{"total":349,"rows":[{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687,"area":null},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543,"area":null},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2305.14720","title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","created":"2023-05-24","cited_by_count":442,"area":null},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365,"area":null},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304,"area":null},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294,"area":null},{"id":"2307.06948","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","created":"2023-07-13","cited_by_count":272,"area":null},{"id":"2301.00785","title":"CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection","created":"2023-01-02","cited_by_count":224,"area":null},{"id":"2310.05916","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","created":"2023-10-09","cited_by_count":196,"area":null},{"id":"2211.14813","title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","created":"2022-11-27","cited_by_count":164,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2206.07045","title":"ReCo: Retrieve and Co-segment for Zero-shot Transfer","created":"2022-06-14","cited_by_count":117,"area":null},{"id":"2308.01907","title":"The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World","created":"2023-08-03","cited_by_count":116,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2404.18929","title":"DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing","created":"2024-04-29","cited_by_count":94,"area":null},{"id":"2303.04748","title":"CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP","created":"2023-03-08","cited_by_count":89,"area":null},{"id":"2401.01970","title":"FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding","created":"2024-01-03","cited_by_count":86,"area":null},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72,"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":"2304.04909","title":"SATR: Zero-Shot Semantic Segmentation of 3D Shapes","created":"2023-04-11","cited_by_count":62,"area":null},{"id":"2304.05396","title":"SAM.MD: Zero-shot medical image segmentation capabilities of the Segment Anything Model","created":"2023-04-10","cited_by_count":61,"area":null},{"id":"2307.09220","title":"A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future","created":"2023-07-18","cited_by_count":61,"area":null},{"id":"2404.03421","title":"Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View","created":"2024-04-04","cited_by_count":61,"area":null},{"id":"2305.10724","title":"Segment Any Anomaly without Training via Hybrid Prompt Regularization","created":"2023-05-18","cited_by_count":60,"area":null},{"id":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2212.03863","title":"X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion","created":"2022-12-07","cited_by_count":49,"area":null},{"id":"2312.16580","title":"VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting","created":"2023-12-27","cited_by_count":45,"area":null},{"id":"2303.02401","title":"Open-Vocabulary Affordance Detection in 3D Point Clouds","created":"2023-03-04","cited_by_count":41,"area":null},{"id":"2312.07353","title":"CLIP in Medical Imaging: A Survey","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2507.05631","title":"OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval","created":"2025-07-08","cited_by_count":40,"area":null},{"id":"2309.07125","title":"Text-Guided Generation and Editing of Compositional 3D Avatars","created":"2023-09-13","cited_by_count":39,"area":null},{"id":"2312.02975","title":"Dexterous Functional Grasping","created":"2023-12-05","cited_by_count":39,"area":null},{"id":"2410.00263","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","created":"2024-09-30","cited_by_count":39,"area":null},{"id":"2411.09219","title":"Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation","created":"2024-11-14","cited_by_count":39,"area":null},{"id":"2407.12957","title":"R+X: Retrieval and Execution from Everyday Human Videos","created":"2024-07-17","cited_by_count":38,"area":null},{"id":"2312.09246","title":"SHAP-EDITOR: Instruction-guided Latent 3D Editing in Seconds","created":"2023-12-14","cited_by_count":37,"area":null},{"id":"2312.11782","title":"Learning Object State Changes in Videos: An Open-World Perspective","created":"2023-12-19","cited_by_count":36,"area":null},{"id":"2406.04341","title":"Interpreting the Second-Order Effects of Neurons in CLIP","created":"2024-06-06","cited_by_count":36,"area":null},{"id":"2212.06858","title":"LidarCLIP or: How I Learned to Talk to Point Clouds","created":"2022-12-13","cited_by_count":33,"area":null},{"id":"2307.16620","title":"Audio-Visual Segmentation by Exploring Cross-Modal Mutual Semantics","created":"2023-07-31","cited_by_count":32,"area":null},{"id":"2306.05399","title":"Matting Anything","created":"2023-06-08","cited_by_count":31,"area":null},{"id":"2310.05107","title":"OV-PARTS: Towards Open-Vocabulary Part Segmentation","created":"2023-10-08","cited_by_count":31,"area":null},{"id":"2405.18356","title":"Universal and Extensible Language-Vision Models for Organ Segmentation and Tumor Detection from Abdominal Computed Tomography","created":"2024-05-28","cited_by_count":31,"area":null},{"id":"2409.18431","title":"Search3D: Hierarchical Open-Vocabulary 3D Segmentation","created":"2024-09-27","cited_by_count":31,"area":null},{"id":"2211.09935","title":"CAPE: Corrective Actions from Precondition Errors using Large Language Models","created":"2022-11-17","cited_by_count":30,"area":null},{"id":"2411.12814","title":"Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline","created":"2024-11-19","cited_by_count":30,"area":null},{"id":"2308.11974","title":"Blending-NeRF: Text-Driven Localized Editing in Neural Radiance Fields","created":"2023-08-23","cited_by_count":28,"area":null},{"id":"2404.02845","title":"Cross-Modal Conditioned Reconstruction for Language-guided Medical Image Segmentation","created":"2024-04-03","cited_by_count":28,"area":null},{"id":"2406.20081","title":"Segment Anything without Supervision","created":"2024-06-28","cited_by_count":28,"area":null},{"id":"2501.10913","title":"Know \"No\" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP","created":"2025-01-19","cited_by_count":28,"area":null},{"id":"2310.19001","title":"Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation","created":"2023-10-29","cited_by_count":27,"area":null},{"id":"2403.01482","title":"EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation","created":"2024-03-03","cited_by_count":27,"area":null},{"id":"2408.06627","title":"WorldScribe: Towards Context-Aware Live Visual Descriptions","created":"2024-08-13","cited_by_count":27,"area":null},{"id":"2211.13854","title":"ComCLIP: Training-Free Compositional Image and Text Matching","created":"2022-11-25","cited_by_count":26,"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":"2404.06362","title":"Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2601.10880","title":"Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation","created":"2026-01-15","cited_by_count":25,"area":null},{"id":"2403.13805","title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","created":"2024-03-20","cited_by_count":24,"area":null},{"id":"2206.05149","title":"Referring Image Matting","created":"2022-06-10","cited_by_count":22,"area":null},{"id":"2210.14142","title":"From colouring-in to pointillism: revisiting semantic segmentation supervision","created":"2022-10-25","cited_by_count":22,"area":null},{"id":"2307.02003","title":"Multi-Modal Prototypes for Open-World Semantic Segmentation","created":"2023-07-05","cited_by_count":22,"area":null},{"id":"2407.13675","title":"MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis","created":"2024-07-18","cited_by_count":22,"area":null},{"id":"2508.00265","title":"Multimodal Referring Segmentation: A Survey","created":"2025-08-01","cited_by_count":22,"area":null},{"id":"2307.10782","title":"See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data","created":"2023-07-20","cited_by_count":21,"area":null},{"id":"2310.14277","title":"A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application","created":"2023-10-22","cited_by_count":21,"area":null},{"id":"2311.16516","title":"Segment Every Out-of-Distribution Object","created":"2023-11-27","cited_by_count":21,"area":null},{"id":"2312.16797","title":"Multi-Prompts Learning with Cross-Modal Alignment for Attribute-based Person Re-Identification","created":"2023-12-28","cited_by_count":20,"area":null},{"id":"2404.09447","title":"kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies","created":"2024-04-15","cited_by_count":20,"area":null},{"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":"2408.14826","title":"Alfie: Democratising RGBA Image Generation With No $$$","created":"2024-08-27","cited_by_count":20,"area":null},{"id":"2306.07532","title":"Referring Camouflaged Object Detection","created":"2023-06-13","cited_by_count":19,"area":null},{"id":"2308.05938","title":"FoodSAM: Any Food Segmentation","created":"2023-08-11","cited_by_count":19,"area":null},{"id":"2308.07539","title":"Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond","created":"2023-08-15","cited_by_count":19,"area":null},{"id":"2406.11507","title":"Prior Normality Prompt Transformer for Multi-class Industrial Image Anomaly Detection","created":"2024-06-17","cited_by_count":19,"area":null},{"id":"2311.15607","title":"Spatially Covariant Image Registration with Text Prompts","created":"2023-11-27","cited_by_count":18,"area":null},{"id":"2405.01002","title":"Spider: A Unified Framework for Context-dependent Concept Segmentation","created":"2024-05-02","cited_by_count":18,"area":null},{"id":"2312.04554","title":"Improved Visual Grounding through Self-Consistent Explanations","created":"2023-12-07","cited_by_count":17,"area":null},{"id":"2312.09313","title":"LatentEditor: Text Driven Local Editing of 3D Scenes","created":"2023-12-14","cited_by_count":17,"area":null},{"id":"2304.06385","title":"TransHP: Image Classification with Hierarchical Prompting","created":"2023-04-13","cited_by_count":16,"area":null},{"id":"2304.10782","title":"Contrastive Language, Action, and State Pre-training for Robot Learning","created":"2023-04-21","cited_by_count":16,"area":null},{"id":"2305.12452","title":"Advancing Referring Expression Segmentation Beyond Single Image","created":"2023-05-21","cited_by_count":16,"area":null},{"id":"2402.11498","title":"Verifiably Following Complex Robot Instructions with Foundation Models","created":"2024-02-18","cited_by_count":16,"area":null},{"id":"2403.05435","title":"OmniCount: Multi-label Object Counting with Semantic-Geometric Priors","created":"2024-03-08","cited_by_count":16,"area":null},{"id":"2407.10488","title":"How and where does CLIP process negation?","created":"2024-07-15","cited_by_count":16,"area":null},{"id":"2405.10185","title":"DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data","created":"2024-05-16","cited_by_count":15,"area":null},{"id":"2308.15226","title":"CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation","created":"2023-08-29","cited_by_count":14,"area":null},{"id":"2310.07056","title":"TextPSG: Panoptic Scene Graph Generation from Textual Descriptions","created":"2023-10-10","cited_by_count":14,"area":null},{"id":"2311.04066","title":"Can CLIP Help Sound Source Localization?","created":"2023-11-07","cited_by_count":14,"area":null},{"id":"2403.12415","title":"VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation","created":"2024-03-19","cited_by_count":14,"area":null},{"id":"2405.12461","title":"WorldAfford: Affordance Grounding based on Natural Language Instructions","created":"2024-05-21","cited_by_count":14,"area":null},{"id":"2410.17772","title":"Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models","created":"2024-10-23","cited_by_count":14,"area":null},{"id":"2403.02580","title":"What do we learn from inverting CLIP models?","created":"2024-03-05","cited_by_count":13,"area":null},{"id":"2306.02240","title":"ProTeCt: Prompt Tuning for Taxonomic Open Set Classification","created":"2023-06-04","cited_by_count":12,"area":null},{"id":"2306.09008","title":"Exploring the Application of Large-scale Pre-trained Models on Adverse Weather Removal","created":"2023-06-15","cited_by_count":12,"area":null},{"id":"2403.09281","title":"CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification","created":"2024-03-14","cited_by_count":12,"area":null},{"id":"2402.00407","title":"InfMAE: A Foundation Model in the Infrared Modality","created":"2024-02-01","cited_by_count":11,"area":null},{"id":"2409.07683","title":"Open-Vocabulary Remote Sensing Image Semantic Segmentation","created":"2024-09-12","cited_by_count":11,"area":null},{"id":"2504.21432","title":"UAV-VLN: End-to-End Vision Language guided Navigation for UAVs","created":"2025-04-30","cited_by_count":11,"area":null},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null}],"next_cursor":"100"}