# Learning Semantic-Aligned Feature Representation for Text-based Person Search

arXiv: https://arxiv.org/abs/2112.06714 · HTML: https://mlsanity.com/paper/2112.06714/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 13 Dec 2021.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Person Search with Natural Language Description](https://mlsanity.com/paper/1702.05729/) (2017)
- [Dual-Path Convolutional Image-Text Embeddings with Instance Loss](https://mlsanity.com/paper/1711.05535/) (2017)
- [Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification](https://mlsanity.com/paper/2107.12666/) (2021)
- [ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language](https://mlsanity.com/paper/2005.07327/) (2020)
- [Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments](https://mlsanity.com/paper/1906.09610/) (2019)
- [Identity-Aware Textual-Visual Matching with Latent Co-attention](https://mlsanity.com/paper/1708.01988/) (2017)
- [Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search](https://mlsanity.com/paper/1809.08440/) (2018)
- [Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association](https://mlsanity.com/paper/1808.01571/) (2018)

## Built on by (most cited first, 30 of 40)

- [Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval](https://mlsanity.com/paper/2303.12501/) (2023)
- [CLIP-Driven Fine-grained Text-Image Person Re-identification](https://mlsanity.com/paper/2210.10276/) (2022)
- [Number it: Temporal Grounding Videos like Flipping Manga](https://mlsanity.com/paper/2411.10332/) (2024)
- [Noisy-Correspondence Learning for Text-to-Image Person Re-identification](https://mlsanity.com/paper/2308.09911/) (2023)
- [RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search](https://mlsanity.com/paper/2305.13653/) (2023)
- [Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions](https://mlsanity.com/paper/2306.07520/) (2023)
- [Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Search](https://mlsanity.com/paper/2208.14365/) (2022)
- [An Empirical Study of CLIP for Text-based Person Search](https://mlsanity.com/paper/2308.10045/) (2023)
- [Chat-Driven Text Generation and Interaction for Person Retrieval](https://mlsanity.com/paper/2509.12662/) (2025)
- [HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception](https://mlsanity.com/paper/2310.20695/) (2023)
- [iKUN: Speak to Trackers without Retraining](https://mlsanity.com/paper/2312.16245/) (2023)
- [Text-based Person Search without Parallel Image-Text Data](https://mlsanity.com/paper/2305.12964/) (2023)
- [PLOT: Text-based Person Search with Part Slot Attention for Corresponding Part Discovery](https://mlsanity.com/paper/2409.13475/) (2024)
- [Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Search](https://mlsanity.com/paper/2411.17776/) (2024)
- [CLIP-based Synergistic Knowledge Transfer for Text-based Person Retrieval](https://mlsanity.com/paper/2309.09496/) (2023)
- [DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval](https://mlsanity.com/paper/2503.04144/) (2025)
- [BiLMa: Bidirectional Local-Matching for Text-based Person Re-identification](https://mlsanity.com/paper/2309.04675/) (2023)
- [Exploiting the Textual Potential from Vision-Language Pre-training for Text-based Person Search](https://mlsanity.com/paper/2303.04497/) (2023)
- [Learning Comprehensive Representations with Richer Self for Text-to-Image Person Re-Identification](https://mlsanity.com/paper/2310.11210/) (2023)
- [Cross-Modal Adaptive Dual Association for Text-to-Image Person Retrieval](https://mlsanity.com/paper/2312.01745/) (2023)
- [Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-identification](https://mlsanity.com/paper/2405.17790/) (2024)
- [From Attributes to Natural Language: A Survey and Foresight on Text-based Person Re-identification](https://mlsanity.com/paper/2408.00096/) (2024)
- [Semi-supervised Text-based Person Search](https://mlsanity.com/paper/2404.18106/) (2024)
- [Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search](https://mlsanity.com/paper/2412.15106/) (2024)
- [UP-Person: Unified Parameter-Efficient Transfer Learning for Text-based Person Retrieval](https://mlsanity.com/paper/2504.10084/) (2025)
- [Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval](https://mlsanity.com/paper/2509.09118/) (2025)
- [What Makes You Unique? Attribute Prompt Composition for Object Re-Identification](https://mlsanity.com/paper/2509.18715/) (2025)
- [Person Text-Image Matching via Text-Feature Interpretability Embedding and External Attack Node Implantation](https://mlsanity.com/paper/2211.08657/) (2022)
- [Enhancing Visual Representation for Text-based Person Searching](https://mlsanity.com/paper/2412.20646/) (2024)
- [Minimizing the Pretraining Gap: Domain-aligned Text-Based Person Retrieval](https://mlsanity.com/paper/2507.10195/) (2025)

## Abstract (arXiv)

Text-based person search aims to retrieve images of a certain pedestrian by a textual description. The key challenge of this task is to eliminate the inter-modality gap and achieve the feature alignment across modalities. In this paper, we propose a semantic-aligned embedding method for text-based person search, in which the feature alignment across modalities is achieved by automatically learning the semantic-aligned visual features and textual features. First, we introduce two Transformer-based backbones to encode robust feature representations of the images and texts. Second, we design a semantic-aligned feature aggregation network to adaptively select and aggregate features with the same semantics into part-aware features, which is achieved by a multi-head attention module constrained by a cross-modality part alignment loss and a diversity loss. Experimental results on the CUHK-PEDES and Flickr30K datasets show that our method achieves state-of-the-art performances.