{"list":"other","total":63,"rows":[{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"id":"2203.11991","title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","created":"2022-03-22","cited_by_count":330},{"id":"1905.13545","title":"High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks","created":"2019-05-28","cited_by_count":310},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307},{"id":"2403.06135","title":"MACE: Mass Concept Erasure in Diffusion Models","created":"2024-03-10","cited_by_count":307},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260},{"id":"2307.12493","title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","created":"2023-07-24","cited_by_count":182},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"id":"2203.05962","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","created":"2022-03-09","cited_by_count":136},{"id":"2401.01686","title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","created":"2024-01-03","cited_by_count":129},{"id":"1805.08982","title":"RGB-T Object Tracking:Benchmark and Baseline","created":"2018-05-23","cited_by_count":121},{"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":"2205.12956","title":"Inception Transformer","created":"2022-05-25","cited_by_count":99},{"id":"2104.13202","title":"LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking","created":"2021-04-27","cited_by_count":96},{"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":"2204.04120","title":"Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline","created":"2022-04-08","cited_by_count":91},{"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":"2311.15851","title":"Single-Model and Any-Modality for Video Object Tracking","created":"2023-11-27","cited_by_count":65},{"id":"1908.11714","title":"Multi-Modal Fusion for End-to-End RGB-T Tracking","created":"2019-08-30","cited_by_count":63},{"id":"2504.12782","title":"Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts","created":"2025-04-17","cited_by_count":62},{"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":"2007.13143","title":"Challenge-Aware RGBT Tracking","created":"2020-07-26","cited_by_count":53},{"id":"2312.10611","title":"Bi-directional Adapter for Multi-modal Tracking","created":"2023-12-17","cited_by_count":46},{"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":"2403.16002","title":"SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking","created":"2024-03-24","cited_by_count":44},{"id":"2101.08533","title":"Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method","created":"2021-01-21","cited_by_count":42},{"id":"1907.10451","title":"Dense Feature Aggregation and Pruning for RGBT Tracking","created":"2019-07-24","cited_by_count":40},{"id":"2302.02367","title":"FastPillars: A Deployment-friendly Pillar-based 3D Detector","created":"2023-02-05","cited_by_count":39},{"id":"1907.07485","title":"Multi-Adapter RGBT Tracking","created":"2019-07-17","cited_by_count":38},{"id":"2505.14454","title":"Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models","created":"2025-05-20","cited_by_count":38},{"id":"2408.14562","title":"A Survey of Camouflaged Object Detection and Beyond","created":"2024-08-26","cited_by_count":37},{"id":"2307.07829","title":"HQG-Net: Unpaired Medical Image Enhancement with High-Quality Guidance","created":"2023-07-15","cited_by_count":36},{"id":"2011.07188","title":"Duality-Gated Mutual Condition Network for RGBT Tracking","created":"2020-11-14","cited_by_count":35},{"id":"2107.10433","title":"MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking","created":"2021-07-22","cited_by_count":32},{"id":"2501.05179","title":"Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models","created":"2025-01-09","cited_by_count":32},{"id":"2401.01244","title":"Temporal Adaptive RGBT Tracking with Modality Prompt","created":"2024-01-02","cited_by_count":30},{"id":"2411.01327","title":"Visual Fourier Prompt Tuning","created":"2024-11-02","cited_by_count":30},{"id":"2401.15865","title":"LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection","created":"2024-01-29","cited_by_count":29},{"id":"2505.19147","title":"Shifting AI Efficiency From Model-Centric to Data-Centric Compression","created":"2025-05-25","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":"2501.18783","title":"RUN: Reversible Unfolding Network for Concealed Object Segmentation","created":"2025-01-30","cited_by_count":28},{"id":"2505.06683","title":"UnfoldIR: Rethinking Deep Unfolding Network in Illumination Degradation Image Restoration","created":"2025-05-10","cited_by_count":22},{"id":"2502.12913","title":"GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning","created":"2025-02-18","cited_by_count":21},{"id":"2208.08829","title":"Learning Spatial-Frequency Transformer for Visual Object Tracking","created":"2022-08-18","cited_by_count":18},{"id":"2404.00288","title":"Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration","created":"2024-03-30","cited_by_count":18},{"id":"2409.09324","title":"Efficient Fine-Tuning of Large Language Models for Automated Medical Documentation","created":"2024-09-14","cited_by_count":16},{"id":"2409.12421","title":"Frequency-Guided Spatial Adaptation for Camouflaged Object Detection","created":"2024-09-19","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":"2405.18734","title":"Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encoder","created":"2024-05-29","cited_by_count":14},{"id":"2509.09119","title":"Sensitivity-LoRA: Low-Load Sensitivity-Based Fine-Tuning for Large Language Models","created":"2025-09-11","cited_by_count":14},{"id":"2209.10158","title":"Position-Aware Relation Learning for RGB-Thermal Salient Object Detection","created":"2022-09-21","cited_by_count":12},{"id":"2401.01674","title":"Transformer RGBT Tracking with Spatio-Temporal Multimodal Tokens","created":"2024-01-03","cited_by_count":11},{"id":"2407.01131","title":"M2IST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression Comprehension","created":"2024-07-01","cited_by_count":11},{"id":"2507.18531","title":"IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning","created":"2025-07-24","cited_by_count":7},{"id":"2410.01841","title":"A GEN AI Framework for Medical Note Generation","created":"2024-09-27","cited_by_count":6},{"id":"2410.22837","title":"SFDFusion: An Efficient Spatial-Frequency Domain Fusion Network for Infrared and Visible Image Fusion","created":"2024-10-30","cited_by_count":6},{"id":"2508.15845","title":"Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports","created":"2025-08-19","cited_by_count":1}],"next_cursor":null}