# Appearance-Preserving 3D Convolution for Video-based Person Re-identification

arXiv: https://arxiv.org/abs/2007.08434 · HTML: https://mlsanity.com/paper/2007.08434/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2020.

## Built on by (most cited first, 30 of 63)

- [Clothes-Changing Person Re-identification with RGB Modality Only](https://mlsanity.com/paper/2204.06890/) (2022)
- [BigGait: Learning Gait Representation You Want by Large Vision Models](https://mlsanity.com/paper/2402.19122/) (2024)
- [BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification](https://mlsanity.com/paper/2104.14783/) (2021)
- [TF-CLIP: Learning Text-free CLIP for Video-based Person Re-Identification](https://mlsanity.com/paper/2312.09627/) (2023)
- [Learning Compatible Embeddings](https://mlsanity.com/paper/2108.01958/) (2021)
- [Spatio-Temporal Representation Factorization for Video-based Person Re-Identification](https://mlsanity.com/paper/2107.11878/) (2021)
- [A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification](https://mlsanity.com/paper/2104.01745/) (2021)
- [Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos](https://mlsanity.com/paper/2104.08241/) (2021)
- [Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2208.02450/) (2022)
- [Dense Interaction Learning for Video-based Person Re-identification](https://mlsanity.com/paper/2103.09013/) (2021)
- [Deeply-Coupled Convolution-Transformer with Spatial-temporal Complementary Learning for Video-based Person Re-identification](https://mlsanity.com/paper/2304.14122/) (2023)
- [Text-Visual Prompting for Efficient 2D Temporal Video Grounding](https://mlsanity.com/paper/2303.04995/) (2023)
- [Multi-direction and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval](https://mlsanity.com/paper/2202.06014/) (2022)
- [Cross-Platform Video Person ReID: A New Benchmark Dataset and Adaptation Approach](https://mlsanity.com/paper/2408.07500/) (2024)
- [MEVID: Multi-view Extended Videos with Identities for Video Person Re-Identification](https://mlsanity.com/paper/2211.04656/) (2022)
- [Spatiotemporal Transformer for Video-based Person Re-identification](https://mlsanity.com/paper/2103.16469/) (2021)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [On Denoising Walking Videos for Gait Recognition](https://mlsanity.com/paper/2505.18582/) (2025)
- [Video-based Person Re-identification with Long Short-Term Representation Learning](https://mlsanity.com/paper/2308.03703/) (2023)
- [ShARc: Shape and Appearance Recognition for Person Identification In-the-wild](https://mlsanity.com/paper/2310.15946/) (2023)
- [GEFF: Improving Any Clothes-Changing Person ReID Model using Gallery Enrichment with Face Features](https://mlsanity.com/paper/2211.13807/) (2022)
- [HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReID](https://mlsanity.com/paper/2508.05038/) (2025)
- [RealGait: Gait Recognition for Person Re-Identification](https://mlsanity.com/paper/2201.04806/) (2022)
- [Video-Level Language-Driven Video-Based Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2506.02439/) (2025)
- [LATex: Leveraging Attribute-based Text Knowledge for Aerial-Ground Person Re-Identification](https://mlsanity.com/paper/2503.23722/) (2025)
- [Video Person Re-identification using Attribute-enhanced Features](https://mlsanity.com/paper/2108.06946/) (2021)
- [Whole-body Detection, Recognition and Identification at Altitude and Range](https://mlsanity.com/paper/2311.05725/) (2023)
- [Activity-Biometrics: Person Identification from Daily Activities](https://mlsanity.com/paper/2403.17360/) (2024)
- [Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification](https://mlsanity.com/paper/2501.16811/) (2025)
- [Multi-scale Context-aware Network with Transformer for Gait Recognition](https://mlsanity.com/paper/2204.03270/) (2022)

## Abstract (arXiv)

Due to the imperfect person detection results and posture changes, temporal appearance misalignment is unavoidable in video-based person re-identification (ReID). In this case, 3D convolution may destroy the appearance representation of person video clips, thus it is harmful to ReID. To address this problem, we propose AppearancePreserving 3D Convolution (AP3D), which is composed of two components: an Appearance-Preserving Module (APM) and a 3D convolution kernel. With APM aligning the adjacent feature maps in pixel level, the following 3D convolution can model temporal information on the premise of maintaining the appearance representation quality. It is easy to combine AP3D with existing 3D ConvNets by simply replacing the original 3D convolution kernels with AP3Ds. Extensive experiments demonstrate the effectiveness of AP3D for video-based ReID and the results on three widely used datasets surpass the state-of-the-arts. Code is available at: https://github.com/guxinqian/AP3D.