{"total":34,"rows":[{"id":"2509.20354","title":"EmbeddingGemma: Powerful and Lightweight Text Representations","created":"2025-09-24","cited_by_count":139,"area":null},{"id":"2102.05644","title":"Training Vision Transformers for Image Retrieval","created":"2021-02-10","cited_by_count":90,"area":null},{"id":"2210.02192","title":"Are All Losses Created Equal: A Neural Collapse Perspective","created":"2022-10-04","cited_by_count":78,"area":null},{"id":"2602.15547","title":"jina-embeddings-v5-text: Task-Targeted Embedding Distillation","created":"2026-02-17","cited_by_count":22,"area":null},{"id":"2102.08427","title":"Evaluating Multi-label Classifiers with Noisy Labels","created":"2021-02-16","cited_by_count":10,"area":null},{"id":"2204.13208","title":"ELM: Embedding and Logit Margins for Long-Tail Learning","created":"2022-04-27","cited_by_count":10,"area":null},{"id":"2205.13655","title":"Mixed Federated Learning: Joint Decentralized and Centralized Learning","created":"2022-05-26","cited_by_count":8,"area":null},{"id":"2108.09335","title":"LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning","created":"2021-08-20","cited_by_count":7,"area":null},{"id":"2401.12012","title":"TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clients","created":"2024-01-22","cited_by_count":7,"area":null},{"id":"2506.04619","title":"Deep Learning Reforms Image Matching: A Survey and Outlook","created":"2025-06-05","cited_by_count":7,"area":null},{"id":"2108.07931","title":"Learning Federated Representations and Recommendations with Limited Negatives","created":"2021-08-18","cited_by_count":6,"area":null},{"id":"2106.04434","title":"SDGMNet: Statistic-based Dynamic Gradient Modulation for Local Descriptor Learning","created":"2021-06-08","cited_by_count":5,"area":null},{"id":"2311.03904","title":"RobustMat: Neural Diffusion for Street Landmark Patch Matching under Challenging Environments","created":"2023-11-07","cited_by_count":5,"area":null},{"id":"2311.04617","title":"Image Patch-Matching with Graph-Based Learning in Street Scenes","created":"2023-11-08","cited_by_count":5,"area":null},{"id":"2404.01616","title":"Transforming LLMs into Cross-modal and Cross-lingual Retrieval Systems","created":"2024-04-02","cited_by_count":5,"area":null},{"id":"2106.07916","title":"Encouraging Intra-Class Diversity Through a Reverse Contrastive Loss for Better Single-Source Domain Generalization","created":"2021-06-15","cited_by_count":4,"area":null},{"id":"2308.01547","title":"Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class Representation","created":"2023-08-03","cited_by_count":3,"area":null},{"id":"2205.00224","title":"Loss Function Entropy Regularization for Diverse Decision Boundaries","created":"2022-04-30","cited_by_count":2,"area":null},{"id":"2305.12843","title":"Registering Neural Radiance Fields as 3D Density Images","created":"2023-05-22","cited_by_count":2,"area":null},{"id":"2307.05974","title":"Contrastive Learning for Conversion Rate Prediction","created":"2023-07-12","cited_by_count":2,"area":null},{"id":"2403.11751","title":"Relational Representation Learning Network for Cross-Spectral Image Patch Matching","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2412.11161","title":"Why and How: Knowledge-Guided Learning for Cross-Spectral Image Patch Matching","created":"2024-12-15","cited_by_count":2,"area":null},{"id":"2608.25768","title":"MoganBert-TR: A Turkish Encoder Foundation Model Trained from Scratch with a CLM-to-MLM Curriculum","created":"2026-08-26","cited_by_count":2,"area":null},{"id":"2201.11307","title":"Dissecting the impact of different loss functions with gradient surgery","created":"2022-01-27","cited_by_count":1,"area":null},{"id":"2507.04233","title":"Grid-Reg: Detector-Free Gridized Feature Learning and Matching for Large-Scale SAR-Optical Image Registration","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2103.02770","title":"SVMax: A Feature Embedding Regularizer","created":"2021-03-04","cited_by_count":0,"area":null},{"id":"2103.11247","title":"Attention-Based Multimodal Image Matching","created":"2021-03-20","cited_by_count":0,"area":null},{"id":"2103.13443","title":"Blind Speech Separation and Dereverberation using Neural Beamforming","created":"2021-03-24","cited_by_count":0,"area":null},{"id":"2111.05485","title":"A Structure Feature Algorithm for Multi-modal Forearm Registration","created":"2021-11-10","cited_by_count":0,"area":null},{"id":"2204.10972","title":"GRM: Gradient Rectification Module for Visual Place Retrieval","created":"2022-04-23","cited_by_count":0,"area":null},{"id":"2206.10737","title":"Deep Metric Color Embeddings for Splicing Localization in Severely Degraded Images","created":"2022-06-21","cited_by_count":0,"area":null},{"id":"2310.03104","title":"Differentially Private Optimization for Non-Decomposable Objective Functions","created":"2023-10-04","cited_by_count":0,"area":null},{"id":"2608.12145","title":"Autonomous Telerehabilitation via Skeletal Motion Prediction and Joint-Level Performance Assessment","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.26344","title":"MoganColBERT-TR: A Late-Interaction Multi-Vector Retrieval Model for Turkish","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}