{"list":"other","total":103,"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2309.13101","title":"Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction","created":"2023-09-22","cited_by_count":759},{"id":"2301.10241","title":"K-Planes: Explicit Radiance Fields in Space, Time, and Appearance","created":"2023-01-24","cited_by_count":746},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"2103.01458","title":"Diffusion Probabilistic Models for 3D Point Cloud Generation","created":"2021-03-02","cited_by_count":735},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2505.13447","title":"Mean Flows for One-step Generative Modeling","created":"2025-05-19","cited_by_count":561},{"id":"2210.06978","title":"LION: Latent Point Diffusion Models for 3D Shape Generation","created":"2022-10-12","cited_by_count":553},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2310.15110","title":"Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model","created":"2023-10-23","cited_by_count":521},{"id":"1906.12320","title":"PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows","created":"2019-06-28","cited_by_count":488},{"id":"2301.11445","title":"3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models","created":"2023-01-26","cited_by_count":458},{"id":"2406.13897","title":"CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets","created":"2024-05-30","cited_by_count":455},{"id":"2011.03277","title":"Modular Primitives for High-Performance Differentiable Rendering","created":"2020-11-06","cited_by_count":441},{"id":"2210.05666","title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling","created":"2022-10-11","cited_by_count":388},{"id":"2205.15285","title":"Fast Dynamic Radiance Fields with Time-Aware Neural Voxels","created":"2022-05-30","cited_by_count":346},{"id":"2312.02201","title":"ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation","created":"2023-12-02","cited_by_count":257},{"id":"2306.17115","title":"Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation","created":"2023-06-29","cited_by_count":228},{"id":"1810.01566","title":"Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids","created":"2018-10-03","cited_by_count":220},{"id":"2204.04153","title":"Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories","created":"2022-04-08","cited_by_count":217},{"id":"2211.11610","title":"Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering","created":"2022-11-21","cited_by_count":217},{"id":"2502.06608","title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","created":"2025-02-10","cited_by_count":213},{"id":"2405.14832","title":"Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer","created":"2024-05-23","cited_by_count":210},{"id":"2301.11280","title":"Text-To-4D Dynamic Scene Generation","created":"2023-01-26","cited_by_count":205},{"id":"2301.02239","title":"Robust Dynamic Radiance Fields","created":"2023-01-05","cited_by_count":194},{"id":"2312.17142","title":"DreamGaussian4D: Generative 4D Gaussian Splatting","created":"2023-12-28","cited_by_count":194},{"id":"2306.05422","title":"Tracking Everything Everywhere All at Once","created":"2023-06-08","cited_by_count":193},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185},{"id":"2404.04319","title":"SpatialTracker: Tracking Any 2D Pixels in 3D Space","created":"2024-04-05","cited_by_count":181},{"id":"2312.13763","title":"Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models","created":"2023-12-21","cited_by_count":169},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161},{"id":"2303.17015","title":"HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion","created":"2023-03-29","cited_by_count":152},{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144},{"id":"2407.17470","title":"SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency","created":"2024-07-24","cited_by_count":144},{"id":"2410.11831","title":"CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos","created":"2024-10-15","cited_by_count":128},{"id":"2212.00190","title":"Mixed Neural Voxels for Fast Multi-view Video Synthesis","created":"2022-12-01","cited_by_count":127},{"id":"2311.02848","title":"Consistent4D: Consistent 360{\\deg} Dynamic Object Generation from Monocular Video","created":"2023-11-06","cited_by_count":125},{"id":"2312.17225","title":"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency","created":"2023-12-28","cited_by_count":117},{"id":"2311.14603","title":"Animate124: Animating One Image to 4D Dynamic Scene","created":"2023-11-24","cited_by_count":115},{"id":"2403.14939","title":"STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians","created":"2024-03-22","cited_by_count":102},{"id":"2403.12365","title":"GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation","created":"2024-03-19","cited_by_count":100},{"id":"2405.16645","title":"Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models","created":"2024-05-26","cited_by_count":100},{"id":"2412.17808","title":"Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders","created":"2024-12-23","cited_by_count":98},{"id":"2412.09621","title":"Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos","created":"2024-12-12","cited_by_count":89},{"id":"2504.13152","title":"St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World","created":"2025-04-17","cited_by_count":89},{"id":"2507.12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","created":"2025-07-16","cited_by_count":87},{"id":"2308.09718","title":"Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training","created":"2023-08-18","cited_by_count":86},{"id":"2311.16854","title":"A Unified Approach for Text- and Image-guided 4D Scene Generation","created":"2023-11-28","cited_by_count":82},{"id":"2403.17920","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","created":"2024-03-26","cited_by_count":77},{"id":"2306.14447","title":"RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools","created":"2023-06-26","cited_by_count":76},{"id":"2205.02909","title":"RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks","created":"2022-05-05","cited_by_count":72},{"id":"2407.05921","title":"TAPVid-3D: A Benchmark for Tracking Any Point in 3D","created":"2024-07-08","cited_by_count":72},{"id":"1709.04307","title":"Variational Autoencoders for Deforming 3D Mesh Models","created":"2017-09-13","cited_by_count":70},{"id":"2504.14717","title":"TAPIP3D: Tracking Any Point in Persistent 3D Geometry","created":"2025-04-20","cited_by_count":69},{"id":"2410.24211","title":"DELTA: Dense Efficient Long-range 3D Tracking for any video","created":"2024-10-31","cited_by_count":65},{"id":"2312.00786","title":"Dense Optical Tracking: Connecting the Dots","created":"2023-12-01","cited_by_count":61},{"id":"2310.08586","title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm","created":"2023-10-12","cited_by_count":56},{"id":"2407.07889","title":"AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulation","created":"2024-07-10","cited_by_count":54},{"id":"2008.02792","title":"CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations","created":"2020-08-06","cited_by_count":51},{"id":"2503.16396","title":"SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation","created":"2025-03-20","cited_by_count":48},{"id":"2401.08742","title":"Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video","created":"2024-01-16","cited_by_count":44},{"id":"2206.02881","title":"Mesh-based Dynamics with Occlusion Reasoning for Cloth Manipulation","created":"2022-06-06","cited_by_count":34},{"id":"2401.11485","title":"ColorVideoVDP: A visual difference predictor for image, video and display distortions","created":"2024-01-21","cited_by_count":34},{"id":"2507.23785","title":"Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis","created":"2025-07-31","cited_by_count":33},{"id":"2401.06614","title":"Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking","created":"2024-01-12","cited_by_count":29},{"id":"2403.19924","title":"SceneTracker: Long-term Scene Flow Estimation Network","created":"2024-03-29","cited_by_count":26},{"id":"2510.06208","title":"ShapeGen4D: Towards High Quality 4D Shape Generation from Videos","created":"2025-10-07","cited_by_count":21},{"id":"2407.01418","title":"RoboPack: Learning Tactile-Informed Dynamics Models for Dense Packing","created":"2024-07-01","cited_by_count":19},{"id":"2503.11999","title":"Diffusion Dynamics Models with Generative State Estimation for Cloth Manipulation","created":"2025-03-15","cited_by_count":19},{"id":"2408.14899","title":"MeshUp: Multi-Target Mesh Deformation via Blended Score Distillation","created":"2024-08-27","cited_by_count":17},{"id":"2401.01734","title":"Learning Keypoints for Robotic Cloth Manipulation using Synthetic Data","created":"2024-01-03","cited_by_count":11},{"id":"2412.15618","title":"3D Shape Tokenization via Latent Flow Matching","created":"2024-12-20","cited_by_count":10}],"next_cursor":"100"}