{"total":347,"rows":[{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719,"area":null},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613,"area":null},{"id":"2306.03514","title":"Recognize Anything: A Strong Image Tagging Model","created":"2023-06-06","cited_by_count":309,"area":null},{"id":"2107.10834","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","created":"2021-07-22","cited_by_count":128,"area":null},{"id":"2101.05022","title":"Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels","created":"2021-01-13","cited_by_count":118,"area":null},{"id":"2206.09541","title":"DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations","created":"2022-06-20","cited_by_count":102,"area":null},{"id":"2304.02556","title":"Detecting and Grounding Multi-Modal Media Manipulation","created":"2023-04-05","cited_by_count":99,"area":null},{"id":"2205.01782","title":"Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition","created":"2022-05-02","cited_by_count":82,"area":null},{"id":"2111.12933","title":"ML-Decoder: Scalable and Versatile Classification Head","created":"2021-11-25","cited_by_count":79,"area":null},{"id":"2210.01033","title":"LPT: Long-tailed Prompt Tuning for Image Classification","created":"2022-10-03","cited_by_count":69,"area":null},{"id":"2310.15200","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","created":"2023-10-23","cited_by_count":67,"area":null},{"id":"2309.14203","title":"Detecting and Grounding Multi-Modal Media Manipulation and Beyond","created":"2023-09-25","cited_by_count":56,"area":null},{"id":"2108.02456","title":"Residual Attention: A Simple but Effective Method for Multi-Label Recognition","created":"2021-08-05","cited_by_count":52,"area":null},{"id":"2303.12080","title":"Natural Language-Assisted Sign Language Recognition","created":"2023-03-21","cited_by_count":46,"area":null},{"id":"2112.05230","title":"Injecting Semantic Concepts into End-to-End Image Captioning","created":"2021-12-09","cited_by_count":41,"area":null},{"id":"2307.16634","title":"CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification","created":"2023-07-31","cited_by_count":39,"area":null},{"id":"2204.08945","title":"Missingness Bias in Model Debugging","created":"2022-04-19","cited_by_count":38,"area":null},{"id":"2206.03740","title":"Large Loss Matters in Weakly Supervised Multi-Label Classification","created":"2022-06-08","cited_by_count":38,"area":null},{"id":"2510.17845","title":"MAT-Agent: Adaptive Multi-Agent Training Optimization","created":"2025-10-10","cited_by_count":35,"area":null},{"id":"2206.06930","title":"Comprehending and Ordering Semantics for Image Captioning","created":"2022-06-14","cited_by_count":33,"area":null},{"id":"2112.07368","title":"Simple and Robust Loss Design for Multi-Label Learning with Missing Labels","created":"2021-12-13","cited_by_count":30,"area":null},{"id":"2203.02172","title":"Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels","created":"2022-03-04","cited_by_count":29,"area":null},{"id":"2403.04697","title":"AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors","created":"2024-03-07","cited_by_count":29,"area":null},{"id":"2208.03354","title":"A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch","created":"2022-08-05","cited_by_count":28,"area":null},{"id":"2504.12880","title":"Can Masked Autoencoders Also Listen to Birds?","created":"2025-04-17","cited_by_count":26,"area":null},{"id":"2110.10955","title":"Multi-label Classification with Partial Annotations using Class-aware Selective Loss","created":"2021-10-21","cited_by_count":25,"area":null},{"id":"2105.05926","title":"Semantic Diversity Learning for Zero-Shot Multi-label Classification","created":"2021-05-12","cited_by_count":24,"area":null},{"id":"2203.16219","title":"Acknowledging the Unknown for Multi-label Learning with Single Positive Labels","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2108.10566","title":"sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification","created":"2021-08-24","cited_by_count":23,"area":null},{"id":"2308.01890","title":"DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotations","created":"2023-08-03","cited_by_count":22,"area":null},{"id":"2310.16112","title":"Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge","created":"2023-10-24","cited_by_count":22,"area":null},{"id":"2106.06195","title":"MlTr: Multi-label Classification with Transformer","created":"2021-06-11","cited_by_count":21,"area":null},{"id":"2303.14005","title":"Category Query Learning for Human-Object Interaction Classification","created":"2023-03-24","cited_by_count":21,"area":null},{"id":"2307.09066","title":"PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification","created":"2023-07-18","cited_by_count":21,"area":null},{"id":"2205.11131","title":"Heterogeneous Semantic Transfer for Multi-label Recognition with Partial Labels","created":"2022-05-23","cited_by_count":19,"area":null},{"id":"2207.02335","title":"Multi-Label Retinal Disease Classification using Transformers","created":"2022-07-05","cited_by_count":19,"area":null},{"id":"2304.07230","title":"PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition","created":"2023-04-14","cited_by_count":19,"area":null},{"id":"2312.12828","title":"TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training","created":"2023-12-20","cited_by_count":19,"area":null},{"id":"2107.11626","title":"Multi-Label Image Classification with Contrastive Learning","created":"2021-07-24","cited_by_count":18,"area":null},{"id":"2207.10273","title":"Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context","created":"2022-07-21","cited_by_count":18,"area":null},{"id":"2309.02120","title":"Multi-label affordance mapping from egocentric vision","created":"2023-09-05","cited_by_count":18,"area":null},{"id":"2103.10895","title":"Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark","created":"2021-03-19","cited_by_count":17,"area":null},{"id":"2203.06127","title":"Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations","created":"2022-03-11","cited_by_count":17,"area":null},{"id":"2211.10763","title":"PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection","created":"2022-11-19","cited_by_count":17,"area":null},{"id":"2304.10539","title":"Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels","created":"2023-04-20","cited_by_count":17,"area":null},{"id":"2312.16151","title":"Large-scale Long-tailed Disease Diagnosis on Radiology Images","created":"2023-12-26","cited_by_count":17,"area":null},{"id":"2502.18495","title":"A Comprehensive Survey on Composed Image Retrieval","created":"2025-02-19","cited_by_count":17,"area":null},{"id":"2508.19188","title":"FastMesh: Efficient Artistic Mesh Generation via Component Decoupling","created":"2025-08-26","cited_by_count":17,"area":null},{"id":"2305.02795","title":"Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning","created":"2023-05-04","cited_by_count":16,"area":null},{"id":"2112.00976","title":"Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification","created":"2021-12-02","cited_by_count":15,"area":null},{"id":"2305.04536","title":"LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition","created":"2023-05-08","cited_by_count":15,"area":null},{"id":"2407.17331","title":"Multi-label Cluster Discrimination for Visual Representation Learning","created":"2024-07-24","cited_by_count":14,"area":null},{"id":"2505.11152","title":"Learning Dense Hand Contact Estimation from Imbalanced Data","created":"2025-05-16","cited_by_count":14,"area":null},{"id":"2311.08223","title":"Improving Image Captioning via Predicting Structured Concepts","created":"2023-11-14","cited_by_count":13,"area":null},{"id":"2401.17910","title":"ControlCap: Controllable Region-level Captioning","created":"2024-01-31","cited_by_count":13,"area":null},{"id":"2110.05481","title":"Which Samples Should be Learned First: Easy or Hard?","created":"2021-10-11","cited_by_count":12,"area":null},{"id":"2209.13948","title":"Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2308.03968","title":"CheXFusion: Effective Fusion of Multi-View Features using Transformers for Long-Tailed Chest X-Ray Classification","created":"2023-08-08","cited_by_count":12,"area":null},{"id":"2407.04036","title":"Beyond Pixels: Semi-Supervised Semantic Segmentation with a Multi-scale Patch-based Multi-Label Classifier","created":"2024-07-04","cited_by_count":12,"area":null},{"id":"2203.04187","title":"RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation","created":"2022-03-08","cited_by_count":11,"area":null},{"id":"2304.01804","title":"Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification","created":"2023-04-04","cited_by_count":11,"area":null},{"id":"2310.10443","title":"Taming the Sigmoid Bottleneck: Provably Argmaxable Sparse Multi-Label Classification","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2312.07087","title":"Toward Robustness in Multi-label Classification: A Data Augmentation Strategy against Imbalance and Noise","created":"2023-12-12","cited_by_count":11,"area":null},{"id":"2102.08427","title":"Evaluating Multi-label Classifiers with Noisy Labels","created":"2021-02-16","cited_by_count":10,"area":null},{"id":"2111.08913","title":"Hierarchical Knowledge Guided Learning for Real-world Retinal Diseases Recognition","created":"2021-11-17","cited_by_count":10,"area":null},{"id":"2111.15340","title":"MC-SSL0.0: Towards Multi-Concept Self-Supervised Learning","created":"2021-11-30","cited_by_count":10,"area":null},{"id":"2207.06084","title":"Towards A Holistic View of Bias in Machine Learning: Bridging Algorithmic Fairness and Imbalanced Learning","created":"2022-07-13","cited_by_count":10,"area":null},{"id":"2309.02578","title":"Anatomy-Driven Pathology Detection on Chest X-rays","created":"2023-09-05","cited_by_count":10,"area":null},{"id":"2310.15985","title":"Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learning","created":"2023-10-24","cited_by_count":10,"area":null},{"id":"2404.10420","title":"AudioProtoPNet: An interpretable deep learning model for bird sound classification","created":"2024-04-16","cited_by_count":10,"area":null},{"id":"2506.07984","title":"CXR-LT 2024: A MICCAI challenge on long-tailed, multi-label, and zero-shot disease classification from chest X-ray","created":"2025-06-09","cited_by_count":10,"area":null},{"id":"2510.08177","title":"Long-tailed Recognition with Model Rebalancing","created":"2025-10-09","cited_by_count":10,"area":null},{"id":"2106.07220","title":"Context-Aware Image Inpainting with Learned Semantic Priors","created":"2021-06-14","cited_by_count":9,"area":null},{"id":"2109.00951","title":"GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps","created":"2021-09-02","cited_by_count":9,"area":null},{"id":"2203.01937","title":"BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification","created":"2022-03-03","cited_by_count":9,"area":null},{"id":"2207.03075","title":"Towards the Practical Utility of Federated Learning in the Medical Domain","created":"2022-07-07","cited_by_count":9,"area":null},{"id":"2210.01111","title":"MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples","created":"2022-10-03","cited_by_count":9,"area":null},{"id":"2212.00552","title":"An Effective Deployment of Contrastive Learning in Multi-label Text Classification","created":"2022-12-01","cited_by_count":9,"area":null},{"id":"2301.04850","title":"Understanding Difficulty-based Sample Weighting with a Universal Difficulty Measure","created":"2023-01-12","cited_by_count":9,"area":null},{"id":"2406.14830","title":"CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representation","created":"2024-06-21","cited_by_count":9,"area":null},{"id":"2407.18520","title":"Text-Region Matching for Multi-Label Image Recognition with Missing Labels","created":"2024-07-26","cited_by_count":9,"area":null},{"id":"2507.16343","title":"Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries","created":"2025-07-22","cited_by_count":9,"area":null},{"id":"2202.08978","title":"Cyclical Focal Loss","created":"2022-02-16","cited_by_count":8,"area":null},{"id":"2205.00476","title":"None Class Ranking Loss for Document-Level Relation Extraction","created":"2022-05-01","cited_by_count":8,"area":null},{"id":"2211.05232","title":"MuMIC -- Multimodal Embedding for Multi-label Image Classification with Tempered Sigmoid","created":"2022-11-02","cited_by_count":8,"area":null},{"id":"2304.11117","title":"A vector quantized masked autoencoder for speech emotion recognition","created":"2023-04-21","cited_by_count":8,"area":null},{"id":"2307.03967","title":"End-to-End Supervised Multilabel Contrastive Learning","created":"2023-07-08","cited_by_count":8,"area":null},{"id":"2308.05542","title":"Robust Asymmetric Loss for Multi-Label Long-Tailed Learning","created":"2023-08-10","cited_by_count":8,"area":null},{"id":"2310.01358","title":"NEUCORE: Neural Concept Reasoning for Composed Image Retrieval","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2404.06287","title":"Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training","created":"2024-04-09","cited_by_count":8,"area":null},{"id":"2109.02688","title":"Rethinking Crowdsourcing Annotation: Partial Annotation with Salient Labels for Multi-Label Image Classification","created":"2021-09-06","cited_by_count":7,"area":null},{"id":"2205.04227","title":"Mixed-UNet: Refined Class Activation Mapping for Weakly-Supervised Semantic Segmentation with Multi-scale Inference","created":"2022-05-06","cited_by_count":7,"area":null},{"id":"2302.13334","title":"Knowledge Restore and Transfer for Multi-label Class-Incremental Learning","created":"2023-02-26","cited_by_count":7,"area":null},{"id":"2304.11275","title":"Semantic-Aware Graph Matching Mechanism for Multi-Label Image Recognition","created":"2023-04-21","cited_by_count":7,"area":null},{"id":"2305.03568","title":"A vector quantized masked autoencoder for audiovisual speech emotion recognition","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2306.16016","title":"Positive Label Is All You Need for Multi-Label Classification","created":"2023-06-28","cited_by_count":7,"area":null},{"id":"2407.06298","title":"Multi-Label Plant Species Classification with Self-Supervised Vision Transformers","created":"2024-07-08","cited_by_count":7,"area":null},{"id":"2507.21778","title":"AU-LLM: Micro-Expression Action Unit Detection via Enhanced LLM-Based Feature Fusion","created":"2025-07-29","cited_by_count":7,"area":null},{"id":"2509.24901","title":"Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2204.03795","title":"Semantic Representation and Dependency Learning for Multi-Label Image Recognition","created":"2022-04-08","cited_by_count":6,"area":null}],"next_cursor":"100"}