{"list":"other","total":59,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2106.02634","title":"Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering","created":"2021-06-04","cited_by_count":332},{"id":"2308.08089","title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","created":"2023-08-16","cited_by_count":264},{"id":"2310.02601","title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control","created":"2023-10-04","cited_by_count":252},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250},{"id":"2406.02509","title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","created":"2024-06-04","cited_by_count":166},{"id":"2403.07420","title":"DragAnything: Motion Control for Anything using Entity Representation","created":"2024-03-12","cited_by_count":159},{"id":"2410.15957","title":"CamI2V: Camera-Controlled Image-to-Video Diffusion Model","created":"2024-10-21","cited_by_count":120},{"id":"2203.09283","title":"PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation","created":"2022-03-17","cited_by_count":95},{"id":"2203.00867","title":"Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding","created":"2022-03-02","cited_by_count":83},{"id":"2302.08908","title":"LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation","created":"2023-02-16","cited_by_count":65},{"id":"2306.04607","title":"GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation","created":"2023-06-07","cited_by_count":56},{"id":"2312.14457","title":"QUAR-VLA: Vision-Language-Action Model for Quadruped Robots","created":"2023-12-22","cited_by_count":56},{"id":"2207.11860","title":"Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation","created":"2022-07-25","cited_by_count":46},{"id":"2205.05570","title":"Review on Panoramic Imaging and Its Applications in Scene Understanding","created":"2022-05-11","cited_by_count":43},{"id":"1909.07721","title":"DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing","created":"2019-09-17","cited_by_count":30},{"id":"2202.13388","title":"PanoFlow: Learning 360{\\deg} Optical Flow for Surrounding Temporal Understanding","created":"2022-02-27","cited_by_count":26},{"id":"2107.07243","title":"VILENS: Visual, Inertial, Lidar, and Leg Odometry for All-Terrain Legged Robots","created":"2021-07-15","cited_by_count":25},{"id":"2410.18978","title":"Framer: Interactive Frame Interpolation","created":"2024-10-24","cited_by_count":24},{"id":"2502.10444","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","created":"2025-02-11","cited_by_count":24},{"id":"2404.05291","title":"Long-horizon Locomotion and Manipulation on a Quadrupedal Robot with Large Language Models","created":"2024-04-08","cited_by_count":21},{"id":"2412.07721","title":"ObjCtrl-2.5D: Training-free Object Control with Camera Poses","created":"2024-12-10","cited_by_count":18},{"id":"2212.14400","title":"Visual CPG-RL: Learning Central Pattern Generators for Visually-Guided Quadruped Locomotion","created":"2022-12-29","cited_by_count":14},{"id":"2202.12613","title":"LF-VIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras with Negative Plane","created":"2022-02-25","cited_by_count":11},{"id":"2209.05167","title":"LF-VISLAM: A SLAM Framework for Large Field-of-View Cameras with Negative Imaging Plane on Mobile Agents","created":"2022-09-12","cited_by_count":11},{"id":"1909.09662","title":"Mine Tunnel Exploration using Multiple Quadrupedal Robots","created":"2019-09-20","cited_by_count":8},{"id":"2409.13912","title":"OneBEV: Using One Panoramic Image for Bird's-Eye-View Semantic Mapping","created":"2024-09-20","cited_by_count":8},{"id":"1904.03048","title":"Robust Legged Robot State Estimation Using Factor Graph Optimization","created":"2019-04-05","cited_by_count":7},{"id":"2305.07995","title":"Seeing Through the Grass: Semantic Pointcloud Filter for Support Surface Learning","created":"2023-05-13","cited_by_count":5},{"id":"2403.13235","title":"AMCO: Adaptive Multimodal Coupling of Vision and Proprioception for Quadruped Robot Navigation in Outdoor Environments","created":"2024-03-20","cited_by_count":5},{"id":"2501.01806","title":"TRG-planner: Traversal Risk Graph-Based Path Planning in Unstructured Environments for Safe and Efficient Navigation","created":"2025-01-03","cited_by_count":5},{"id":"2206.04533","title":"DogTouch: CNN-based Recognition of Surface Textures by Quadruped Robot with High Density Tactile Sensors","created":"2022-06-09","cited_by_count":3},{"id":"2210.14997","title":"LiDAR-guided object search and detection in Subterranean Environments","created":"2022-10-26","cited_by_count":3},{"id":"2306.06663","title":"LF-PGVIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras using Points and Geodesic Segments","created":"2023-06-11","cited_by_count":3},{"id":"2312.00820","title":"Non-Cross Diffusion for Semantic Consistency","created":"2023-11-30","cited_by_count":2},{"id":"2409.19778","title":"Lessons Learned from Developing a Human-Centered Guide Dog Robot for Mobility Assistance","created":"2024-09-29","cited_by_count":2},{"id":"2411.17134","title":"TRIP: Terrain Traversability Mapping With Risk-Aware Prediction for Enhanced Online Quadrupedal Robot Navigation","created":"2024-11-26","cited_by_count":2},{"id":"2106.03307","title":"Terrain Adaptive Gait Transitioning for a Quadruped Robot using Model Predictive Control","created":"2021-06-07","cited_by_count":1},{"id":"2302.10729","title":"Understanding Dynamic Human-Robot Proxemics in the Case of Four-Legged Canine-Inspired Robots","created":"2023-02-21","cited_by_count":1},{"id":"2307.01101","title":"Assessment of the Utilization of Quadruped Robots in Pharmaceutical Research and Development Laboratories","created":"2023-07-03","cited_by_count":1},{"id":"2404.03444","title":"Simultaneous State Estimation and Contact Detection for Legged Robots by Multiple-Model Kalman Filtering","created":"2024-04-04","cited_by_count":1},{"id":"2404.10938","title":"Safety-critical Autonomous Inspection of Distillation Columns using Quadrupedal Robots Equipped with Roller Arms","created":"2024-04-16","cited_by_count":1},{"id":"2409.15253","title":"Investigating Robot Dogs for Construction Monitoring: A Comparative Analysis of Specifications and On-site Requirements","created":"2024-09-23","cited_by_count":1},{"id":"2503.12101","title":"MUSE: A Real-Time Multi-Sensor State Estimator for Quadruped Robots","created":"2025-03-15","cited_by_count":1}],"next_cursor":null}