{"total":118,"rows":[{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2312.00878","title":"Grounding Everything: Emerging Localization Properties in Vision-Language Transformers","created":"2023-12-01","cited_by_count":91,"area":"mllm"},{"id":"2309.02773","title":"Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter","created":"2023-09-06","cited_by_count":76,"area":"diffusion"},{"id":"2503.06661","title":"AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP","created":"2025-03-09","cited_by_count":73,"area":null},{"id":"2312.07661","title":"CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor","created":"2023-12-12","cited_by_count":69,"area":null},{"id":"2407.08268","title":"Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation","created":"2024-07-11","cited_by_count":61,"area":"mllm"},{"id":"2502.07601","title":"Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models","created":"2025-02-11","cited_by_count":54,"area":"lr"},{"id":"2305.05803","title":"Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation","created":"2023-05-09","cited_by_count":53,"area":null},{"id":"2404.08531","title":"Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection","created":"2024-04-12","cited_by_count":49,"area":null},{"id":"2306.04300","title":"CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation","created":"2023-06-07","cited_by_count":44,"area":null},{"id":"2311.16241","title":"SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance","created":"2023-11-27","cited_by_count":41,"area":null},{"id":"2409.19483","title":"MedCLIP-SAMv2: Towards Universal Text-Driven Medical Image Segmentation","created":"2024-09-28","cited_by_count":39,"area":null},{"id":"2308.14575","title":"Referring Image Segmentation Using Text Supervision","created":"2023-08-28","cited_by_count":35,"area":null},{"id":"2408.12957","title":"Image Segmentation in Foundation Model Era: A Survey","created":"2024-08-23","cited_by_count":35,"area":"diffusion"},{"id":"2312.03585","title":"Foundation Model Assisted Weakly Supervised Semantic Segmentation","created":"2023-12-06","cited_by_count":33,"area":null},{"id":"2407.00203","title":"PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration","created":"2024-06-28","cited_by_count":28,"area":"mllm"},{"id":"2502.08391","title":"ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification","created":"2025-02-12","cited_by_count":28,"area":null},{"id":"2305.01275","title":"Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentation","created":"2023-05-02","cited_by_count":27,"area":null},{"id":"2312.14209","title":"TextFusion: Unveiling the Power of Textual Semantics for Controllable Image Fusion","created":"2023-12-21","cited_by_count":26,"area":null},{"id":"2309.01859","title":"NLLB-CLIP -- train performant multilingual image retrieval model on a budget","created":"2023-09-04","cited_by_count":24,"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":"2407.09033","title":"Textual Query-Driven Mask Transformer for Domain Generalized Segmentation","created":"2024-07-12","cited_by_count":21,"area":"mllm"},{"id":"2405.08458","title":"Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation","created":"2024-05-14","cited_by_count":20,"area":null},{"id":"2502.06756","title":"SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2305.01586","title":"An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems","created":"2023-05-02","cited_by_count":19,"area":null},{"id":"2310.13026","title":"Weakly-Supervised Semantic Segmentation with Image-Level Labels: from Traditional Models to Foundation Models","created":"2023-10-19","cited_by_count":19,"area":null},{"id":"2309.10726","title":"Few-Shot Panoptic Segmentation With Foundation Models","created":"2023-09-19","cited_by_count":18,"area":null},{"id":"2401.11122","title":"Spatial Structure Constraints for Weakly Supervised Semantic Segmentation","created":"2024-01-20","cited_by_count":17,"area":null},{"id":"2403.11184","title":"DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation","created":"2024-03-17","cited_by_count":17,"area":null},{"id":"2411.13836","title":"CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation","created":"2024-11-21","cited_by_count":17,"area":null},{"id":"2309.04109","title":"From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models","created":"2023-09-08","cited_by_count":16,"area":"diffusion"},{"id":"2403.07630","title":"Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation","created":"2024-03-12","cited_by_count":16,"area":null},{"id":"2406.11189","title":"Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation","created":"2024-06-17","cited_by_count":15,"area":null},{"id":"2409.06809","title":"DetailCLIP: Detail-Oriented CLIP for Fine-Grained Tasks","created":"2024-09-10","cited_by_count":15,"area":"mllm"},{"id":"2402.18467","title":"Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation","created":"2024-02-28","cited_by_count":14,"area":null},{"id":"2403.04294","title":"A$^{3}$lign-DFER: Pioneering Comprehensive Dynamic Affective Alignment for Dynamic Facial Expression Recognition with CLIP","created":"2024-03-07","cited_by_count":14,"area":null},{"id":"2504.02328","title":"Refining CLIP's Spatial Awareness: A Visual-Centric Perspective","created":"2025-04-03","cited_by_count":13,"area":null},{"id":"2402.14812","title":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition","created":"2024-02-22","cited_by_count":10,"area":null},{"id":"2409.03209","title":"iSeg: An Iterative Refinement-based Framework for Training-free Segmentation","created":"2024-09-05","cited_by_count":10,"area":"diffusion"},{"id":"2410.01544","title":"Boosting Weakly-Supervised Referring Image Segmentation via Progressive Comprehension","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2310.02296","title":"CLIP Is Also a Good Teacher: A New Learning Framework for Inductive Zero-shot Semantic Segmentation","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2503.09320","title":"2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos","created":"2025-03-12","cited_by_count":9,"area":null},{"id":"2505.24103","title":"Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2508.00557","title":"Training-Free Class Purification for Open-Vocabulary Semantic Segmentation","created":"2025-08-01","cited_by_count":9,"area":"mllm"},{"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":"2407.02768","title":"Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation","created":"2024-07-03","cited_by_count":8,"area":null},{"id":"2503.20826","title":"Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation","created":"2025-03-26","cited_by_count":8,"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":"2310.10533","title":"Label-efficient Segmentation via Affinity Propagation","created":"2023-10-16","cited_by_count":7,"area":null},{"id":"2405.19035","title":"A Good Foundation is Worth Many Labels: Label-Efficient Panoptic Segmentation","created":"2024-05-29","cited_by_count":7,"area":null},{"id":"2411.12044","title":"ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements","created":"2024-11-18","cited_by_count":7,"area":"mllm"},{"id":"2502.12513","title":"RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm","created":"2025-02-18","cited_by_count":7,"area":null},{"id":"2508.00395","title":"Decouple before Align: Visual Disentanglement Enhances Prompt Tuning","created":"2025-08-01","cited_by_count":7,"area":"mllm"},{"id":"2405.14294","title":"Tuning-free Universally-Supervised Semantic Segmentation","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2410.01341","title":"Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2403.03463","title":"FLAME Diffuser: Wildfire Image Synthesis using Mask Guided Diffusion","created":"2024-03-06","cited_by_count":5,"area":"diffusion"},{"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":"2506.01539","title":"G4Seg: Generation for Inexact Segmentation Refinement with Diffusion Models","created":"2025-06-02","cited_by_count":5,"area":"diffusion"},{"id":"2512.03508","title":"Exploiting Domain Properties in Language-Driven Domain Generalization for Semantic Segmentation","created":"2025-12-03","cited_by_count":5,"area":"mllm"},{"id":"2309.01369","title":"Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation","created":"2023-09-04","cited_by_count":4,"area":"diffusion"},{"id":"2401.13296","title":"Visual Objectification in Films: Towards a New AI Task for Video Interpretation","created":"2024-01-24","cited_by_count":4,"area":null},{"id":"2404.08195","title":"Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation","created":"2024-04-12","cited_by_count":4,"area":null},{"id":"2407.10131","title":"WPS-SAM: Towards Weakly-Supervised Part Segmentation with Foundation Models","created":"2024-07-14","cited_by_count":4,"area":null},{"id":"2409.15801","title":"DIAL: Dense Image-text ALignment for Weakly Supervised Semantic Segmentation","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2501.16222","title":"SPECIAL: Zero-shot Hyperspectral Image Classification With CLIP","created":"2025-01-27","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":"2503.07982","title":"TRACE: Your Diffusion Model is Secretly an Instance Edge Detector","created":"2025-03-11","cited_by_count":4,"area":"diffusion"},{"id":"2504.10487","title":"FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation","created":"2025-04-14","cited_by_count":4,"area":null},{"id":"2401.11791","title":"Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation","created":"2024-01-22","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":"2403.17173","title":"Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2404.00380","title":"DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation","created":"2024-03-30","cited_by_count":3,"area":null},{"id":"2502.11955","title":"pySLAM: An Open-Source, Modular, and Extensible Framework for SLAM","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2503.11953","title":"SPOC: Spatially-Progressing Object State Change Segmentation in Video","created":"2025-03-15","cited_by_count":3,"area":null},{"id":"2506.04214","title":"Sounding that Object: Interactive Object-Aware Image to Audio Generation","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2507.04621","title":"Multimodal LLM Integrated Semantic Communications for 6G Immersive Experiences","created":"2025-07-07","cited_by_count":3,"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":"2405.11614","title":"Nickel and Diming Your GAN: A Dual-Method Approach to Enhancing GAN Efficiency via Knowledge Distillation","created":"2024-05-19","cited_by_count":2,"area":"distill"},{"id":"2405.14230","title":"Boosting Medical Image-based Cancer Detection via Text-guided Supervision from Reports","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2407.05061","title":"Test-time Contrastive Concepts for Open-world Semantic Segmentation with Vision-Language Models","created":"2024-07-06","cited_by_count":2,"area":"mllm"},{"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":"2408.02039","title":"Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation","created":"2024-08-04","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":"2511.08248","title":"NERVE: Neighbourhood & Entropy-guided Random-walk for training free open-Vocabulary sEgmentation","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2605.12325","title":"VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.31266","title":"Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generation","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2307.02862","title":"A Critical Look at the Current Usage of Foundation Model for Dense Recognition Task","created":"2023-07-06","cited_by_count":1,"area":"diffusion"},{"id":"2412.17601","title":"AFANet: Adaptive Frequency-Aware Network for Weakly-Supervised Few-Shot Semantic Segmentation","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2501.11653","title":"Dynamic Scene Understanding from Vision-Language Representations","created":"2025-01-20","cited_by_count":1,"area":null},{"id":"2502.02977","title":"Efficiently Disentangling CLIP for Multi-Object Perception","created":"2025-02-05","cited_by_count":1,"area":"mllm"},{"id":"2504.07942","title":"MARS: a Multimodal Alignment and Ranking System for Few-Shot Segmentation","created":"2025-04-10","cited_by_count":1,"area":null},{"id":"2507.09615","title":"Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score","created":"2025-07-13","cited_by_count":1,"area":"mllm"},{"id":"2508.00213","title":"SAM-PTx: Text-Guided Fine-Tuning of SAM with Parameter-Efficient, Parallel-Text Adapters","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2511.15118","title":"Unbiased Semantic Decoding with Vision Foundation Models for Few-shot Segmentation","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2605.13674","title":"Weakly Supervised Segmentation as Semantic-Based Regularization","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2607.29059","title":"Learning from Adversity: Semantic-Aware Mask Refinement through Adversarial Perturbation","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2402.10851","title":"HistoSegCap: Capsules for Weakly-Supervised Semantic Segmentation of Histological Tissue Type in Whole Slide Images","created":"2024-02-16","cited_by_count":0,"area":null},{"id":"2411.12615","title":"Text-Driven Weakly Supervised OCT Lesion Segmentation with Structural Guidance","created":"2024-11-19","cited_by_count":0,"area":null}],"next_cursor":"100"}