{"list":"other","total":53,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"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":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2203.16220","title":"Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection","created":"2022-03-30","cited_by_count":317},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"2108.10831","title":"LLVIP: A Visible-infrared Paired Dataset for Low-light Vision","created":"2021-08-24","cited_by_count":231},{"id":"2205.07680","title":"BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models","created":"2022-05-16","cited_by_count":225},{"id":"2312.09008","title":"Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer","created":"2023-12-11","cited_by_count":196},{"id":"2309.17102","title":"Guiding Instruction-based Image Editing via Multimodal Large Language Models","created":"2023-09-29","cited_by_count":185},{"id":"2312.06739","title":"SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models","created":"2023-12-11","cited_by_count":177},{"id":"2308.02097","title":"Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation","created":"2023-08-04","cited_by_count":129},{"id":"2403.12036","title":"One-Step Image Translation with Text-to-Image Models","created":"2024-03-18","cited_by_count":116},{"id":"2503.10639","title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing","created":"2025-03-13","cited_by_count":104},{"id":"2305.15086","title":"Unpaired Image-to-Image Translation via Neural Schr\\\"odinger Bridge","created":"2023-05-24","cited_by_count":96},{"id":"2009.12664","title":"Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks","created":"2020-09-26","cited_by_count":85},{"id":"2408.16766","title":"CSGO: Content-Style Composition in Text-to-Image Generation","created":"2024-08-29","cited_by_count":78},{"id":"2404.09692","title":"XoFTR: Cross-modal Feature Matching Transformer","created":"2024-04-15","cited_by_count":48},{"id":"2412.19412","title":"MINIMA: Modality Invariant Image Matching","created":"2024-12-27","cited_by_count":47},{"id":"2501.07556","title":"MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training","created":"2025-01-13","cited_by_count":41},{"id":"2204.06183","title":"ViViD++: Vision for Visibility Dataset","created":"2022-04-13","cited_by_count":34},{"id":"2301.12689","title":"Edge-guided Multi-domain RGB-to-TIR image Translation for Training Vision Tasks with Challenging Labels","created":"2023-01-30","cited_by_count":30},{"id":"2303.17386","title":"Complementary Random Masking for RGB-Thermal Semantic Segmentation","created":"2023-03-30","cited_by_count":27},{"id":"2501.11319","title":"StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer","created":"2025-01-20","cited_by_count":23},{"id":"1902.10892","title":"Sparse Depth Enhanced Direct Thermal-infrared SLAM Beyond the Visible Spectrum","created":"2019-02-28","cited_by_count":22},{"id":"2403.08997","title":"Caltech Aerial RGB-Thermal Dataset in the Wild","created":"2024-03-13","cited_by_count":19},{"id":"2403.20142","title":"StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation","created":"2024-03-29","cited_by_count":18},{"id":"2403.07860","title":"Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation","created":"2024-03-12","cited_by_count":17},{"id":"2407.09299","title":"PID: Physics-Informed Diffusion Model for Infrared Image Generation","created":"2024-07-12","cited_by_count":17},{"id":"2503.19012","title":"DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understanding","created":"2025-03-24","cited_by_count":16},{"id":"2401.13853","title":"Dataset and Benchmark: Novel Sensors for Autonomous Vehicle Perception","created":"2024-01-24","cited_by_count":15},{"id":"2405.12944","title":"AMFD: Distillation via Adaptive Multimodal Fusion for Multispectral Pedestrian Detection","created":"2024-05-21","cited_by_count":15},{"id":"2509.24878","title":"ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation","created":"2025-09-29","cited_by_count":14},{"id":"2408.00969","title":"Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion Approach","created":"2024-08-02","cited_by_count":13},{"id":"2407.10125","title":"When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset","created":"2024-07-14","cited_by_count":10},{"id":"2007.00622","title":"A Multi-spectral Dataset for Evaluating Motion Estimation Systems","created":"2020-07-01","cited_by_count":8},{"id":"2504.02801","title":"F-ViTA: Foundation Model Guided Visible to Thermal Translation","created":"2025-04-03","cited_by_count":7},{"id":"2404.07072","title":"Implicit Multi-Spectral Transformer: An Lightweight and Effective Visible to Infrared Image Translation Model","created":"2024-04-10","cited_by_count":6},{"id":"2410.18340","title":"Thermal Chameleon: Task-Adaptive Tone-mapping for Radiometric Thermal-Infrared images","created":"2024-10-24","cited_by_count":3}],"next_cursor":null}