# X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfer

arXiv: https://arxiv.org/abs/2312.07378 · HTML: https://mlsanity.com/paper/2312.07378/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 12 Dec 2023.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [SAT: 2D Semantics Assisted Training for 3D Visual Grounding](https://mlsanity.com/paper/2105.11450/) (2021)
- [Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2206.02099/) (2022)
- [MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences](https://mlsanity.com/paper/1910.09165/) (2019)
- [Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review](https://mlsanity.com/paper/2004.05224/) (2020)
- [PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences](https://mlsanity.com/paper/2205.13713/) (2022)
- [3DV: 3D Dynamic Voxel for Action Recognition in Depth Video](https://mlsanity.com/paper/2005.05501/) (2020)
- [Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding](https://mlsanity.com/paper/2208.00281/) (2022)
- [PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing](https://mlsanity.com/paper/1910.08287/) (2019)
- [Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning](https://mlsanity.com/paper/2212.05330/) (2022)
- [Rank Pooling for Action Recognition](https://mlsanity.com/paper/1512.01848/) (2015)
- [Learning from Temporal Gradient for Semi-supervised Action Recognition](https://mlsanity.com/paper/2111.13241/) (2021)
- [No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces](https://mlsanity.com/paper/2203.11113/) (2022)

## Built on by (most cited first, 12 of 12)

- [Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perception](https://mlsanity.com/paper/2602.23069/) (2026)
- [MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models](https://mlsanity.com/paper/2405.14338/) (2024)
- [HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation](https://mlsanity.com/paper/2403.16788/) (2024)
- [Advancing 3D Point Cloud Understanding through Deep Transfer Learning: A Comprehensive Survey](https://mlsanity.com/paper/2407.17877/) (2024)
- [RadarLLM: Empowering Large Language Models to Understand Human Motion from Millimeter-Wave Point Cloud Sequence](https://mlsanity.com/paper/2504.09862/) (2025)
- [LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Rendering and Control](https://mlsanity.com/paper/2406.16038/) (2024)
- [Tri-Efficient Transfer Learning for Point Cloud Videos](https://mlsanity.com/paper/2606.24175/) (2026)
- [STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understanding](https://mlsanity.com/paper/2604.11637/) (2026)
- [SRENet: Spectral Re-Entry Network for Point Cloud Action Recognition](https://mlsanity.com/paper/2606.03160/) (2026)
- [GATS: Gaussian Aware Temporal Scaling Transformer for Invariant 4D Spatio-Temporal Point Cloud Representation](https://mlsanity.com/paper/2603.16154/) (2026)
- [Paving the Way for Point Cloud Video Representation Learning Using A PDE Model](https://mlsanity.com/paper/2606.01604/) (2026)
- [POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking](https://mlsanity.com/paper/2607.06649/) (2026)

## Abstract (arXiv)

The field of 4D point cloud understanding is rapidly developing with the goal of analyzing dynamic 3D point cloud sequences. However, it remains a challenging task due to the sparsity and lack of texture in point clouds. Moreover, the irregularity of point cloud poses a difficulty in aligning temporal information within video sequences. To address these issues, we propose a novel cross-modal knowledge transfer framework, called X4D-SceneFormer. This framework enhances 4D-Scene understanding by transferring texture priors from RGB sequences using a Transformer architecture with temporal relationship mining. Specifically, the framework is designed with a dual-branch architecture, consisting of an 4D point cloud transformer and a Gradient-aware Image Transformer (GIT). During training, we employ multiple knowledge transfer techniques, including temporal consistency losses and masked self-attention, to strengthen the knowledge transfer between modalities. This leads to enhanced performance during inference using single-modal 4D point cloud inputs. Extensive experiments demonstrate the superior performance of our framework on various 4D point cloud video understanding tasks, including action recognition, action segmentation and semantic segmentation. The results achieve 1st places, i.e., 85.3% (+7.9%) accuracy and 47.3% (+5.0%) mIoU for 4D action segmentation and semantic segmentation, on the HOI4D challengefootnoteurlhttp://www.hoi4d.top/., outperforming previous state-of-the-art by a large margin. We release the code at https://github.com/jinglinglingling/X4D