{"list":"other","total":109,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"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":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519},{"id":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2503.22020","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","created":"2025-03-27","cited_by_count":451},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2506.21539","title":"WorldVLA: Towards Autoregressive Action World Model","created":"2025-06-26","cited_by_count":367},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"2312.02145","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","created":"2023-12-04","cited_by_count":327},{"id":"2408.10188","title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","created":"2024-08-19","cited_by_count":309},{"id":"2412.10345","title":"TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies","created":"2024-12-13","cited_by_count":304},{"id":"2103.06011","title":"DSEC: A Stereo Event Camera Dataset for Driving Scenarios","created":"2021-03-10","cited_by_count":303},{"id":"2410.19115","title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","created":"2024-10-24","cited_by_count":299},{"id":"1908.00222","title":"Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling","created":"2019-08-01","cited_by_count":286},{"id":"1804.00650","title":"DeepMVS: Learning Multi-view Stereopsis","created":"2018-04-02","cited_by_count":277},{"id":"1908.00463","title":"DIODE: A Dense Indoor and Outdoor DEpth Dataset","created":"2019-08-01","cited_by_count":240},{"id":"2006.14480","title":"One Thousand and One Hours: Self-driving Motion Prediction Dataset","created":"2020-06-25","cited_by_count":240},{"id":"1907.12209","title":"Enforcing geometric constraints of virtual normal for depth prediction","created":"2019-07-29","cited_by_count":234},{"id":"2505.23747","title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","created":"2025-05-29","cited_by_count":217},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"id":"2508.07917","title":"MolmoAct: Action Reasoning Models that can Reason in Space","created":"2025-08-11","cited_by_count":197},{"id":"2112.12610","title":"PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving","created":"2021-12-23","cited_by_count":190},{"id":"2309.16553","title":"MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond","created":"2023-09-28","cited_by_count":185},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"2501.09898","title":"FoundationStereo: Zero-Shot Stereo Matching","created":"2025-01-17","cited_by_count":173},{"id":"2502.20110","title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","created":"2025-02-27","cited_by_count":173},{"id":"2303.01943","title":"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo","created":"2023-03-03","cited_by_count":172},{"id":"2507.16815","title":"ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning","created":"2025-07-22","cited_by_count":156},{"id":"1805.01328","title":"Evaluation of CNN-based Single-Image Depth Estimation Methods","created":"2018-05-03","cited_by_count":138},{"id":"1810.02695","title":"Learning Depth with Convolutional Spatial Propagation Network","created":"2018-10-04","cited_by_count":136},{"id":"2504.19854","title":"NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks","created":"2025-04-28","cited_by_count":127},{"id":"2104.03866","title":"SMD-Nets: Stereo Mixture Density Networks","created":"2021-04-08","cited_by_count":120},{"id":"1911.05377","title":"CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion","created":"2019-11-13","cited_by_count":110},{"id":"1810.08705","title":"Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing","created":"2018-10-19","cited_by_count":106},{"id":"2306.17253","title":"Towards Zero-Shot Scale-Aware Monocular Depth Estimation","created":"2023-06-29","cited_by_count":101},{"id":"2203.15132","title":"LocalBins: Improving Depth Estimation by Learning Local Distributions","created":"2022-03-28","cited_by_count":94},{"id":"2212.03239","title":"Perspective Fields for Single Image Camera Calibration","created":"2022-12-06","cited_by_count":75},{"id":"2412.14015","title":"Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation","created":"2024-12-18","cited_by_count":74},{"id":"2412.06699","title":"You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale","created":"2024-12-09","cited_by_count":65},{"id":"2007.13215","title":"OASIS: A Large-Scale Dataset for Single Image 3D in the Wild","created":"2020-07-26","cited_by_count":62},{"id":"2403.11270","title":"Bilateral Propagation Network for Depth Completion","created":"2024-03-17","cited_by_count":60},{"id":"2106.02778","title":"Radar-Camera Pixel Depth Association for Depth Completion","created":"2021-06-05","cited_by_count":50},{"id":"2010.00058","title":"Depth Estimation from Monocular Images and Sparse Radar Data","created":"2020-09-30","cited_by_count":44},{"id":"2312.02284","title":"PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation","created":"2023-12-04","cited_by_count":41},{"id":"2312.12176","title":"All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes","created":"2023-12-19","cited_by_count":41},{"id":"1909.05452","title":"Flow-Motion and Depth Network for Monocular Stereo and Beyond","created":"2019-09-12","cited_by_count":37},{"id":"2108.04814","title":"R4Dyn: Exploring Radar for Self-Supervised Monocular Depth Estimation of Dynamic Scenes","created":"2021-08-10","cited_by_count":36},{"id":"2306.10988","title":"Tame a Wild Camera: In-the-Wild Monocular Camera Calibration","created":"2023-06-19","cited_by_count":34},{"id":"2107.07596","title":"Depth Estimation from Monocular Images and Sparse radar using Deep Ordinal Regression Network","created":"2021-07-15","cited_by_count":33},{"id":"2301.08245","title":"Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces","created":"2023-01-19","cited_by_count":33},{"id":"2505.05800","title":"3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks","created":"2025-05-09","cited_by_count":31},{"id":"2411.19278","title":"OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration","created":"2024-11-28","cited_by_count":30}],"next_cursor":"100"}