{"total":117,"rows":[{"id":"2306.03514","title":"Recognize Anything: A Strong Image Tagging Model","created":"2023-06-06","cited_by_count":309,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"area":null},{"id":"2111.12933","title":"ML-Decoder: Scalable and Versatile Classification Head","created":"2021-11-25","cited_by_count":79,"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":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59,"area":null},{"id":"2302.09923","title":"Prompt Stealing Attacks Against Text-to-Image Generation Models","created":"2023-02-20","cited_by_count":51,"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":"2403.12960","title":"FaceXFormer: A Unified Transformer for Facial Analysis","created":"2024-03-19","cited_by_count":34,"area":null},{"id":"2207.01887","title":"Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer","created":"2022-07-05","cited_by_count":33,"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":"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":"2207.08677","title":"Label2Label: A Language Modeling Framework for Multi-Attribute Learning","created":"2022-07-18","cited_by_count":23,"area":null},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"area":null},{"id":"2404.18279","title":"Out-of-distribution Detection in Medical Image Analysis: A survey","created":"2024-04-28","cited_by_count":22,"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":"2401.16549","title":"Deep Learning for Multi-Label Learning: A Comprehensive Survey","created":"2024-01-29","cited_by_count":19,"area":null},{"id":"2309.02120","title":"Multi-label affordance mapping from egocentric vision","created":"2023-09-05","cited_by_count":18,"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":"2208.12398","title":"Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classification","created":"2022-08-26","cited_by_count":16,"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":"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":"2401.17910","title":"ControlCap: Controllable Region-level Captioning","created":"2024-01-31","cited_by_count":13,"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":"2312.02142","title":"Object Recognition as Next Token Prediction","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2501.09333","title":"Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis","created":"2025-01-16","cited_by_count":12,"area":null},{"id":"2203.04049","title":"Graph Attention Transformer Network for Multi-Label Image Classification","created":"2022-03-08","cited_by_count":11,"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":"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":"2111.15340","title":"MC-SSL0.0: Towards Multi-Concept Self-Supervised Learning","created":"2021-11-30","cited_by_count":10,"area":null},{"id":"2203.12531","title":"Multi-label Transformer for Action Unit Detection","created":"2022-03-23","cited_by_count":9,"area":null},{"id":"2207.10379","title":"Temporal Saliency Query Network for Efficient Video Recognition","created":"2022-07-21","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":"2407.08027","title":"Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images","created":"2024-07-10","cited_by_count":9,"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":"2307.09715","title":"Semantic-Aware Dual Contrastive Learning for Multi-label Image Classification","created":"2023-07-19","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":"2302.13334","title":"Knowledge Restore and Transfer for Multi-label Class-Incremental Learning","created":"2023-02-26","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":"2412.05029","title":"Mixed Blessing: Class-Wise Embedding guided Instance-Dependent Partial Label Learning","created":"2024-12-06","cited_by_count":7,"area":null},{"id":"2208.09562","title":"Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features","created":"2022-08-19","cited_by_count":6,"area":null},{"id":"2304.05634","title":"How you feelin'? Learning Emotions and Mental States in Movie Scenes","created":"2023-04-12","cited_by_count":6,"area":null},{"id":"2410.03302","title":"Action Selection Learning for Multi-label Multi-view Action Recognition","created":"2024-10-04","cited_by_count":6,"area":null},{"id":"2503.15337","title":"Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2511.21519","title":"Self-Paced Learning for Images of Antinuclear Antibodies","created":"2025-11-26","cited_by_count":6,"area":null},{"id":"2207.02410","title":"A Deep Model for Partial Multi-Label Image Classification with Curriculum Based Disambiguation","created":"2022-07-06","cited_by_count":5,"area":null},{"id":"2304.03580","title":"Language-aware Multiple Datasets Detection Pretraining for DETRs","created":"2023-04-07","cited_by_count":5,"area":null},{"id":"2405.09059","title":"Task-adaptive Q-Face","created":"2024-05-15","cited_by_count":5,"area":null},{"id":"2408.08125","title":"Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image Classification","created":"2024-08-15","cited_by_count":5,"area":null},{"id":"2209.06585","title":"Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classification","created":"2022-09-14","cited_by_count":4,"area":null},{"id":"2303.00952","title":"Towards Activated Muscle Group Estimation in the Wild","created":"2023-03-02","cited_by_count":4,"area":null},{"id":"2311.15200","title":"SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classification","created":"2023-11-26","cited_by_count":4,"area":null},{"id":"2403.07246","title":"Towards Zero-shot Human-Object Interaction Detection via Vision-Language Integration","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2510.17520","title":"Curiosity Meets Cooperation: A Game-Theoretic Approach to Long-Tail Multi-Label Learning","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2208.14439","title":"Self-Supervised Pyramid Representation Learning for Multi-Label Visual Analysis and Beyond","created":"2022-08-30","cited_by_count":3,"area":null},{"id":"2209.15402","title":"Rethinking the Learning Paradigm for Facial Expression Recognition","created":"2022-09-30","cited_by_count":3,"area":null},{"id":"2211.02629","title":"Multi-view Multi-label Fine-grained Emotion Decoding from Human Brain Activity","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2306.01232","title":"Deep Reinforcement Learning Framework for Thoracic Diseases Classification via Prior Knowledge Guidance","created":"2023-06-02","cited_by_count":3,"area":null},{"id":"2308.14378","title":"GKGNet: Group K-Nearest Neighbor based Graph Convolutional Network for Multi-Label Image Recognition","created":"2023-08-28","cited_by_count":3,"area":null},{"id":"2311.07263","title":"LT-ViT: A Vision Transformer for multi-label Chest X-ray classification","created":"2023-11-13","cited_by_count":3,"area":null},{"id":"2312.07165","title":"Language-Guided Transformer for Federated Multi-Label Classification","created":"2023-12-12","cited_by_count":3,"area":null},{"id":"2405.16071","title":"DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2407.16244","title":"HSVLT: Hierarchical Scale-Aware Vision-Language Transformer for Multi-Label Image Classification","created":"2024-07-23","cited_by_count":3,"area":null},{"id":"2412.00101","title":"Multi-Label Contrastive Learning : A Comprehensive Study","created":"2024-11-27","cited_by_count":3,"area":null},{"id":"2412.03796","title":"Automated Multi-Label Annotation for Mental Health Illnesses Using Large Language Models","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2509.15553","title":"Diffusion-Based Cross-Modal Feature Extraction for Multi-Label Classification","created":"2025-09-19","cited_by_count":3,"area":null},{"id":"2306.10079","title":"M3PT: A Multi-Modal Model for POI Tagging","created":"2023-06-16","cited_by_count":2,"area":null},{"id":"2312.03119","title":"AI-SAM: Automatic and Interactive Segment Anything Model","created":"2023-12-05","cited_by_count":2,"area":null},{"id":"2401.17881","title":"PVLR: Prompt-driven Visual-Linguistic Representation Learning for Multi-Label Image Recognition","created":"2024-01-31","cited_by_count":2,"area":null},{"id":"2402.02377","title":"NOAH: Learning Pairwise Object Category Attentions for Image Classification","created":"2024-02-04","cited_by_count":2,"area":null},{"id":"2404.07245","title":"Generative Resident Separation and Multi-label Classification for Multi-person Activity Recognition","created":"2024-04-10","cited_by_count":2,"area":null},{"id":"2407.20920","title":"SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition","created":"2024-07-30","cited_by_count":2,"area":null},{"id":"2408.15566","title":"TagOOD: A Novel Approach to Out-of-Distribution Detection via Vision-Language Representations and Class Center Learning","created":"2024-08-28","cited_by_count":2,"area":null},{"id":"2501.05644","title":"Interpretable Enzyme Function Prediction via Residue-Level Detection","created":"2025-01-10","cited_by_count":2,"area":null},{"id":"2503.00515","title":"Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2509.12544","title":"Neural Collapse-Inspired Multi-Label Federated Learning under Label-Distribution Skew","created":"2025-09-16","cited_by_count":2,"area":null},{"id":"2509.17747","title":"Dual-View Alignment Learning with Hierarchical-Prompt for Class-Imbalance Multi-Label Classification","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2302.00633","title":"Deep Dependency Networks for Multi-Label Classification","created":"2023-02-01","cited_by_count":1,"area":null},{"id":"2310.18517","title":"Learning to recognize occluded and small objects with partial inputs","created":"2023-10-27","cited_by_count":1,"area":null},{"id":"2403.07603","title":"ProPML: Probability Partial Multi-label Learning","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2503.18430","title":"CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection","created":"2025-03-24","cited_by_count":1,"area":null},{"id":"2504.18201","title":"Multi-Grained Compositional Visual Clue Learning for Image Intent Recognition","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2505.24703","title":"PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2510.20393","title":"Mitigating Cross-modal Representation Bias for Multicultural Image-to-Recipe Retrieval","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2512.23486","title":"Multi-label Classification with Panoptic Context Aggregation Networks","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2604.15555","title":"CXR-LT 2026 Challenge: Multi-Center Long-Tailed and Zero Shot Chest X-ray Classification","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2204.09134","title":"Diverse Imagenet Models Transfer Better","created":"2022-04-19","cited_by_count":0,"area":null},{"id":"2210.14147","title":"Food Ingredients Recognition through Multi-label Learning","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2302.14487","title":"Enhancing Classification with Hierarchical Scalable Query on Fusion Transformer","created":"2023-02-28","cited_by_count":0,"area":null},{"id":"2306.10034","title":"Unlocking Insights into Business Trajectories with Transformer-based Spatio-temporal Data Analysis","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2308.13801","title":"Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class Discovery","created":"2023-08-26","cited_by_count":0,"area":null},{"id":"2310.07510","title":"Heuristic Vision Pre-Training with Self-Supervised and Supervised Multi-Task Learning","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2404.11667","title":"Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification","created":"2024-04-17","cited_by_count":0,"area":null},{"id":"2405.15633","title":"Less is more: Summarizing Patch Tokens for efficient Multi-Label Class-Incremental Learning","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2405.20600","title":"Multi-label Class Incremental Emotion Decoding with Augmented Emotional Semantics Learning","created":"2024-05-31","cited_by_count":0,"area":null}],"next_cursor":"100"}