# Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identification arXiv: https://arxiv.org/abs/2509.16635 ยท HTML: https://mlsanity.com/paper/2509.16635/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Builds on 37 of its 62 references that are in the map. - First posted on arXiv 20 Sep 2025. ## Builds on (most cited first, 30 of 37) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020) - [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016) - [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017) - [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020) - [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017) - [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020) - [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018) - [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017) - [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017) - [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021) - [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021) - [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019) - [VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts](https://mlsanity.com/paper/2111.02358/) (2021) - [DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://mlsanity.com/paper/2201.05596/) (2022) - [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020) - [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022) - [Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2303.02861/) (2023) - [Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2007.09314/) (2020) - [Clothes-Changing Person Re-identification with RGB Modality Only](https://mlsanity.com/paper/2204.06890/) (2022) - [Person Re-identification by Contour Sketch under Moderate Clothing Change](https://mlsanity.com/paper/2002.02295/) (2020) - [Long-Term Cloth-Changing Person Re-identification](https://mlsanity.com/paper/2005.12633/) (2020) - [Cross-modality Person re-identification with Shared-Specific Feature Transfer](https://mlsanity.com/paper/2002.12489/) (2020) - [Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2303.14481/) (2023) - [Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization](https://mlsanity.com/paper/2103.15537/) (2021) - [UniHCP: A Unified Model for Human-Centric Perceptions](https://mlsanity.com/paper/2303.02936/) (2023) - [Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs](https://mlsanity.com/paper/2206.04674/) (2022) - [When Person Re-identification Meets Changing Clothes](https://mlsanity.com/paper/2003.04070/) (2020) - [Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark](https://mlsanity.com/paper/2105.15076/) (2021) - [HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining](https://mlsanity.com/paper/2303.05675/) (2023) - [Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2304.04205/) (2023) ## Built on by (most cited first, 5 of 5) - [MFEN:Multi-Frequency Expert Network for Visible-Infrared Person Re-ID](https://mlsanity.com/paper/2606.12051/) (2026) - [MMGait: Towards Multi-Modal Gait Recognition](https://mlsanity.com/paper/2604.15979/) (2026) - [Unified Multi-Dataset Training for TBPS](https://mlsanity.com/paper/2601.14978/) (2026) - [Beyond Visual Cues: Semantic-Driven Token Filtering and Expert Routing for Anytime Person ReID](https://mlsanity.com/paper/2604.15090/) (2026) - [ANFI: Rethinking Neighbor Feature Interaction in Person Re-ID](https://mlsanity.com/paper/2607.25407/) (2026) ## Abstract (arXiv) In real applications, person re-identification (ReID) is expected to retrieve the target person at any time, including both daytime and nighttime, ranging from short-term to long-term. However, existing ReID tasks and datasets can not meet this requirement, as they are constrained by available time and only provide training and evaluation for specific scenarios. Therefore, we investigate a new task called Anytime Person Re-identification (AT-ReID), which aims to achieve effective retrieval in multiple scenarios based on variations in time. To address the AT-ReID problem, we collect the first large-scale dataset, AT-USTC, which contains 403k images of individuals wearing multiple clothes captured by RGB and IR cameras. Our data collection spans 21 months, and 270 volunteers were photographed on average 29.1 times across different dates or scenes, 4-15 times more than current datasets, providing conditions for follow-up investigations in AT-ReID. Further, to tackle the new challenge of multi-scenario retrieval, we propose a unified model named Uni-AT, which comprises a multi-scenario ReID (MS-ReID) framework for scenario-specific features learning, a Mixture-of-Attribute-Experts (MoAE) module to alleviate inter-scenario interference, and a Hierarchical Dynamic Weighting (HDW) strategy to ensure balanced training across all scenarios. Extensive experiments show that our model leads to satisfactory results and exhibits excellent generalization to all scenarios.