{"list":"other","total":93,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1912.12033","title":"Deep Learning for 3D Point Clouds: A Survey","created":"2019-12-27","cited_by_count":558},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2304.12620","title":"Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation","created":"2023-04-25","cited_by_count":490},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"1908.06948","title":"Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography","created":"2019-08-16","cited_by_count":244},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"1809.00461","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","created":"2018-09-03","cited_by_count":232},{"id":"2304.12306","title":"Segment Anything in Medical Images","created":"2023-04-24","cited_by_count":227},{"id":"2106.02638","title":"Associating Objects with Transformers for Video Object Segmentation","created":"2021-06-04","cited_by_count":226},{"id":"2106.05210","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","created":"2021-06-09","cited_by_count":203},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197},{"id":"2312.00863","title":"EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything","created":"2023-12-01","cited_by_count":188},{"id":"1902.09513","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","created":"2019-02-25","cited_by_count":178},{"id":"1612.02646","title":"Learning Video Object Segmentation from Static Images","created":"2016-12-08","cited_by_count":151},{"id":"2210.09782","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","created":"2022-10-18","cited_by_count":148},{"id":"2003.08333","title":"Collaborative Video Object Segmentation by Foreground-Background Integration","created":"2020-03-18","cited_by_count":142},{"id":"2107.01153","title":"A Survey on Deep Learning Technique for Video Segmentation","created":"2021-07-02","cited_by_count":132},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124},{"id":"2007.07020","title":"Video Object Segmentation with Episodic Graph Memory Networks","created":"2020-07-14","cited_by_count":118},{"id":"2405.12971","title":"BiomedParse: a biomedical foundation model for image parsing of everything everywhere all at once","created":"2024-05-21","cited_by_count":111},{"id":"2308.08746","title":"SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation","created":"2023-08-17","cited_by_count":104},{"id":"2206.04403","title":"VITA: Video Instance Segmentation via Object Token Association","created":"2022-06-09","cited_by_count":94},{"id":"2203.14291","title":"Video Polyp Segmentation: A Deep Learning Perspective","created":"2022-03-27","cited_by_count":82},{"id":"2010.06349","title":"Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration","created":"2020-10-13","cited_by_count":81},{"id":"2307.01197","title":"Segment Anything Meets Point Tracking","created":"2023-07-03","cited_by_count":81},{"id":"1501.02565","title":"EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow","created":"2015-01-12","cited_by_count":80},{"id":"2410.16268","title":"SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree","created":"2024-10-21","cited_by_count":80},{"id":"2204.04656","title":"Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation","created":"2022-04-10","cited_by_count":79},{"id":"2211.10181","title":"LVOS: A Benchmark for Long-term Video Object Segmentation","created":"2022-11-18","cited_by_count":77},{"id":"2004.00218","title":"3D Deep Learning on Medical Images: A Review","created":"2020-04-01","cited_by_count":76},{"id":"2401.10229","title":"OMG-Seg: Is One Model Good Enough For All Segmentation?","created":"2024-01-18","cited_by_count":75},{"id":"2109.11404","title":"Hierarchical Memory Matching Network for Video Object Segmentation","created":"2021-09-23","cited_by_count":72},{"id":"2306.13465","title":"3DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentation","created":"2023-06-23","cited_by_count":70},{"id":"2007.05533","title":"ISINet: An Instance-Based Approach for Surgical Instrument Segmentation","created":"2020-07-10","cited_by_count":67},{"id":"2102.04604","title":"SwiftNet: Real-time Video Object Segmentation","created":"2021-02-09","cited_by_count":67},{"id":"1704.05737","title":"Learning Video Object Segmentation with Visual Memory","created":"2017-04-19","cited_by_count":66},{"id":"2411.17576","title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","created":"2024-11-26","cited_by_count":66},{"id":"2106.04463","title":"A multi-centre polyp detection and segmentation dataset for generalisability assessment","created":"2021-06-08","cited_by_count":63},{"id":"2312.17183","title":"Large-Vocabulary Segmentation for Medical Images with Text Prompts","created":"2023-12-28","cited_by_count":62},{"id":"2408.04579","title":"SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More","created":"2024-08-08","cited_by_count":60},{"id":"1803.04242","title":"Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation","created":"2018-03-12","cited_by_count":56},{"id":"2004.07193","title":"A Transductive Approach for Video Object Segmentation","created":"2020-04-15","cited_by_count":55},{"id":"2307.15958","title":"XMem++: Production-level Video Segmentation From Few Annotated Frames","created":"2023-07-29","cited_by_count":53},{"id":"2408.07931","title":"Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning","created":"2024-08-15","cited_by_count":47},{"id":"2404.19326","title":"LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation","created":"2024-04-30","cited_by_count":44},{"id":"2411.17646","title":"SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation","created":"2024-11-26","cited_by_count":44},{"id":"2305.10300","title":"One-Prompt to Segment All Medical Images","created":"2023-05-17","cited_by_count":38},{"id":"2205.15361","title":"TubeFormer-DeepLab: Video Mask Transformer","created":"2022-05-30","cited_by_count":35},{"id":"2503.22268","title":"Segment Any Motion in Videos","created":"2025-03-28","cited_by_count":35},{"id":"2211.16200","title":"From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instruments","created":"2022-11-26","cited_by_count":32},{"id":"2404.12389","title":"Moving Object Segmentation: All You Need Is SAM (and Flow)","created":"2024-04-18","cited_by_count":30},{"id":"2305.18221","title":"GazeGNN: A Gaze-Guided Graph Neural Network for Chest X-ray Classification","created":"2023-05-29","cited_by_count":25},{"id":"2307.00997","title":"RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation","created":"2023-07-03","cited_by_count":25},{"id":"1508.05151","title":"Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation","created":"2015-08-21","cited_by_count":22},{"id":"2406.08476","title":"RMem: Restricted Memory Banks Improve Video Object Segmentation","created":"2024-06-12","cited_by_count":22},{"id":"2501.07256","title":"EdgeTAM: On-Device Track Anything Model","created":"2025-01-13","cited_by_count":21},{"id":"2203.11442","title":"Scalable Video Object Segmentation with Identification Mechanism","created":"2022-03-22","cited_by_count":18},{"id":"2310.12995","title":"Comprehensive Multimodal Segmentation in Medical Imaging: Combining YOLOv8 with SAM and HQ-SAM Models","created":"2023-10-04","cited_by_count":18},{"id":"2401.13051","title":"PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation","created":"2024-01-23","cited_by_count":17},{"id":"2506.01558","title":"SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes","created":"2025-06-02","cited_by_count":17},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16},{"id":"2503.12781","title":"SAM2 for Image and Video Segmentation: A Comprehensive Survey","created":"2025-03-17","cited_by_count":13},{"id":"2409.18653","title":"When SAM2 Meets Video Camouflaged Object Segmentation: A Comprehensive Evaluation and Adaptation","created":"2024-09-27","cited_by_count":11},{"id":"2306.14109","title":"When SAM Meets Sonar Images","created":"2023-06-25","cited_by_count":10},{"id":"2309.13539","title":"MediViSTA: Medical Video Segmentation via Temporal Fusion SAM Adaptation for Echocardiography","created":"2023-09-24","cited_by_count":10},{"id":"2405.01725","title":"Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey","created":"2024-05-02","cited_by_count":10},{"id":"2402.16338","title":"BLO-SAM: Bi-level Optimization Based Overfitting-Preventing Finetuning of SAM","created":"2024-02-26","cited_by_count":8},{"id":"2506.01304","title":"SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost","created":"2025-06-02","cited_by_count":8},{"id":"2403.08003","title":"Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment Anything","created":"2024-03-12","cited_by_count":7},{"id":"2505.01854","title":"Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2","created":"2025-05-03","cited_by_count":5},{"id":"2503.19119","title":"TrackRAD2025 challenge dataset: Real-time tumor tracking for MRI-guided radiotherapy","created":"2025-03-24","cited_by_count":3},{"id":"2507.14613","title":"Depthwise-Dilated Convolutional Adapters for Medical Object Tracking and Segmentation Using the Segment Anything Model 2","created":"2025-07-19","cited_by_count":2},{"id":"2503.20967","title":"Eyes Tell the Truth: GazeVal Highlights Shortcomings of Generative AI in Medical Imaging","created":"2025-03-26","cited_by_count":1}],"next_cursor":null}