{"total":121,"rows":[{"id":"2103.14862","title":"TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization","created":"2021-03-27","cited_by_count":123,"area":null},{"id":"2203.12719","title":"What to Hide from Your Students: Attention-Guided Masked Image Modeling","created":"2022-03-23","cited_by_count":118,"area":null},{"id":"2105.12723","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","created":"2021-05-26","cited_by_count":97,"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":"2106.06650","title":"Large-Scale Unsupervised Object Discovery","created":"2021-06-12","cited_by_count":54,"area":null},{"id":"2103.04523","title":"Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization","created":"2021-03-08","cited_by_count":46,"area":null},{"id":"2104.14783","title":"BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification","created":"2021-04-30","cited_by_count":44,"area":null},{"id":"2104.06148","title":"Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detection","created":"2021-04-13","cited_by_count":43,"area":null},{"id":"2111.03216","title":"Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network","created":"2021-11-05","cited_by_count":42,"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":"2107.12589","title":"Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization","created":"2021-07-27","cited_by_count":34,"area":null},{"id":"2108.00873","title":"Shallow Feature Matters for Weakly Supervised Object Localization","created":"2021-08-02","cited_by_count":34,"area":null},{"id":"2103.15375","title":"AlignMixup: Improving Representations By Interpolating Aligned Features","created":"2021-03-29","cited_by_count":33,"area":null},{"id":"2110.05741","title":"Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization","created":"2021-10-12","cited_by_count":30,"area":null},{"id":"2302.05499","title":"CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition","created":"2023-02-10","cited_by_count":30,"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":"2204.00220","title":"Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization","created":"2022-04-01","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":"2311.12770","title":"Swift Parameter-free Attention Network for Efficient Super-Resolution","created":"2023-11-21","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":"2308.03005","title":"MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation","created":"2023-08-06","cited_by_count":22,"area":null},{"id":"2103.11257","title":"Robust Models Are More Interpretable Because Attributions Look Normal","created":"2021-03-20","cited_by_count":21,"area":null},{"id":"2110.03094","title":"Improving Pneumonia Localization via Cross-Attention on Medical Images and Reports","created":"2021-10-06","cited_by_count":21,"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":"2107.13221","title":"Normalization Matters in Weakly Supervised Object Localization","created":"2021-07-28","cited_by_count":19,"area":null},{"id":"2304.01537","title":"PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification","created":"2023-04-04","cited_by_count":19,"area":null},{"id":"2103.17242","title":"Dogfight: Detecting Drones from Drones Videos","created":"2021-03-31","cited_by_count":18,"area":null},{"id":"2203.14196","title":"HINT: Hierarchical Neuron Concept Explainer","created":"2022-03-27","cited_by_count":17,"area":null},{"id":"2309.12943","title":"Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation","created":"2023-09-22","cited_by_count":17,"area":null},{"id":"2203.01714","title":"Weakly Supervised Object Localization as Domain Adaption","created":"2022-03-03","cited_by_count":16,"area":null},{"id":"2106.07861","title":"Keep CALM and Improve Visual Feature Attribution","created":"2021-06-15","cited_by_count":15,"area":null},{"id":"2407.10649","title":"Adaptive Patch Contrast for Weakly Supervised Semantic Segmentation","created":"2024-07-15","cited_by_count":15,"area":null},{"id":"2104.10351","title":"Improving Weakly-supervised Object Localization via Causal Intervention","created":"2021-04-21","cited_by_count":14,"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":"2207.10225","title":"On Label Granularity and Object Localization","created":"2022-07-20","cited_by_count":12,"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":"2103.02152","title":"Group-wise Inhibition based Feature Regularization for Robust Classification","created":"2021-03-03","cited_by_count":11,"area":null},{"id":"2206.09358","title":"What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs","created":"2022-06-19","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":"2402.00281","title":"Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues","created":"2024-02-01","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":"2112.02862","title":"SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation","created":"2021-12-06","cited_by_count":10,"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":"2201.02445","title":"Negative Evidence Matters in Interpretable Histology Image Classification","created":"2022-01-07","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":"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":"2103.16651","title":"DAP: Detection-Aware Pre-training with Weak Supervision","created":"2021-03-30","cited_by_count":7,"area":null},{"id":"2106.07049","title":"Weakly-supervised High-resolution Segmentation of Mammography Images for Breast Cancer Diagnosis","created":"2021-06-13","cited_by_count":7,"area":null},{"id":"2112.11895","title":"Few-shot Font Generation with Weakly Supervised Localized Representations","created":"2021-12-22","cited_by_count":7,"area":null},{"id":"2203.13505","title":"Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation","created":"2022-03-25","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":"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":"2504.14783","title":"How Effective Can Dropout Be in Multiple Instance Learning ?","created":"2025-04-21","cited_by_count":7,"area":null},{"id":"2105.12694","title":"Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey","created":"2021-05-26","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":"2112.14379","title":"Background-aware Classification Activation Map for Weakly Supervised Object Localization","created":"2021-12-29","cited_by_count":6,"area":null},{"id":"2209.09195","title":"Constrained Sampling for Class-Agnostic Weakly Supervised Object Localization","created":"2022-09-09","cited_by_count":6,"area":null},{"id":"2308.10112","title":"PDL: Regularizing Multiple Instance Learning with Progressive Dropout Layers","created":"2023-08-19","cited_by_count":6,"area":null},{"id":"2312.13646","title":"Weakly Supervised Semantic Segmentation for Driving Scenes","created":"2023-12-21","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":"2101.09915","title":"Weakly Supervised Thoracic Disease Localization via Disease Masks","created":"2021-01-25","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":"2102.09321","title":"Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse Features for Person Re-identification","created":"2021-02-18","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":"2111.03392","title":"SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Cost","created":"2021-11-05","cited_by_count":4,"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":"2301.01060","title":"Knowledge-guided Causal Intervention for Weakly-supervised Object Localization","created":"2023-01-03","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":"2104.14375","title":"MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2305.15354","title":"Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization","created":"2023-05-24","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":"2403.15977","title":"Towards Two-Stream Foveation-based Active Vision Learning","created":"2024-03-24","cited_by_count":3,"area":null},{"id":"2106.10472","title":"Informative Class Activation Maps","created":"2021-06-19","cited_by_count":2,"area":null},{"id":"2108.01056","title":"Distributed Attention for Grounded Image Captioning","created":"2021-08-02","cited_by_count":2,"area":null},{"id":"2108.01785","title":"Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection","created":"2021-08-03","cited_by_count":2,"area":null},{"id":"2205.01233","title":"One Weird Trick to Improve Your Semi-Weakly Supervised Semantic Segmentation Model","created":"2022-05-02","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":"2308.03272","title":"Feature-Suppressed Contrast for Self-Supervised Food Pre-training","created":"2023-08-07","cited_by_count":2,"area":null},{"id":"2308.06161","title":"Rethinking the Localization in Weakly Supervised Object Localization","created":"2023-08-11","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":"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":"2407.06018","title":"Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos","created":"2024-07-08","cited_by_count":2,"area":null},{"id":"2409.17370","title":"The Overfocusing Bias of Convolutional Neural Networks: A Saliency-Guided Regularization Approach","created":"2024-09-25","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":"2111.14131","title":"Learning a Weight Map for Weakly-Supervised Localization","created":"2021-11-28","cited_by_count":1,"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":"2309.03509","title":"BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applications","created":"2023-09-07","cited_by_count":1,"area":null},{"id":"2310.05330","title":"A Lightweight Video Anomaly Detection Model with Weak Supervision and Adaptive Instance Selection","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2405.14563","title":"Concept Visualization: Explaining the CLIP Multi-modal Embedding Using WordNet","created":"2024-05-23","cited_by_count":1,"area":null},{"id":"2406.04493","title":"ReceiptSense: Beyond Traditional OCR -- A Dataset for Receipt Understanding","created":"2024-06-06","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":"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}],"next_cursor":"100"}