{"list":"other","total":103,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1702.05747","title":"A Survey on Deep Learning in Medical Image Analysis","created":"2017-02-19","cited_by_count":1186},{"id":"1802.04712","title":"Attention-based Deep Multiple Instance Learning","created":"2018-02-13","cited_by_count":1095},{"id":"2004.09666","title":"Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images","created":"2020-04-20","cited_by_count":745},{"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":"2206.02647","title":"Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning","created":"2022-06-06","cited_by_count":359},{"id":"2403.06135","title":"MACE: Mass Concept Erasure in Diffusion Models","created":"2024-03-10","cited_by_count":307},{"id":"2203.12081","title":"DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification","created":"2022-03-22","cited_by_count":256},{"id":"2307.12493","title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","created":"2023-07-24","cited_by_count":182},{"id":"1902.06543","title":"Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology","created":"2019-02-18","cited_by_count":173},{"id":"1912.12378","title":"Deep neural network models for computational histopathology: A survey","created":"2019-12-28","cited_by_count":165},{"id":"2411.19666","title":"Multimodal Whole Slide Foundation Model for Pathology","created":"2024-11-29","cited_by_count":162},{"id":"2511.18870","title":"HunyuanVideo 1.5 Technical Report","created":"2025-11-24","cited_by_count":160},{"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":"2412.20413","title":"EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers","created":"2024-12-29","cited_by_count":95},{"id":"2303.06873","title":"Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Images","created":"2023-03-13","cited_by_count":91},{"id":"2402.17228","title":"Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology","created":"2024-02-27","cited_by_count":67},{"id":"2407.02158","title":"UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks","created":"2024-07-02","cited_by_count":65},{"id":"2108.09079","title":"Structure-Preserving Deraining with Residue Channel Prior Guidance","created":"2021-08-20","cited_by_count":63},{"id":"2308.14103","title":"Towards Unified Token Learning for Vision-Language Tracking","created":"2023-08-27","cited_by_count":62},{"id":"2504.12782","title":"Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts","created":"2025-04-17","cited_by_count":62},{"id":"2307.15254","title":"Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification","created":"2023-07-28","cited_by_count":60},{"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":"2406.07255","title":"Towards Realistic Data Generation for Real-World Super-Resolution","created":"2024-06-11","cited_by_count":56},{"id":"2206.04425","title":"Multiple Instance Learning for Digital Pathology: A Review on the State-of-the-Art, Limitations & Future Potential","created":"2022-06-09","cited_by_count":54},{"id":"2503.23580","title":"DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution","created":"2025-03-30","cited_by_count":53},{"id":"2408.09110","title":"Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community","created":"2024-08-17","cited_by_count":50},{"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":"2401.10090","title":"Cross-Modality Perturbation Synergy Attack for Person Re-identification","created":"2024-01-18","cited_by_count":45},{"id":"2405.07023","title":"Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolution","created":"2024-05-11","cited_by_count":37},{"id":"2509.21278","title":"Does FLUX Already Know How to Perform Physically Plausible Image Composition?","created":"2025-09-25","cited_by_count":32},{"id":"2507.20177","title":"Towards Universal Modal Tracking with Online Dense Temporal Token Learning","created":"2025-07-27","cited_by_count":30},{"id":"2112.08655","title":"Feature Distillation Interaction Weighting Network for Lightweight Image Super-Resolution","created":"2021-12-16","cited_by_count":29},{"id":"2510.02253","title":"DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing","created":"2025-10-02","cited_by_count":29},{"id":"2501.16583","title":"Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restoration","created":"2025-01-27","cited_by_count":28},{"id":"2508.07901","title":"Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation","created":"2025-08-11","cited_by_count":28},{"id":"2312.06162","title":"Textual Prompt Guided Image Restoration","created":"2023-12-11","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":"2504.04517","title":"Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection","created":"2025-04-06","cited_by_count":24},{"id":"2401.10512","title":"Exploring Color Invariance through Image-Level Ensemble Learning","created":"2024-01-19","cited_by_count":23},{"id":"2407.13640","title":"Beyond Augmentation: Empowering Model Robustness under Extreme Capture Environments","created":"2024-07-18","cited_by_count":23},{"id":"2411.16800","title":"Phys4DGen: Physics-Compliant 4D Generation with Multi-Material Composition Perception","created":"2024-11-25","cited_by_count":23},{"id":"2507.21606","title":"Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Tracking","created":"2025-07-29","cited_by_count":23},{"id":"2510.10581","title":"GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search","created":"2025-10-12","cited_by_count":23},{"id":"2412.09465","title":"OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs","created":"2024-12-12","cited_by_count":22},{"id":"2502.08333","title":"Foundation Models in Computational Pathology: A Review of Challenges, Opportunities, and Impact","created":"2025-02-12","cited_by_count":22},{"id":"2507.20291","title":"Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training","created":"2025-07-27","cited_by_count":21},{"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":"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":"2407.19768","title":"Efficient Face Super-Resolution via Wavelet-based Feature Enhancement Network","created":"2024-07-29","cited_by_count":18},{"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":"2207.02796","title":"Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution","created":"2022-07-06","cited_by_count":16},{"id":"2402.04855","title":"Dual-Path Coupled Image Deraining Network via Spatial-Frequency Interaction","created":"2024-02-07","cited_by_count":16},{"id":"2406.04280","title":"xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology","created":"2024-06-06","cited_by_count":16},{"id":"2501.15724","title":"A Survey on Computational Pathology Foundation Models: Datasets, Adaptation Strategies, and Evaluation Tasks","created":"2025-01-27","cited_by_count":16},{"id":"2504.00870","title":"Data-free Knowledge Distillation with Diffusion Models","created":"2025-04-01","cited_by_count":16},{"id":"2408.10145","title":"Multi-Scale Representation Learning for Image Restoration with State-Space Model","created":"2024-08-19","cited_by_count":15},{"id":"2503.07191","title":"All That Glitters Is Not Gold: Key-Secured 3D Secrets within 3D Gaussian Splatting","created":"2025-03-10","cited_by_count":15},{"id":"2511.20186","title":"Exo2EgoSyn: Unlocking Foundation Video Generation Models for Exocentric-to-Egocentric Video Synthesis","created":"2025-11-25","cited_by_count":15},{"id":"2102.12135","title":"Efficient and Accurate Multi-scale Topological Network for Single Image Dehazing","created":"2021-02-24","cited_by_count":14},{"id":"2310.08276","title":"Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval","created":"2023-10-12","cited_by_count":14},{"id":"2407.03757","title":"DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts","created":"2024-07-04","cited_by_count":14},{"id":"2504.02362","title":"Brightness Perceiving for Recursive Low-Light Image Enhancement","created":"2025-04-03","cited_by_count":14},{"id":"2508.09173","title":"Camel: Energy-Aware LLM Inference on Resource-Constrained Devices","created":"2025-08-07","cited_by_count":14},{"id":"2508.16830","title":"AIM 2025 Low-light RAW Video Denoising Challenge: Dataset, Methods and Results","created":"2025-08-22","cited_by_count":14},{"id":"2511.20886","title":"V$^{2}$-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence","created":"2025-11-25","cited_by_count":14},{"id":"2212.14181","title":"Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network","created":"2022-12-29","cited_by_count":13},{"id":"2309.04780","title":"Latent Degradation Representation Constraint for Single Image Deraining","created":"2023-09-09","cited_by_count":13},{"id":"2508.03077","title":"RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions","created":"2025-08-05","cited_by_count":13},{"id":"2411.11906","title":"$\\text{S}^{3}$Mamba: Arbitrary-Scale Super-Resolution via Scaleable State Space Model","created":"2024-11-16","cited_by_count":12},{"id":"2505.12108","title":"EarthSynth: Generating Informative Earth Observation with Diffusion Models","created":"2025-05-17","cited_by_count":12},{"id":"2406.07006","title":"MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results","created":"2024-06-11","cited_by_count":11},{"id":"2406.14912","title":"FC3DNet: A Fully Connected Encoder-Decoder for Efficient Demoir'eing","created":"2024-06-21","cited_by_count":11},{"id":"2503.17132","title":"Temporal-Guided Spiking Neural Networks for Event-Based Human Action Recognition","created":"2025-03-21","cited_by_count":11},{"id":"2510.03302","title":"Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models","created":"2025-09-30","cited_by_count":11},{"id":"2509.23584","title":"VividFace: High-Quality and Efficient One-Step Diffusion For Video Face Enhancement","created":"2025-09-28","cited_by_count":10},{"id":"2109.04381","title":"Copy-Move Image Forgery Detection Based on Evolving Circular Domains Coverage","created":"2021-09-09","cited_by_count":9},{"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":"2503.10047","title":"Dual-domain Modulation Network for Lightweight Image Super-Resolution","created":"2025-03-13","cited_by_count":8},{"id":"2510.12114","title":"Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration","created":"2025-10-14","cited_by_count":8},{"id":"2507.21816","title":"Control Copy-Paste: Controllable Diffusion-Based Augmentation Method for Remote Sensing Few-Shot Object Detection","created":"2025-07-29","cited_by_count":7},{"id":"2511.00908","title":"GraphGeo: Multi-Agent Debate Framework for Visual Geo-localization with Heterogeneous Graph Neural Networks","created":"2025-11-02","cited_by_count":6},{"id":"2511.18031","title":"Diverse Instance Generation via Diffusion Models for Enhanced Few-Shot Object Detection in Remote Sensing Images","created":"2025-11-22","cited_by_count":5},{"id":"2511.18677","title":"A Theory-Inspired Framework for Few-Shot Cross-Modal Sketch Person Re-Identification","created":"2025-11-24","cited_by_count":5},{"id":"2601.00322","title":"Depth-Synergized Mamba Meets Memory Experts for All-Day Image Reflection Separation","created":"2026-01-01","cited_by_count":5},{"id":"2508.01602","title":"Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment","created":"2025-08-03","cited_by_count":4},{"id":"2511.12419","title":"Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion Guidance","created":"2025-11-16","cited_by_count":4},{"id":"2511.14213","title":"Measurement-Constrained Sampling for Text-Prompted Blind Face Restoration","created":"2025-11-18","cited_by_count":4},{"id":"2503.10043","title":"FourierSR: A Fourier Token-based Plugin for Efficient Image Super-Resolution","created":"2025-03-13","cited_by_count":3},{"id":"2509.12715","title":"AsyMoE: Leveraging Modal Asymmetry for Enhanced Expert Specialization in Large Vision-Language Models","created":"2025-09-16","cited_by_count":3},{"id":"2511.00911","title":"G2rammar: Bilingual Grammar Modeling for Enhanced Text-attributed Graph Learning","created":"2025-11-02","cited_by_count":3},{"id":"2509.18593","title":"SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolution","created":"2025-09-23","cited_by_count":2},{"id":"2510.10611","title":"HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication","created":"2025-10-12","cited_by_count":2}],"next_cursor":"100"}