{"total":117,"rows":[{"id":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176,"area":null},{"id":"2105.03889","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","created":"2021-05-09","cited_by_count":164,"area":null},{"id":"2203.02891","title":"Multi-class Token Transformer for Weakly Supervised Semantic Segmentation","created":"2022-03-06","cited_by_count":138,"area":null},{"id":"2203.02664","title":"Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers","created":"2022-03-05","cited_by_count":118,"area":null},{"id":"2104.07918","title":"Weakly Supervised Object Localization and Detection: A Survey","created":"2021-04-16","cited_by_count":84,"area":null},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82,"area":null},{"id":"2111.09833","title":"TransMix: Attend to Mix for Vision Transformers","created":"2021-11-18","cited_by_count":79,"area":null},{"id":"2303.01267","title":"Token Contrast for Weakly-Supervised Semantic Segmentation","created":"2023-03-02","cited_by_count":65,"area":null},{"id":"2303.09665","title":"LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding","created":"2023-03-16","cited_by_count":64,"area":null},{"id":"2208.10431","title":"ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition","created":"2022-08-22","cited_by_count":63,"area":null},{"id":"2303.13434","title":"Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective","created":"2023-03-23","cited_by_count":54,"area":null},{"id":"2108.03658","title":"One-Shot Object Affordance Detection in the Wild","created":"2021-08-08","cited_by_count":40,"area":null},{"id":"2112.07891","title":"Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data","created":"2021-12-15","cited_by_count":27,"area":null},{"id":"2302.06378","title":"Semantic Image Segmentation: Two Decades of Research","created":"2023-02-13","cited_by_count":27,"area":null},{"id":"2109.07069","title":"F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling","created":"2021-09-15","cited_by_count":26,"area":null},{"id":"2203.07239","title":"TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentation","created":"2022-03-14","cited_by_count":26,"area":null},{"id":"2211.12268","title":"Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation","created":"2022-11-22","cited_by_count":26,"area":null},{"id":"2410.20722","title":"Interpretable Image Classification with Adaptive Prototype-based Vision Transformers","created":"2024-10-28","cited_by_count":25,"area":null},{"id":"2112.05291","title":"LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization","created":"2021-12-10","cited_by_count":24,"area":null},{"id":"2205.05920","title":"Group R-CNN for Weakly Semi-supervised Object Detection with Points","created":"2022-05-12","cited_by_count":24,"area":null},{"id":"2112.00580","title":"Background Activation Suppression for Weakly Supervised Object Localization","created":"2021-12-01","cited_by_count":22,"area":null},{"id":"2208.13196","title":"Grounded Affordance from Exocentric View","created":"2022-08-28","cited_by_count":22,"area":null},{"id":"2304.01184","title":"WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation","created":"2023-04-03","cited_by_count":22,"area":null},{"id":"2308.03005","title":"MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation","created":"2023-08-06","cited_by_count":22,"area":null},{"id":"2205.13922","title":"CREAM: Weakly Supervised Object Localization via Class RE-Activation Mapping","created":"2022-05-27","cited_by_count":21,"area":null},{"id":"2207.10447","title":"Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration","created":"2022-07-21","cited_by_count":20,"area":null},{"id":"2307.09756","title":"Generative Prompt Model for Weakly Supervised Object Localization","created":"2023-07-19","cited_by_count":20,"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":"2402.15490","title":"A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends","created":"2024-02-23","cited_by_count":16,"area":null},{"id":"2209.08956","title":"Panoramic Vision Transformer for Saliency Detection in 360{\\deg} Videos","created":"2022-09-19","cited_by_count":15,"area":null},{"id":"2204.06772","title":"ViTOL: Vision Transformer for Weakly Supervised Object Localization","created":"2022-04-14","cited_by_count":13,"area":null},{"id":"2209.09209","title":"Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization","created":"2022-09-09","cited_by_count":13,"area":null},{"id":"2208.14542","title":"TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos","created":"2022-08-30","cited_by_count":12,"area":null},{"id":"2409.06210","title":"INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding","created":"2024-09-10","cited_by_count":12,"area":null},{"id":"2207.05358","title":"eX-ViT: A Novel eXplainable Vision Transformer for Weakly Supervised Semantic Segmentation","created":"2022-07-12","cited_by_count":11,"area":null},{"id":"2208.01838","title":"Re-Attention Transformer for Weakly Supervised Object Localization","created":"2022-08-03","cited_by_count":11,"area":null},{"id":"2409.01030","title":"Learning to Discover Forgery Cues for Face Forgery Detection","created":"2024-09-02","cited_by_count":11,"area":null},{"id":"2203.15353","title":"SIOD: Single Instance Annotated Per Category Per Image for Object Detection","created":"2022-03-29","cited_by_count":10,"area":null},{"id":"2404.12015","title":"What does CLIP know about peeling a banana?","created":"2024-04-18","cited_by_count":9,"area":null},{"id":"2404.19113","title":"Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histology","created":"2024-04-29","cited_by_count":9,"area":null},{"id":"2412.11076","title":"MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation","created":"2024-12-15","cited_by_count":9,"area":null},{"id":"2112.02841","title":"GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation","created":"2021-12-06","cited_by_count":8,"area":null},{"id":"2309.08035","title":"Interpretability-Aware Vision Transformer","created":"2023-09-14","cited_by_count":8,"area":null},{"id":"2310.06196","title":"DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2111.08313","title":"Towards Comprehensive Monocular Depth Estimation: Multiple Heads Are Better Than One","created":"2021-11-16","cited_by_count":7,"area":null},{"id":"2207.05205","title":"Scaling Novel Object Detection with Weakly Supervised Detection Transformers","created":"2022-07-11","cited_by_count":7,"area":null},{"id":"2303.09044","title":"CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos","created":"2023-03-16","cited_by_count":7,"area":null},{"id":"2303.10438","title":"Spatial-Aware Token for Weakly Supervised Object Localization","created":"2023-03-18","cited_by_count":7,"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":"2112.14379","title":"Background-aware Classification Activation Map for Weakly Supervised Object Localization","created":"2021-12-29","cited_by_count":6,"area":null},{"id":"2212.02019","title":"SASFormer: Transformers for Sparsely Annotated Semantic Segmentation","created":"2022-12-05","cited_by_count":6,"area":null},{"id":"2304.04902","title":"Weakly Supervised Intracranial Hemorrhage Segmentation using Head-Wise Gradient-Infused Self-Attention Maps from a Swin Transformer in Categorical Learning","created":"2023-04-11","cited_by_count":6,"area":null},{"id":"2408.01191","title":"A Weakly Supervised and Globally Explainable Learning Framework for Brain Tumor Segmentation","created":"2024-08-02","cited_by_count":6,"area":null},{"id":"2508.07877","title":"Selective Contrastive Learning for Weakly Supervised Affordance Grounding","created":"2025-08-11","cited_by_count":6,"area":null},{"id":"2206.11826","title":"Toward Clinically Assisted Colorectal Polyp Recognition via Structured Cross-modal Representation Consistency","created":"2022-06-23","cited_by_count":5,"area":null},{"id":"2303.09171","title":"Empowering CAM-Based Methods with Capability to Generate Fine-Grained and High-Faithfulness Explanations","created":"2023-03-16","cited_by_count":5,"area":null},{"id":"2307.10853","title":"Exploring Effective Priors and Efficient Models for Weakly-Supervised Change Detection","created":"2023-07-20","cited_by_count":5,"area":null},{"id":"2404.10034","title":"A Realistic Protocol for Evaluation of Weakly Supervised Object Localization","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2407.15794","title":"Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical video","created":"2024-07-22","cited_by_count":5,"area":null},{"id":"2201.00475","title":"CaFT: Clustering and Filter on Tokens of Transformer for Weakly Supervised Object Localization","created":"2022-01-03","cited_by_count":4,"area":null},{"id":"2209.15211","title":"Dual Progressive Transformations for Weakly Supervised Semantic Segmentation","created":"2022-09-30","cited_by_count":4,"area":null},{"id":"2306.07490","title":"Top-Down Framework for Weakly-supervised Grounded Image Captioning","created":"2023-06-13","cited_by_count":4,"area":null},{"id":"2404.05603","title":"Self-Explainable Affordance Learning with Embodied Caption","created":"2024-04-08","cited_by_count":4,"area":null},{"id":"2412.03968","title":"Exact: Exploring Space-Time Perceptive Clues for Weakly Supervised Satellite Image Time Series Semantic Segmentation","created":"2024-12-05","cited_by_count":4,"area":null},{"id":"2502.15885","title":"DOEI: Dual Optimization of Embedding Information for Attention-Enhanced Class Activation Maps","created":"2025-02-21","cited_by_count":4,"area":null},{"id":"2510.17384","title":"Closed-Loop Transfer for Weakly-supervised Affordance Grounding","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2302.02075","title":"X-ReID: Cross-Instance Transformer for Identity-Level Person Re-Identification","created":"2023-02-04","cited_by_count":3,"area":null},{"id":"2305.03112","title":"Calibrating Undisciplined Over-Smoothing in Transformer for Weakly Supervised Semantic Segmentation","created":"2023-05-04","cited_by_count":3,"area":null},{"id":"2306.11490","title":"UM-CAM: Uncertainty-weighted Multi-resolution Class Activation Maps for Weakly-supervised Fetal Brain Segmentation","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2308.04321","title":"All-pairs Consistency Learning for Weakly Supervised Semantic Segmentation","created":"2023-08-08","cited_by_count":3,"area":null},{"id":"2309.04172","title":"Unsupervised Object Localization with Representer Point Selection","created":"2023-09-08","cited_by_count":3,"area":null},{"id":"2309.05261","title":"Gall Bladder Cancer Detection from US Images with Only Image Level Labels","created":"2023-09-11","cited_by_count":3,"area":null},{"id":"2312.08916","title":"Progressive Feature Self-reinforcement for Weakly Supervised Semantic Segmentation","created":"2023-12-14","cited_by_count":3,"area":null},{"id":"2402.17891","title":"Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2403.01156","title":"Auxiliary Tasks Enhanced Dual-affinity Learning for Weakly Supervised Semantic Segmentation","created":"2024-03-02","cited_by_count":3,"area":null},{"id":"2108.01056","title":"Distributed Attention for Grounded Image Captioning","created":"2021-08-02","cited_by_count":2,"area":null},{"id":"2208.05616","title":"OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms","created":"2022-08-11","cited_by_count":2,"area":null},{"id":"2210.14618","title":"SemFormer: Semantic Guided Activation Transformer for Weakly Supervised Semantic Segmentation","created":"2022-10-26","cited_by_count":2,"area":null},{"id":"2304.08271","title":"Open-World Weakly-Supervised Object Localization","created":"2023-04-17","cited_by_count":2,"area":null},{"id":"2305.08491","title":"Masked Collaborative Contrast for Weakly Supervised Semantic Segmentation","created":"2023-05-15","cited_by_count":2,"area":null},{"id":"2309.01331","title":"Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2403.06676","title":"CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2404.09475","title":"Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2410.01848","title":"Spatial Action Unit Cues for Interpretable Deep Facial Expression Recognition","created":"2024-10-01","cited_by_count":2,"area":null},{"id":"2501.12632","title":"TeD-Loc: Text Distillation for Weakly Supervised Object Localization","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2503.24135","title":"PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI Localization","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2209.10471","title":"Sample, Crop, Track: Self-Supervised Mobile 3D Object Detection for Urban Driving LiDAR","created":"2022-09-21","cited_by_count":1,"area":null},{"id":"2211.10931","title":"Attention-based Class Activation Diffusion for Weakly-Supervised Semantic Segmentation","created":"2022-11-20","cited_by_count":1,"area":null},{"id":"2211.15672","title":"ExpNet: A unified network for Expert-Level Classification","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2410.13621","title":"EP-SAM: Weakly Supervised Histopathology Segmentation via Enhanced Prompt with Segment Anything","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2412.17504","title":"An Evaluation Framework for Product Images Background Inpainting based on Human Feedback and Product Consistency","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2502.10145","title":"Interpretable Concept-based Deep Learning Framework for Multimodal Human Behavior Modeling","created":"2025-02-14","cited_by_count":1,"area":null},{"id":"2505.04905","title":"Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2209.10074","title":"PicT: A Slim Weakly Supervised Vision Transformer for Pavement Distress Classification","created":"2022-09-21","cited_by_count":0,"area":null},{"id":"2310.00307","title":"Dual-Augmented Transformer Network for Weakly Supervised Semantic Segmentation","created":"2023-09-30","cited_by_count":0,"area":null},{"id":"2310.07184","title":"NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2312.09584","title":"Multiscale Vision Transformer With Deep Clustering-Guided Refinement for Weakly Supervised Object Localization","created":"2023-12-15","cited_by_count":0,"area":null},{"id":"2403.05703","title":"Not just Birds and Cars: Generic, Scalable and Explainable Models for Professional Visual Recognition","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2403.08801","title":"CoBra: Complementary Branch Fusing Class and Semantic Knowledge for Robust Weakly Supervised Semantic Segmentation","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2404.03394","title":"Background Noise Reduction of Attention Map for Weakly Supervised Semantic Segmentation","created":"2024-04-04","cited_by_count":0,"area":null}],"next_cursor":"100"}