{"total":215,"rows":[{"id":"2111.06119","title":"Fine-Grained Image Analysis with Deep Learning: A Survey","created":"2021-11-11","cited_by_count":135,"area":null},{"id":"2111.15000","title":"Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes","created":"2021-11-29","cited_by_count":120,"area":null},{"id":"2304.02211","title":"METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens","created":"2023-04-05","cited_by_count":101,"area":null},{"id":"2209.08290","title":"Changer: Feature Interaction is What You Need for Change Detection","created":"2022-09-17","cited_by_count":79,"area":null},{"id":"2104.03059","title":"Differentiable Patch Selection for Image Recognition","created":"2021-04-07","cited_by_count":68,"area":null},{"id":"2111.06349","title":"Unsupervised Part Discovery from Contrastive Reconstruction","created":"2021-11-11","cited_by_count":57,"area":null},{"id":"2109.07036","title":"PnP-DETR: Towards Efficient Visual Analysis with Transformers","created":"2021-09-15","cited_by_count":52,"area":null},{"id":"2208.10358","title":"A Medical Semantic-Assisted Transformer for Radiographic Report Generation","created":"2022-08-22","cited_by_count":44,"area":null},{"id":"2105.06220","title":"VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations","created":"2021-05-13","cited_by_count":40,"area":null},{"id":"2301.04011","title":"Learning Support and Trivial Prototypes for Interpretable Image Classification","created":"2023-01-08","cited_by_count":38,"area":null},{"id":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37,"area":null},{"id":"2102.09717","title":"Continual Learning for Blind Image Quality Assessment","created":"2021-02-19","cited_by_count":36,"area":null},{"id":"2107.04768","title":"DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering","created":"2021-07-10","cited_by_count":35,"area":null},{"id":"2107.08192","title":"RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition","created":"2021-07-17","cited_by_count":34,"area":null},{"id":"2108.02399","title":"Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach","created":"2021-08-05","cited_by_count":32,"area":null},{"id":"2210.01439","title":"Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment","created":"2022-10-04","cited_by_count":29,"area":null},{"id":"2203.02751","title":"MetaFormer: A Unified Meta Framework for Fine-Grained Recognition","created":"2022-03-05","cited_by_count":28,"area":null},{"id":"2103.10107","title":"Danish Fungi 2020 -- Not Just Another Image Recognition Dataset","created":"2021-03-18","cited_by_count":27,"area":null},{"id":"2112.06183","title":"Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species","created":"2021-12-12","cited_by_count":27,"area":null},{"id":"2204.13349","title":"Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor","created":"2022-04-28","cited_by_count":27,"area":null},{"id":"2401.13837","title":"Democratizing Fine-grained Visual Recognition with Large Language Models","created":"2024-01-24","cited_by_count":25,"area":null},{"id":"2105.02498","title":"Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling?","created":"2021-05-06","cited_by_count":24,"area":null},{"id":"2202.05613","title":"CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning","created":"2022-02-11","cited_by_count":24,"area":null},{"id":"2203.15987","title":"Fine-Grained Object Classification via Self-Supervised Pose Alignment","created":"2022-03-30","cited_by_count":22,"area":null},{"id":"2306.04670","title":"Object Detection with Transformers: A Review","created":"2023-06-07","cited_by_count":22,"area":null},{"id":"2201.08029","title":"Domain Generalization via Frequency-domain-based Feature Disentanglement and Interaction","created":"2022-01-20","cited_by_count":21,"area":null},{"id":"2104.03821","title":"Robust Differentiable SVD","created":"2021-04-08","cited_by_count":19,"area":null},{"id":"2309.00399","title":"Fine-grained Recognition with Learnable Semantic Data Augmentation","created":"2023-09-01","cited_by_count":17,"area":null},{"id":"2506.00343","title":"The iNaturalist Sounds Dataset","created":"2025-05-31","cited_by_count":17,"area":null},{"id":"2201.12543","title":"Fast Differentiable Matrix Square Root and Inverse Square Root","created":"2022-01-29","cited_by_count":16,"area":null},{"id":"2204.04654","title":"Fashionformer: A simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition","created":"2022-04-10","cited_by_count":16,"area":null},{"id":"2308.05396","title":"Learning Gabor Texture Features for Fine-Grained Recognition","created":"2023-08-10","cited_by_count":16,"area":null},{"id":"2207.12389","title":"MemSAC: Memory Augmented Sample Consistency for Large Scale Unsupervised Domain Adaptation","created":"2022-07-25","cited_by_count":15,"area":null},{"id":"2107.01671","title":"Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory","created":"2021-07-04","cited_by_count":14,"area":null},{"id":"2201.08663","title":"Fast Differentiable Matrix Square Root","created":"2022-01-21","cited_by_count":14,"area":null},{"id":"2303.01669","title":"Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems","created":"2023-03-03","cited_by_count":14,"area":null},{"id":"2103.13559","title":"Rethinking Self-Supervised Learning: Small is Beautiful","created":"2021-03-25","cited_by_count":13,"area":null},{"id":"2209.01339","title":"DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation","created":"2022-09-03","cited_by_count":13,"area":null},{"id":"2108.02924","title":"Interpretable Visual Understanding with Cognitive Attention Network","created":"2021-08-06","cited_by_count":12,"area":null},{"id":"2108.13122","title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","created":"2021-08-30","cited_by_count":12,"area":null},{"id":"2109.10986","title":"An Efficient and Scalable Collection of Fly-inspired Voting Units for Visual Place Recognition in Changing Environments","created":"2021-09-22","cited_by_count":12,"area":null},{"id":"2201.05916","title":"Multi-level Second-order Few-shot Learning","created":"2022-01-15","cited_by_count":12,"area":null},{"id":"2201.08712","title":"Improved Random Features for Dot Product Kernels","created":"2022-01-21","cited_by_count":12,"area":null},{"id":"2206.05184","title":"SERE: Exploring Feature Self-relation for Self-supervised Transformer","created":"2022-06-10","cited_by_count":12,"area":null},{"id":"2208.00617","title":"Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism","created":"2022-08-01","cited_by_count":12,"area":null},{"id":"2209.01542","title":"Recurrent Bilinear Optimization for Binary Neural Networks","created":"2022-09-04","cited_by_count":12,"area":null},{"id":"2303.04554","title":"RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps","created":"2023-03-08","cited_by_count":12,"area":null},{"id":"2102.09875","title":"Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition","created":"2021-02-19","cited_by_count":11,"area":null},{"id":"2109.08890","title":"Towards Joint Intent Detection and Slot Filling via Higher-order Attention","created":"2021-09-18","cited_by_count":11,"area":null},{"id":"2110.14381","title":"Temporal-attentive Covariance Pooling Networks for Video Recognition","created":"2021-10-27","cited_by_count":11,"area":null},{"id":"2109.11159","title":"OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification","created":"2021-09-23","cited_by_count":10,"area":null},{"id":"2205.13282","title":"On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition","created":"2022-05-26","cited_by_count":10,"area":null},{"id":"2106.12832","title":"Detection of Deepfake Videos Using Long Distance Attention","created":"2021-06-24","cited_by_count":9,"area":null},{"id":"2304.03147","title":"Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions","created":"2023-04-06","cited_by_count":9,"area":null},{"id":"2307.11342","title":"Tuning Pre-trained Model via Moment Probing","created":"2023-07-21","cited_by_count":9,"area":null},{"id":"2407.10484","title":"Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry","created":"2024-07-15","cited_by_count":9,"area":null},{"id":"2108.13098","title":"Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification","created":"2021-08-30","cited_by_count":8,"area":null},{"id":"2205.10529","title":"Fine-Grained Visual Classification using Self Assessment Classifier","created":"2022-05-21","cited_by_count":8,"area":null},{"id":"2207.03824","title":"Boosting Zero-shot Learning via Contrastive Optimization of Attribute Representations","created":"2022-07-08","cited_by_count":8,"area":null},{"id":"2108.04628","title":"Learning Canonical 3D Object Representation for Fine-Grained Recognition","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2203.11449","title":"How well does CLIP understand texture?","created":"2022-03-22","cited_by_count":7,"area":null},{"id":"2212.13685","title":"Part-guided Relational Transformers for Fine-grained Visual Recognition","created":"2022-12-28","cited_by_count":7,"area":null},{"id":"2303.13166","title":"Take 5: Interpretable Image Classification with a Handful of Features","created":"2023-03-23","cited_by_count":7,"area":null},{"id":"2305.15775","title":"Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace","created":"2023-05-25","cited_by_count":7,"area":null},{"id":"2102.08065","title":"Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries","created":"2021-02-16","cited_by_count":6,"area":null},{"id":"2102.09744","title":"Trends in Vehicle Re-identification Past, Present, and Future: A Comprehensive Review","created":"2021-02-19","cited_by_count":6,"area":null},{"id":"2112.02747","title":"Making a Bird AI Expert Work for You and Me","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2201.08949","title":"Temporal Aggregation for Adaptive RGBT Tracking","created":"2022-01-22","cited_by_count":6,"area":null},{"id":"2204.11231","title":"Do ReLU Networks Have An Edge When Approximating Compactly-Supported Functions?","created":"2022-04-24","cited_by_count":6,"area":null},{"id":"2304.11597","title":"Learning Partial Correlation based Deep Visual Representation for Image Classification","created":"2023-04-23","cited_by_count":6,"area":null},{"id":"2305.07180","title":"Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition","created":"2023-05-12","cited_by_count":6,"area":null},{"id":"2101.00652","title":"Depth as Attention for Face Representation Learning","created":"2021-01-03","cited_by_count":5,"area":null},{"id":"2101.08527","title":"Progressive Co-Attention Network for Fine-grained Visual Classification","created":"2021-01-21","cited_by_count":5,"area":null},{"id":"2104.10935","title":"SoT: Delving Deeper into Classification Head for Transformer","created":"2021-04-22","cited_by_count":5,"area":null},{"id":"2107.02859","title":"Poly-NL: Linear Complexity Non-local Layers with Polynomials","created":"2021-07-06","cited_by_count":5,"area":null},{"id":"2208.01997","title":"Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization","created":"2022-08-03","cited_by_count":5,"area":null},{"id":"2209.07811","title":"Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity","created":"2022-09-16","cited_by_count":5,"area":null},{"id":"2307.15427","title":"Deep Learning Pipeline for Automated Visual Moth Monitoring: Insect Localization and Species Classification","created":"2023-07-28","cited_by_count":5,"area":null},{"id":"2309.13822","title":"PARTICLE: Part Discovery and Contrastive Learning for Fine-grained Recognition","created":"2023-09-25","cited_by_count":5,"area":null},{"id":"2310.18564","title":"A General Framework for Robust G-Invariance in G-Equivariant Networks","created":"2023-10-28","cited_by_count":5,"area":null},{"id":"2102.04331","title":"Soccer Event Detection Using Deep Learning","created":"2021-02-08","cited_by_count":4,"area":null},{"id":"2106.03432","title":"Channel DropBlock: An Improved Regularization Method for Fine-Grained Visual Classification","created":"2021-06-07","cited_by_count":4,"area":null},{"id":"2108.08301","title":"Identifying Illicit Drug Dealers on Instagram with Large-scale Multimodal Data Fusion","created":"2021-08-18","cited_by_count":4,"area":null},{"id":"2109.03156","title":"Fair Comparison: Quantifying Variance in Resultsfor Fine-grained Visual Categorization","created":"2021-09-07","cited_by_count":4,"area":null},{"id":"2110.05848","title":"Fine-Grained Adversarial Semi-supervised Learning","created":"2021-10-12","cited_by_count":4,"area":null},{"id":"2212.12478","title":"Image Classification with Small Datasets: Overview and Benchmark","created":"2022-12-23","cited_by_count":4,"area":null},{"id":"2302.11082","title":"BB-GCN: A Bi-modal Bridged Graph Convolutional Network for Multi-label Chest X-Ray Recognition","created":"2023-02-22","cited_by_count":4,"area":null},{"id":"2303.15266","title":"Multi-Granularity Archaeological Dating of Chinese Bronze Dings Based on a Knowledge-Guided Relation Graph","created":"2023-03-27","cited_by_count":4,"area":null},{"id":"2312.10515","title":"PETDet: Proposal Enhancement for Two-Stage Fine-Grained Object Detection","created":"2023-12-16","cited_by_count":4,"area":null},{"id":"2403.09728","title":"Simulating Weighted Automata over Sequences and Trees with Transformers","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2412.06740","title":"Convolution goes higher-order: a biologically inspired mechanism empowers image classification","created":"2024-12-09","cited_by_count":4,"area":null},{"id":"2503.12385","title":"Car-1000: A New Large Scale Fine-Grained Visual Categorization Dataset","created":"2025-03-16","cited_by_count":4,"area":null},{"id":"2506.22908","title":"Attention to the Burstiness in Visual Prompt Tuning!","created":"2025-06-28","cited_by_count":4,"area":null},{"id":"2102.00367","title":"Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained Features","created":"2021-01-31","cited_by_count":3,"area":null},{"id":"2103.09528","title":"Meta-learning of Pooling Layers for Character Recognition","created":"2021-03-17","cited_by_count":3,"area":null},{"id":"2108.08659","title":"Residual Tensor Train: A Quantum-inspired Approach for Learning Multiple Multilinear Correlations","created":"2021-08-19","cited_by_count":3,"area":null},{"id":"2212.09983","title":"Texture Representation via Analysis and Synthesis with Generative Adversarial Networks","created":"2022-12-20","cited_by_count":3,"area":null},{"id":"2306.01970","title":"Temporal-spatial Correlation Attention Network for Clinical Data Analysis in Intensive Care Unit","created":"2023-06-03","cited_by_count":3,"area":null},{"id":"2403.10298","title":"Context-Semantic Quality Awareness Network for Fine-Grained Visual Categorization","created":"2024-03-15","cited_by_count":3,"area":null},{"id":"2404.08915","title":"PM2: A New Prompting Multi-modal Model Paradigm for Few-shot Medical Image Classification","created":"2024-04-13","cited_by_count":3,"area":null}],"next_cursor":"100"}