{"total":145,"rows":[{"id":"2303.12501","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","created":"2023-03-22","cited_by_count":132,"area":"lr"},{"id":"2101.00529","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","created":"2021-01-02","cited_by_count":110,"area":"mllm"},{"id":"2107.12666","title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification","created":"2021-07-27","cited_by_count":110,"area":null},{"id":"2109.05534","title":"DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval","created":"2021-09-12","cited_by_count":102,"area":null},{"id":"2210.10276","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","created":"2022-10-19","cited_by_count":79,"area":null},{"id":"2306.02898","title":"Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark","created":"2023-06-05","cited_by_count":75,"area":null},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2208.08608","title":"See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval","created":"2022-08-18","cited_by_count":65,"area":null},{"id":"2101.03036","title":"Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search","created":"2021-01-08","cited_by_count":62,"area":null},{"id":"2207.07802","title":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification","created":"2022-07-16","cited_by_count":62,"area":null},{"id":"2105.11628","title":"TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search","created":"2021-05-25","cited_by_count":57,"area":null},{"id":"2201.09206","title":"A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization","created":"2022-01-23","cited_by_count":57,"area":null},{"id":"2308.09911","title":"Noisy-Correspondence Learning for Text-to-Image Person Re-identification","created":"2023-08-19","cited_by_count":56,"area":null},{"id":"2203.14713","title":"Image-text Retrieval: A Survey on Recent Research and Development","created":"2022-03-28","cited_by_count":55,"area":null},{"id":"2110.10807","title":"Text-Based Person Search with Limited Data","created":"2021-10-20","cited_by_count":54,"area":null},{"id":"2305.13653","title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search","created":"2023-05-23","cited_by_count":54,"area":null},{"id":"2305.08386","title":"PLIP: Language-Image Pre-training for Person Representation Learning","created":"2023-05-15","cited_by_count":49,"area":null},{"id":"2201.09201","title":"Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments","created":"2022-01-23","cited_by_count":46,"area":null},{"id":"2306.07520","title":"Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions","created":"2023-06-13","cited_by_count":46,"area":null},{"id":"2211.07394","title":"Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization","created":"2022-11-14","cited_by_count":45,"area":null},{"id":"2311.12751","title":"Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching","created":"2023-11-21","cited_by_count":42,"area":null},{"id":"2112.06714","title":"Learning Semantic-Aligned Feature Representation for Text-based Person Search","created":"2021-12-13","cited_by_count":40,"area":null},{"id":"2209.05773","title":"CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrieval","created":"2022-09-13","cited_by_count":39,"area":null},{"id":"2208.14365","title":"Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Search","created":"2022-08-30","cited_by_count":38,"area":null},{"id":"2209.06209","title":"Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifold","created":"2022-09-13","cited_by_count":38,"area":null},{"id":"2308.10045","title":"An Empirical Study of CLIP for Text-based Person Search","created":"2023-08-19","cited_by_count":38,"area":null},{"id":"2412.17007","title":"Where am I? Cross-View Geo-localization with Natural Language Descriptions","created":"2024-12-22","cited_by_count":38,"area":null},{"id":"2204.08381","title":"Multiple-environment Self-adaptive Network for Aerial-view Geo-localization","created":"2022-04-18","cited_by_count":37,"area":null},{"id":"2101.08238","title":"AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification","created":"2021-01-19","cited_by_count":34,"area":null},{"id":"2509.12662","title":"Chat-Driven Text Generation and Interaction for Person Retrieval","created":"2025-09-16","cited_by_count":34,"area":null},{"id":"2312.03441","title":"UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity","created":"2023-12-06","cited_by_count":30,"area":null},{"id":"2103.11920","title":"Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval","created":"2021-03-22","cited_by_count":28,"area":null},{"id":"2402.10805","title":"Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond","created":"2024-02-16","cited_by_count":28,"area":"mllm"},{"id":"2112.03162","title":"Embedding Arithmetic of Multimodal Queries for Image Retrieval","created":"2021-12-06","cited_by_count":21,"area":null},{"id":"2309.01420","title":"Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification","created":"2023-09-04","cited_by_count":19,"area":null},{"id":"2212.11958","title":"Asymmetric Cross-Scale Alignment for Text-Based Person Search","created":"2022-11-26","cited_by_count":18,"area":null},{"id":"2211.05296","title":"Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularization","created":"2022-11-10","cited_by_count":17,"area":null},{"id":"2305.12964","title":"Text-based Person Search without Parallel Image-Text Data","created":"2023-05-22","cited_by_count":17,"area":null},{"id":"2411.13610","title":"Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localization","created":"2024-11-20","cited_by_count":17,"area":null},{"id":"2205.10878","title":"Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval","created":"2022-05-22","cited_by_count":16,"area":null},{"id":"2210.08908","title":"Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval","created":"2022-10-17","cited_by_count":14,"area":null},{"id":"2301.09498","title":"Triplet Contrastive Representation Learning for Unsupervised Vehicle Re-identification","created":"2023-01-23","cited_by_count":14,"area":null},{"id":"2306.02092","title":"Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations","created":"2023-06-03","cited_by_count":14,"area":null},{"id":"2404.10292","title":"From Data Deluge to Data Curation: A Filtering-WoRA Paradigm for Efficient Text-based Person Search","created":"2024-04-16","cited_by_count":14,"area":null},{"id":"2105.14897","title":"Connecting Language and Vision for Natural Language-Based Vehicle Retrieval","created":"2021-05-31","cited_by_count":12,"area":null},{"id":"2108.01578","title":"SPG-VTON: Semantic Prediction Guidance for Multi-pose Virtual Try-on","created":"2021-08-03","cited_by_count":12,"area":null},{"id":"2311.07514","title":"VGSG: Vision-Guided Semantic-Group Network for Text-based Person Search","created":"2023-11-13","cited_by_count":11,"area":null},{"id":"2411.17776","title":"Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Search","created":"2024-11-26","cited_by_count":11,"area":null},{"id":"2505.06566","title":"Dynamic Uncertainty Learning with Noisy Correspondence for Text-Based Person Search","created":"2025-05-10","cited_by_count":11,"area":null},{"id":"2306.08789","title":"Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training","created":"2023-06-15","cited_by_count":10,"area":null},{"id":"2309.09496","title":"CLIP-based Synergistic Knowledge Transfer for Text-based Person Retrieval","created":"2023-09-18","cited_by_count":10,"area":null},{"id":"2109.12965","title":"Text-based Person Search in Full Images via Semantic-Driven Proposal Generation","created":"2021-09-27","cited_by_count":9,"area":null},{"id":"2201.05820","title":"Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification","created":"2022-01-15","cited_by_count":9,"area":null},{"id":"2304.12570","title":"Learnable Pillar-based Re-ranking for Image-Text Retrieval","created":"2023-04-25","cited_by_count":9,"area":null},{"id":"2511.22470","title":"Hybrid, Unified and Iterative: A Novel Framework for Text-based Person Anomaly Retrieval","created":"2025-11-27","cited_by_count":9,"area":null},{"id":"2104.10406","title":"Discrete-continuous Action Space Policy Gradient-based Attention for Image-Text Matching","created":"2021-04-21","cited_by_count":8,"area":null},{"id":"2109.00452","title":"Self-supervised Point Cloud Representation Learning via Separating Mixed Shapes","created":"2021-09-01","cited_by_count":8,"area":null},{"id":"2308.04343","title":"Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval","created":"2023-08-08","cited_by_count":8,"area":null},{"id":"2309.04675","title":"BiLMa: Bidirectional Local-Matching for Text-based Person Re-identification","created":"2023-09-09","cited_by_count":8,"area":null},{"id":"2311.09084","title":"Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search","created":"2023-11-15","cited_by_count":8,"area":null},{"id":"2303.04497","title":"Exploiting the Textual Potential from Vision-Language Pre-training for Text-based Person Search","created":"2023-03-08","cited_by_count":7,"area":"mllm"},{"id":"2310.11210","title":"Learning Comprehensive Representations with Richer Self for Text-to-Image Person Re-Identification","created":"2023-10-17","cited_by_count":7,"area":null},{"id":"2412.03910","title":"DGNS: Deformable Gaussian Splatting and Dynamic Neural Surface for Monocular Dynamic 3D Reconstruction","created":"2024-12-05","cited_by_count":7,"area":null},{"id":"2508.09560","title":"WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization","created":"2025-08-13","cited_by_count":7,"area":null},{"id":"2104.04991","title":"Integrating Information Theory and Adversarial Learning for Cross-modal Retrieval","created":"2021-04-11","cited_by_count":6,"area":null},{"id":"2105.01605","title":"Person Search Challenges and Solutions: A Survey","created":"2021-05-01","cited_by_count":6,"area":null},{"id":"2106.02400","title":"A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval","created":"2021-06-04","cited_by_count":6,"area":null},{"id":"2110.11338","title":"VLDeformer: Vision-Language Decomposed Transformer for Fast Cross-Modal Retrieval","created":"2021-10-20","cited_by_count":6,"area":null},{"id":"2211.03434","title":"Complete Cross-triplet Loss in Label Space for Audio-visual Cross-modal Retrieval","created":"2022-11-07","cited_by_count":6,"area":null},{"id":"2309.15494","title":"VideoAdviser: Video Knowledge Distillation for Multimodal Transfer Learning","created":"2023-09-27","cited_by_count":6,"area":"distill"},{"id":"2407.17274","title":"Revolutionizing Text-to-Image Retrieval as Autoregressive Token-to-Voken Generation","created":"2024-07-24","cited_by_count":6,"area":null},{"id":"2504.07718","title":"Multi-modal Reference Learning for Fine-grained Text-to-Image Retrieval","created":"2025-04-10","cited_by_count":6,"area":null},{"id":"2504.18782","title":"CAMeL: Cross-modality Adaptive Meta-Learning for Text-based Person Retrieval","created":"2025-04-26","cited_by_count":6,"area":null},{"id":"2309.02169","title":"Dual Relation Alignment for Composed Image Retrieval","created":"2023-09-05","cited_by_count":5,"area":null},{"id":"2312.01745","title":"Cross-Modal Adaptive Dual Association for Text-to-Image Person Retrieval","created":"2023-12-04","cited_by_count":5,"area":null},{"id":"2405.17790","title":"Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-identification","created":"2024-05-28","cited_by_count":5,"area":null},{"id":"2406.05620","title":"Beat: Bi-directional One-to-Many Embedding Alignment for Text-based Person Retrieval","created":"2024-06-09","cited_by_count":5,"area":null},{"id":"2408.00096","title":"From Attributes to Natural Language: A Survey and Foresight on Text-based Person Re-identification","created":"2024-07-31","cited_by_count":5,"area":null},{"id":"2304.06297","title":"ALR-GAN: Adaptive Layout Refinement for Text-to-Image Synthesis","created":"2023-04-13","cited_by_count":4,"area":null},{"id":"2305.04497","title":"IIITD-20K: Dense captioning for Text-Image ReID","created":"2023-05-08","cited_by_count":4,"area":null},{"id":"2310.13451","title":"Two-Stage Triplet Loss Training with Curriculum Augmentation for Audio-Visual Retrieval","created":"2023-10-20","cited_by_count":4,"area":null},{"id":"2404.13789","title":"Anchor-aware Deep Metric Learning for Audio-visual Retrieval","created":"2024-04-21","cited_by_count":4,"area":null},{"id":"2404.18106","title":"Semi-supervised Text-based Person Search","created":"2024-04-28","cited_by_count":4,"area":null},{"id":"2412.15106","title":"Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2509.04376","title":"AnomalyLMM: Bridging Generative Knowledge and Discriminative Retrieval for Text-Based Person Anomaly Search","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2509.09118","title":"Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval","created":"2025-09-11","cited_by_count":4,"area":null},{"id":"2604.23282","title":"Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search","created":"2026-04-25","cited_by_count":4,"area":null},{"id":"2204.08209","title":"OMG: Observe Multiple Granularities for Natural Language-Based Vehicle Retrieval","created":"2022-04-18","cited_by_count":3,"area":null},{"id":"2206.06404","title":"Compositional Mixture Representations for Vision and Text","created":"2022-06-13","cited_by_count":3,"area":null},{"id":"2211.08657","title":"Person Text-Image Matching via Text-Feature Interpretability Embedding and External Attack Node Implantation","created":"2022-11-16","cited_by_count":3,"area":null},{"id":"2306.14460","title":"Hierarchical Matching and Reasoning for Multi-Query Image Retrieval","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2309.08154","title":"Dynamic Visual Semantic Sub-Embeddings and Fast Re-Ranking","created":"2023-09-15","cited_by_count":3,"area":null},{"id":"2406.10845","title":"LAIP: Learning Local Alignment from Image-Phrase Modeling for Text-based Person Search","created":"2024-06-16","cited_by_count":3,"area":null},{"id":"2412.20646","title":"Enhancing Visual Representation for Text-based Person Searching","created":"2024-12-30","cited_by_count":3,"area":null},{"id":"2507.10195","title":"Minimizing the Pretraining Gap: Domain-aligned Text-Based Person Retrieval","created":"2025-07-14","cited_by_count":3,"area":null},{"id":"2508.02384","title":"SMART-Ship: A Comprehensive Synchronized Multi-modal Aligned Remote Sensing Targets Dataset and Benchmark for Berthed Ships Analysis","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2104.02605","title":"An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information","created":"2021-03-21","cited_by_count":2,"area":null},{"id":"2106.01764","title":"Less is More: Sparse Sampling for Dense Reaction Predictions","created":"2021-06-03","cited_by_count":2,"area":null},{"id":"2204.09268","title":"Uncertainty-based Cross-Modal Retrieval with Probabilistic Representations","created":"2022-04-20","cited_by_count":2,"area":null},{"id":"2303.00181","title":"Selectively Hard Negative Mining for Alleviating Gradient Vanishing in Image-Text Matching","created":"2023-03-01","cited_by_count":2,"area":null}],"next_cursor":"100"}