{"total":95,"rows":[{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2111.06119","title":"Fine-Grained Image Analysis with Deep Learning: A Survey","created":"2021-11-11","cited_by_count":135,"area":null},{"id":"2103.07976","title":"TransFG: A Transformer Architecture for Fine-grained Recognition","created":"2021-03-14","cited_by_count":132,"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":"2112.02902","title":"Interpretable Image Classification with Differentiable Prototypes Assignment","created":"2021-12-06","cited_by_count":97,"area":null},{"id":"2205.02151","title":"Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification","created":"2022-05-04","cited_by_count":78,"area":null},{"id":"2204.14244","title":"CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification","created":"2022-04-29","cited_by_count":65,"area":null},{"id":"2111.06349","title":"Unsupervised Part Discovery from Contrastive Reconstruction","created":"2021-11-11","cited_by_count":57,"area":null},{"id":"2108.07948","title":"Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment","created":"2021-08-18","cited_by_count":41,"area":"distill"},{"id":"2201.03014","title":"Glance and Focus Networks for Dynamic Visual Recognition","created":"2022-01-09","cited_by_count":41,"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":"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":"2304.05538","title":"ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification","created":"2023-04-11","cited_by_count":33,"area":null},{"id":"2101.06635","title":"Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification","created":"2021-01-17","cited_by_count":31,"area":null},{"id":"2111.09733","title":"Perceiving and Modeling Density is All You Need for Image Dehazing","created":"2021-11-18","cited_by_count":30,"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":"2210.04206","title":"Attention Diversification for Domain Generalization","created":"2022-10-09","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":"2308.08162","title":"Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations","created":"2023-08-16","cited_by_count":27,"area":null},{"id":"2310.10071","title":"ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking","created":"2023-10-16","cited_by_count":25,"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":"2203.15987","title":"Fine-Grained Object Classification via Self-Supervised Pose Alignment","created":"2022-03-30","cited_by_count":22,"area":null},{"id":"2111.01628","title":"Human Attention in Fine-grained Classification","created":"2021-11-02","cited_by_count":21,"area":null},{"id":"2207.01376","title":"Task Discrepancy Maximization for Fine-grained Few-Shot Classification","created":"2022-07-04","cited_by_count":21,"area":null},{"id":"2209.02109","title":"SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization","created":"2022-09-05","cited_by_count":21,"area":null},{"id":"2208.14607","title":"SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization","created":"2022-08-31","cited_by_count":19,"area":null},{"id":"2106.02694","title":"Efficient Classification of Very Large Images with Tiny Objects","created":"2021-06-04","cited_by_count":17,"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":"2110.01240","title":"A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition","created":"2021-10-04","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":"2501.11309","title":"Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation","created":"2025-01-20","cited_by_count":15,"area":null},{"id":"2207.04602","title":"Adaptive Fine-Grained Predicates Learning for Scene Graph Generation","created":"2022-07-11","cited_by_count":14,"area":null},{"id":"2204.02397","title":"SALISA: Saliency-based Input Sampling for Efficient Video Object Detection","created":"2022-04-05","cited_by_count":12,"area":null},{"id":"2310.19168","title":"BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and Mapping","created":"2023-10-29","cited_by_count":12,"area":null},{"id":"2101.03919","title":"Comprehensible Convolutional Neural Networks via Guided Concept Learning","created":"2021-01-11","cited_by_count":11,"area":null},{"id":"2503.10183","title":"Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM Decoding","created":"2025-03-13","cited_by_count":10,"area":"mllm"},{"id":"2106.15788","title":"Exploring Localization for Self-supervised Fine-grained Contrastive Learning","created":"2021-06-30","cited_by_count":9,"area":null},{"id":"2207.09759","title":"Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action Recognition","created":"2022-07-20","cited_by_count":9,"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":"2409.10329","title":"InfoDisent: Explainability of Image Classification Models by Information Disentanglement","created":"2024-09-16","cited_by_count":8,"area":null},{"id":"2106.10587","title":"Exploring Vision Transformers for Fine-grained Classification","created":"2021-06-19","cited_by_count":7,"area":null},{"id":"2107.12189","title":"An Efficient Insect Pest Classification Using Multiple Convolutional Neural Network Based Models","created":"2021-07-26","cited_by_count":7,"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":"2212.13685","title":"Part-guided Relational Transformers for Fine-grained Visual Recognition","created":"2022-12-28","cited_by_count":7,"area":null},{"id":"2305.06114","title":"Few-shot Action Recognition via Intra- and Inter-Video Information Maximization","created":"2023-05-10","cited_by_count":7,"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":"2106.08543","title":"Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions","created":"2021-06-16","cited_by_count":5,"area":null},{"id":"2112.01034","title":"Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data","created":"2021-12-02","cited_by_count":5,"area":null},{"id":"2204.01707","title":"Quadratic Neuron-empowered Heterogeneous Autoencoder for Unsupervised Anomaly Detection","created":"2022-04-02","cited_by_count":5,"area":null},{"id":"2308.00093","title":"Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification","created":"2023-07-28","cited_by_count":4,"area":null},{"id":"2308.14418","title":"Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization","created":"2023-08-28","cited_by_count":4,"area":null},{"id":"2309.04723","title":"Frequency-Aware Self-Supervised Long-Tailed Learning","created":"2023-09-09","cited_by_count":4,"area":null},{"id":"2407.12891","title":"Global-Local Similarity for Efficient Fine-Grained Image Recognition with Vision Transformers","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2408.06631","title":"IFShip: Interpretable Fine-grained Ship Classification with Domain Knowledge-Enhanced Vision-Language Models","created":"2024-08-13","cited_by_count":4,"area":"mllm"},{"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":"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":"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":"2203.15383","title":"Category Guided Attention Network for Brain Tumor Segmentation in MRI","created":"2022-03-29","cited_by_count":3,"area":null},{"id":"2205.13255","title":"Active Labeling: Streaming Stochastic Gradients","created":"2022-05-26","cited_by_count":3,"area":null},{"id":"2305.07102","title":"Salient Mask-Guided Vision Transformer for Fine-Grained Classification","created":"2023-05-11","cited_by_count":3,"area":null},{"id":"2308.04912","title":"Cross-view Semantic Alignment for Livestreaming Product Recognition","created":"2023-08-09","cited_by_count":3,"area":null},{"id":"2507.11893","title":"Spatial Frequency Modulation for Semantic Segmentation","created":"2025-07-16","cited_by_count":3,"area":null},{"id":"2101.09666","title":"Grad-CAM guided channel-spatial attention module for fine-grained visual classification","created":"2021-01-24","cited_by_count":2,"area":null},{"id":"2103.14872","title":"Deep Learning Techniques for In-Crop Weed Identification: A Review","created":"2021-03-27","cited_by_count":2,"area":null},{"id":"2207.11511","title":"SSBNet: Improving Visual Recognition Efficiency by Adaptive Sampling","created":"2022-07-23","cited_by_count":2,"area":null},{"id":"2210.08784","title":"Cross-layer Attention Network for Fine-grained Visual Categorization","created":"2022-10-17","cited_by_count":2,"area":null},{"id":"2212.13693","title":"Parsing Objects at a Finer Granularity: A Survey","created":"2022-12-28","cited_by_count":2,"area":null},{"id":"2308.02161","title":"M2Former: Multi-Scale Patch Selection for Fine-Grained Visual Recognition","created":"2023-08-04","cited_by_count":2,"area":null},{"id":"2105.10438","title":"Compositional Fine-Grained Low-Shot Learning","created":"2021-05-21","cited_by_count":1,"area":null},{"id":"2106.02141","title":"Fine-Grained Visual Classification of Plant Species In The Wild: Object Detection as A Reinforced Means of Attention","created":"2021-06-03","cited_by_count":1,"area":null},{"id":"2106.10920","title":"Cross-layer Navigation Convolutional Neural Network for Fine-grained Visual Classification","created":"2021-06-21","cited_by_count":1,"area":null},{"id":"2405.17824","title":"mTREE: Multi-Level Text-Guided Representation End-to-End Learning for Whole Slide Image Analysis","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2406.08457","title":"ConceptHash: Interpretable Fine-Grained Hashing via Concept Discovery","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2501.04144","title":"Chirpy3D: Part-Aware Multi-View Diffusion for Creative Fine-Grained Object Generation","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2501.06059","title":"COMIX: Compositional Explanations using Prototypes","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2505.23365","title":"MCFNet: A Multimodal Collaborative Fusion Network for Fine-Grained Semantic Classification","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2101.09412","title":"Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Noisy Samples and Utilizing Hard Ones","created":"2021-01-23","cited_by_count":0,"area":null},{"id":"2104.04952","title":"Fine-Grained Attention for Weakly Supervised Object Localization","created":"2021-04-11","cited_by_count":0,"area":null},{"id":"2110.12178","title":"An attention-driven hierarchical multi-scale representation for visual recognition","created":"2021-10-23","cited_by_count":0,"area":null},{"id":"2204.02008","title":"Learning Video Salient Object Detection Progressively from Unlabeled Videos","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2207.11637","title":"Explored An Effective Methodology for Fine-Grained Snake Recognition","created":"2022-07-24","cited_by_count":0,"area":null},{"id":"2303.07648","title":"SimFLE: Simple Facial Landmark Encoding for Self-Supervised Facial Expression Recognition in the Wild","created":"2023-03-14","cited_by_count":0,"area":null},{"id":"2305.12635","title":"A bioinspired three-stage model for camouflaged object detection","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2306.01929","title":"Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Work","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2307.00954","title":"HODINet: High-Order Discrepant Interaction Network for RGB-D Salient Object Detection","created":"2023-07-03","cited_by_count":0,"area":null},{"id":"2310.06337","title":"Local Style Awareness of Font Images","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2311.06868","title":"Concept-wise Fine-tuning Matters in Preventing Negative Transfer","created":"2023-11-12","cited_by_count":0,"area":null},{"id":"2405.04093","title":"DCNN: Dual Cross-current Neural Networks Realized Using An Interactive Deep Learning Discriminator for Fine-grained Objects","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2503.07075","title":"XR-VLM: Cross-Relationship Modeling with Multi-part Prompts and Visual Features for Fine-Grained Recognition","created":"2025-03-10","cited_by_count":0,"area":"mllm"},{"id":"2504.09215","title":"Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition","created":"2025-04-12","cited_by_count":0,"area":null},{"id":"2504.20322","title":"Fine-Grained Classification: Connecting Metadata via Cross-Contrastive Pre-Training","created":"2025-04-29","cited_by_count":0,"area":null},{"id":"2507.07929","title":"Towards Continuous Home Cage Monitoring: An Evaluation of Tracking and Identification Strategies for Laboratory Mice","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2509.21061","title":"EnGraf-Net: Multiple Granularity Branch Network with Fine-Coarse Graft Grained for Classification Task","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2604.20213","title":"Weighted Knowledge Distillation for Semi-Supervised Segmentation of Maxillary Sinus in Panoramic X-ray Images","created":"2026-04-22","cited_by_count":0,"area":"distill"}],"next_cursor":null}