{"list":"other","total":84,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2004.09666","title":"Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images","created":"2020-04-20","cited_by_count":745},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2106.00908","title":"TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification","created":"2021-06-02","cited_by_count":555},{"id":"2011.08939","title":"Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning","created":"2020-11-17","cited_by_count":478},{"id":"2209.07511","title":"Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models","created":"2022-09-15","cited_by_count":382},{"id":"2206.02647","title":"Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning","created":"2022-06-06","cited_by_count":359},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"2307.12493","title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","created":"2023-07-24","cited_by_count":182},{"id":"2411.19666","title":"Multimodal Whole Slide Foundation Model for Pathology","created":"2024-11-29","cited_by_count":162},{"id":"1504.07947","title":"Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification","created":"2015-04-29","cited_by_count":159},{"id":"2212.04690","title":"Benchmarking Self-Supervised Learning on Diverse Pathology Datasets","created":"2022-12-09","cited_by_count":150},{"id":"2306.07831","title":"Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images","created":"2023-06-13","cited_by_count":134},{"id":"2111.04740","title":"BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images","created":"2021-11-08","cited_by_count":132},{"id":"2401.01686","title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","created":"2024-01-03","cited_by_count":129},{"id":"2410.18775","title":"Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances","created":"2024-10-24","cited_by_count":110},{"id":"2212.04145","title":"Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation","created":"2022-12-08","cited_by_count":98},{"id":"2412.20413","title":"EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers","created":"2024-12-29","cited_by_count":95},{"id":"2305.11003","title":"Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping","created":"2023-05-18","cited_by_count":92},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89},{"id":"2302.02551","title":"CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets","created":"2023-02-06","cited_by_count":79},{"id":"2406.11138","title":"Diffusion Models in Low-Level Vision: A Survey","created":"2024-06-17","cited_by_count":74},{"id":"2311.11638","title":"Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model","created":"2023-11-20","cited_by_count":69},{"id":"2407.02158","title":"UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks","created":"2024-07-02","cited_by_count":65},{"id":"2504.12782","title":"Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts","created":"2025-04-17","cited_by_count":62},{"id":"2407.15362","title":"A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model","created":"2024-07-22","cited_by_count":59},{"id":"2404.10343","title":"The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report","created":"2024-04-16","cited_by_count":57},{"id":"2111.09571","title":"Person Re-identification Method Based on Color Attack and Joint Defence","created":"2021-11-18","cited_by_count":56},{"id":"2308.03166","title":"Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects","created":"2023-08-06","cited_by_count":56},{"id":"2406.07255","title":"Towards Realistic Data Generation for Real-World Super-Resolution","created":"2024-06-11","cited_by_count":56},{"id":"2501.16652","title":"Molecular-driven Foundation Model for Oncologic Pathology","created":"2025-01-28","cited_by_count":55},{"id":"2401.02460","title":"Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions","created":"2024-01-04","cited_by_count":54},{"id":"2503.06617","title":"Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling","created":"2025-03-09","cited_by_count":48},{"id":"2401.01724","title":"Lightweight Adaptive Feature De-drifting for Compressed Image Classification","created":"2024-01-03","cited_by_count":46},{"id":"2210.03664","title":"Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image Classification","created":"2022-10-07","cited_by_count":43},{"id":"2305.17891","title":"The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification","created":"2023-05-29","cited_by_count":41},{"id":"2206.08861","title":"DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classification","created":"2022-06-17","cited_by_count":40},{"id":"2506.17612","title":"JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent","created":"2025-06-21","cited_by_count":39},{"id":"2405.07023","title":"Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolution","created":"2024-05-11","cited_by_count":37},{"id":"2408.14562","title":"A Survey of Camouflaged Object Detection and Beyond","created":"2024-08-26","cited_by_count":37},{"id":"2102.02996","title":"Deep Texture-Aware Features for Camouflaged Object Detection","created":"2021-02-05","cited_by_count":36},{"id":"2307.07829","title":"HQG-Net: Unpaired Medical Image Enhancement with High-Quality Guidance","created":"2023-07-15","cited_by_count":36},{"id":"2308.03063","title":"M$^3$Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition","created":"2023-08-06","cited_by_count":34},{"id":"2504.04158","title":"JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration","created":"2025-04-05","cited_by_count":34},{"id":"2507.20177","title":"Towards Universal Modal Tracking with Online Dense Temporal Token Learning","created":"2025-07-27","cited_by_count":30},{"id":"2208.08789","title":"Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis","created":"2022-08-18","cited_by_count":29},{"id":"2312.06162","title":"Textual Prompt Guided Image Restoration","created":"2023-12-11","cited_by_count":27},{"id":"2402.19326","title":"Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction","created":"2024-02-29","cited_by_count":27},{"id":"2411.10798","title":"Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolution","created":"2024-11-16","cited_by_count":26},{"id":"2407.13640","title":"Beyond Augmentation: Empowering Model Robustness under Extreme Capture Environments","created":"2024-07-18","cited_by_count":23},{"id":"2307.02249","title":"Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Good Instance Classifier is All You Need","created":"2023-07-05","cited_by_count":22},{"id":"2505.06683","title":"UnfoldIR: Rethinking Deep Unfolding Network in Illumination Degradation Image Restoration","created":"2025-05-10","cited_by_count":22},{"id":"2412.13126","title":"Knowledge-enhanced Pretraining for Vision-language Pathology Foundation Model on Cancer Diagnosis","created":"2024-12-17","cited_by_count":21},{"id":"2406.05205","title":"CPLIP: Zero-Shot Learning for Histopathology with Comprehensive Vision-Language Alignment","created":"2024-06-07","cited_by_count":20},{"id":"2404.16484","title":"Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey","created":"2024-04-25","cited_by_count":19},{"id":"2407.13646","title":"Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking","created":"2024-07-18","cited_by_count":19},{"id":"2411.06456","title":"Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restoration","created":"2024-11-10","cited_by_count":19},{"id":"2412.00878","title":"Beyond Pixels: Text Enhances Generalization in Real-World Image Restoration","created":"2024-12-01","cited_by_count":17},{"id":"2505.12266","title":"PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement","created":"2025-05-18","cited_by_count":17},{"id":"2402.04855","title":"Dual-Path Coupled Image Deraining Network via Spatial-Frequency Interaction","created":"2024-02-07","cited_by_count":16},{"id":"2504.00870","title":"Data-free Knowledge Distillation with Diffusion Models","created":"2025-04-01","cited_by_count":16},{"id":"2504.04045","title":"A Survey of Pathology Foundation Model: Progress and Future Directions","created":"2025-04-05","cited_by_count":16},{"id":"2407.03757","title":"DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts","created":"2024-07-04","cited_by_count":14},{"id":"2408.16540","title":"GRPose: Learning Graph Relations for Human Image Generation with Pose Priors","created":"2024-08-29","cited_by_count":14},{"id":"2406.16477","title":"DaLPSR: Leverage Degradation-Aligned Language Prompt for Real-World Image Super-Resolution","created":"2024-06-24","cited_by_count":9},{"id":"2504.01873","title":"A Diffusion-Based Framework for Occluded Object Movement","created":"2025-04-02","cited_by_count":5},{"id":"2504.15054","title":"Structure-guided Diffusion Transformer for Low-Light Image Enhancement","created":"2025-04-21","cited_by_count":4},{"id":"2409.04631","title":"Zero-Shot Whole Slide Image Retrieval in Histopathology Using Embeddings of Foundation Models","created":"2024-09-06","cited_by_count":2}],"next_cursor":null}