing approaches are challenged by both accuracy and efficiency. Given the uniqueness of PANDA with both wide FoV and high resolution, a new task of interaction-aware group detection is introduced. We design a 'global-to-local zoom-in' framework, where global trajectories and local interactions are simultaneously encoded, yielding promising results. We believe PANDA will contribute to the community of artificial intelligence and praxeology by understanding human behaviors and interactions in large-scale real-world scenes. PANDA Website: http://www.panda-dataset.com.