{"total":52,"rows":[{"id":"2211.15660","title":"SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding","created":"2022-11-28","cited_by_count":167,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2106.12011","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","created":"2021-06-22","cited_by_count":84,"area":null},{"id":"2305.17997","title":"DiffRate : Differentiable Compression Rate for Efficient Vision Transformers","created":"2023-05-29","cited_by_count":77,"area":"inference"},{"id":"2203.10209","title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","created":"2022-03-19","cited_by_count":70,"area":null},{"id":"2405.11442","title":"Unifying 3D Vision-Language Understanding via Promptable Queries","created":"2024-05-19","cited_by_count":70,"area":null},{"id":"2106.02351","title":"SOLQ: Segmenting Objects by Learning Queries","created":"2021-06-04","cited_by_count":68,"area":null},{"id":"2111.13673","title":"Mask Transfiner for High-Quality Instance Segmentation","created":"2021-11-26","cited_by_count":64,"area":null},{"id":"2203.12827","title":"Sparse Instance Activation for Real-Time Instance Segmentation","created":"2022-03-24","cited_by_count":63,"area":null},{"id":"2305.08719","title":"M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis","created":"2023-05-15","cited_by_count":46,"area":null},{"id":"2303.15764","title":"X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance","created":"2023-03-28","cited_by_count":37,"area":null},{"id":"2210.06323","title":"AISFormer: Amodal Instance Segmentation with Transformer","created":"2022-10-12","cited_by_count":35,"area":null},{"id":"2203.12217","title":"Training-free Transformer Architecture Search","created":"2022-03-23","cited_by_count":33,"area":null},{"id":"2303.08594","title":"FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation","created":"2023-03-15","cited_by_count":32,"area":null},{"id":"2305.02187","title":"CLUSTSEG: Clustering for Universal Segmentation","created":"2023-05-03","cited_by_count":32,"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":"2404.19444","title":"AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion","created":"2024-04-30","cited_by_count":21,"area":null},{"id":"2304.02942","title":"InterFormer: Real-time Interactive Image Segmentation","created":"2023-04-06","cited_by_count":20,"area":null},{"id":"2308.05359","title":"Pseudo-label Alignment for Semi-supervised Instance Segmentation","created":"2023-08-10","cited_by_count":17,"area":null},{"id":"2309.14207","title":"Automatic Animation of Hair Blowing in Still Portrait Photos","created":"2023-09-25","cited_by_count":13,"area":null},{"id":"2302.01171","title":"Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt","created":"2023-02-02","cited_by_count":11,"area":null},{"id":"2303.08319","title":"FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2108.07851","title":"Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net","created":"2021-08-17","cited_by_count":9,"area":null},{"id":"2309.13248","title":"Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation","created":"2023-09-23","cited_by_count":9,"area":null},{"id":"2312.09534","title":"WeatherProof: A Paired-Dataset Approach to Semantic Segmentation in Adverse Weather","created":"2023-12-15","cited_by_count":9,"area":null},{"id":"2212.12977","title":"SMMix: Self-Motivated Image Mixing for Vision Transformers","created":"2022-12-26","cited_by_count":8,"area":null},{"id":"2306.07265","title":"detrex: Benchmarking Detection Transformers","created":"2023-06-12","cited_by_count":8,"area":null},{"id":"2306.05689","title":"Single-Stage Visual Relationship Learning using Conditional Queries","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2307.12239","title":"Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation","created":"2023-07-23","cited_by_count":6,"area":null},{"id":"2202.12251","title":"ISDA: Position-Aware Instance Segmentation with Deformable Attention","created":"2022-02-23","cited_by_count":5,"area":null},{"id":"2208.04438","title":"Occlusion-Aware Instance Segmentation via BiLayer Network Architectures","created":"2022-08-08","cited_by_count":5,"area":null},{"id":"2401.07641","title":"SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting","created":"2024-01-15","cited_by_count":5,"area":null},{"id":"2308.02606","title":"Improving Human-Object Interaction Detection via Virtual Image Learning","created":"2023-08-04","cited_by_count":4,"area":null},{"id":"2405.13388","title":"Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2504.04085","title":"DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2204.02898","title":"End-to-End Instance Edge Detection","created":"2022-04-06","cited_by_count":3,"area":null},{"id":"2207.10859","title":"Geodesic-Former: a Geodesic-Guided Few-shot 3D Point Cloud Instance Segmenter","created":"2022-07-22","cited_by_count":3,"area":null},{"id":"2310.12393","title":"Deep Learning Techniques for Video Instance Segmentation: A Survey","created":"2023-10-19","cited_by_count":3,"area":null},{"id":"2206.07011","title":"Consistent Video Instance Segmentation with Inter-Frame Recurrent Attention","created":"2022-06-14","cited_by_count":2,"area":null},{"id":"2301.09416","title":"Towards Robust Video Instance Segmentation with Temporal-Aware Transformer","created":"2023-01-20","cited_by_count":2,"area":null},{"id":"2410.16707","title":"DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2204.08744","title":"Proposal-free Lidar Panoptic Segmentation with Pillar-level Affinity","created":"2022-04-19","cited_by_count":1,"area":null},{"id":"2403.14874","title":"WeatherProof: Leveraging Language Guidance for Semantic Segmentation in Adverse Weather","created":"2024-03-21","cited_by_count":1,"area":null},{"id":"2410.19166","title":"DCT-HistoTransformer: Efficient Lightweight Vision Transformer with DCT Integration for histopathological image analysis","created":"2024-10-24","cited_by_count":1,"area":null},{"id":"2308.10839","title":"Vision Transformer Pruning Via Matrix Decomposition","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2402.03708","title":"SISP: A Benchmark Dataset for Fine-grained Ship Instance Segmentation in Panchromatic Satellite Images","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2403.09199","title":"Task-Specific Adaptation of Segmentation Foundation Model via Prompt Learning","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2408.04723","title":"Survey: Transformer-based Models in Data Modality Conversion","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2503.07517","title":"FastInstShadow: A Simple Query-Based Model for Instance Shadow Detection","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2605.18173","title":"Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2609.28222","title":"From Alignment to Fusion in 3D Vision-Language","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}