# 3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification

arXiv: https://arxiv.org/abs/1812.10222 · HTML: https://mlsanity.com/paper/1812.10222/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Dec 2018.

## Built on by (most cited first, 14 of 14)

- [SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition](https://mlsanity.com/paper/2102.11603/) (2021)
- [A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification](https://mlsanity.com/paper/2104.01745/) (2021)
- [Learning Sequential Descriptors for Sequence-based Visual Place Recognition](https://mlsanity.com/paper/2207.03868/) (2022)
- [SFANet: A Spectrum-aware Feature Augmentation Network for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2102.12137/) (2021)
- [LipFormer: Learning to Lipread Unseen Speakers based on Visual-Landmark Transformers](https://mlsanity.com/paper/2302.02141/) (2023)
- [Enhancing Visible-Infrared Person Re-identification with Modality- and Instance-aware Visual Prompt Learning](https://mlsanity.com/paper/2406.12316/) (2024)
- [AirObject: A Temporally Evolving Graph Embedding for Object Identification](https://mlsanity.com/paper/2111.15150/) (2021)
- [Auto-selected Knowledge Adapters for Lifelong Person Re-identification](https://mlsanity.com/paper/2405.19005/) (2024)
- [Kinematics Modeling Network for Video-based Human Pose Estimation](https://mlsanity.com/paper/2207.10971/) (2022)
- [Complete Solution for Vehicle Re-ID in Surround-view Camera System](https://mlsanity.com/paper/2212.04126/) (2022)
- [Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identification](https://mlsanity.com/paper/2406.14797/) (2024)
- [Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization](https://mlsanity.com/paper/2509.05604/) (2025)
- [Reliability-Aware 3D Geometric Injection for Universal Person Re-identification](https://mlsanity.com/paper/2607.18863/) (2026)
- [Beyond Appearance: A Multi-cue Framework and Large-scale Benchmark for Pedestrian Association and Tracking on Mobile Aerial-Ground Platforms](https://mlsanity.com/paper/2607.23803/) (2026)

## Abstract (arXiv)

In this paper, we introduce a global video representation to video-based person re-identification (re-ID) that aggregates local 3D features across the entire video extent. Most of the existing methods rely on 2D convolutional networks (ConvNets) to extract frame-wise deep features which are pooled temporally to generate the video-level representations. However, 2D ConvNets lose temporal input information immediately after the convolution, and a separate temporal pooling is limited in capturing human motion in shorter sequences. To this end, we present a textitglobal video representation (3D PersonVLAD), complementary to 3D ConvNets as a novel layer to capture the appearance and motion dynamics in full-length videos. However, encoding each video frame in its entirety and computing an aggregate global representation across all frames is tremendously challenging due to occlusions and misalignments. To resolve this, our proposed network is further augmented with 3D part alignment module to learn local features through soft-attention module. These attended features are statistically aggregated to yield identity-discriminative representations. Our global 3D features are demonstrated to achieve state-of-the-art results on three benchmark datasets: MARS citeMARS, iLIDS-VID citeVideoRanking, and PRID 2011