{"list":"other","total":82,"rows":[{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"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":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"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":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"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":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2104.04631","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","created":"2021-04-09","cited_by_count":325},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2112.14683","title":"StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2","created":"2021-12-29","cited_by_count":301},{"id":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","cited_by_count":287},{"id":"1801.01615","title":"Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies","created":"2018-01-05","cited_by_count":239},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204},{"id":"2501.03847","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control","created":"2025-01-07","cited_by_count":185},{"id":"2008.04451","title":"Grasping Field: Learning Implicit Representations for Human Grasps","created":"2020-08-10","cited_by_count":179},{"id":"2311.16933","title":"SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models","created":"2023-11-28","cited_by_count":175},{"id":"2104.03304","title":"Hand-Object Contact Consistency Reasoning for Human Grasps Generation","created":"2021-04-07","cited_by_count":160},{"id":"2203.15709","title":"OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction","created":"2022-03-29","cited_by_count":131},{"id":"2410.11831","title":"CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos","created":"2024-10-15","cited_by_count":128},{"id":"2212.07555","title":"IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions","created":"2022-12-14","cited_by_count":124},{"id":"2303.00938","title":"UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy","created":"2023-03-02","cited_by_count":124},{"id":"2311.17009","title":"Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer","created":"2023-11-28","cited_by_count":124},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124},{"id":"2112.03028","title":"D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions","created":"2021-12-01","cited_by_count":113},{"id":"2303.12538","title":"Affordance Diffusion: Synthesizing Hand-Object Interactions","created":"2023-03-21","cited_by_count":110},{"id":"2412.05435","title":"UniScene: Unified Occupancy-centric Driving Scene Generation","created":"2024-12-06","cited_by_count":106},{"id":"2401.08399","title":"TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding","created":"2024-01-16","cited_by_count":88},{"id":"2403.19417","title":"OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion","created":"2024-03-28","cited_by_count":82},{"id":"2311.18836","title":"ChatPose: Chatting about 3D Human Pose","created":"2023-11-30","cited_by_count":72},{"id":"2503.00779","title":"Phantom: Training Robots Without Robots Using Only Human Videos","created":"2025-03-02","cited_by_count":70},{"id":"2501.02973","title":"HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos","created":"2025-01-06","cited_by_count":66},{"id":"2503.21860","title":"ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning","created":"2025-03-27","cited_by_count":66},{"id":"2403.19649","title":"GraspXL: Generating Grasping Motions for Diverse Objects at Scale","created":"2024-03-28","cited_by_count":60},{"id":"2410.03665","title":"Estimating Body and Hand Motion in an Ego-sensed World","created":"2024-10-04","cited_by_count":58},{"id":"2312.04483","title":"Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation","created":"2023-12-07","cited_by_count":50},{"id":"2407.09646","title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","created":"2024-07-12","cited_by_count":45},{"id":"2309.06441","title":"Learning Disentangled Avatars with Hybrid 3D Representations","created":"2023-09-12","cited_by_count":44},{"id":"2312.02975","title":"Dexterous Functional Grasping","created":"2023-12-05","cited_by_count":39},{"id":"2403.12011","title":"HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data","created":"2024-03-18","cited_by_count":37},{"id":"2402.14810","title":"GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion","created":"2024-02-22","cited_by_count":35},{"id":"2412.04244","title":"GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities","created":"2024-12-05","cited_by_count":33},{"id":"2503.19157","title":"HOIGPT: Learning Long Sequence Hand-Object Interaction with Language Models","created":"2025-03-24","cited_by_count":33},{"id":"1707.00383","title":"Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation","created":"2017-07-03","cited_by_count":29},{"id":"2406.06843","title":"HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction","created":"2024-06-10","cited_by_count":29},{"id":"2403.01813","title":"A Simple Baseline for Efficient Hand Mesh Reconstruction","created":"2024-03-04","cited_by_count":27},{"id":"2503.08257","title":"DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness","created":"2025-03-11","cited_by_count":26},{"id":"2503.11423","title":"TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation","created":"2025-03-14","cited_by_count":24},{"id":"2111.12608","title":"Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing","created":"2021-11-24","cited_by_count":22},{"id":"2211.15663","title":"Hand-Object Interaction Image Generation","created":"2022-11-28","cited_by_count":19},{"id":"2408.07147","title":"Controlling the World by Sleight of Hand","created":"2024-08-13","cited_by_count":19},{"id":"2503.16942","title":"Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model","created":"2025-03-21","cited_by_count":19},{"id":"2412.16212","title":"ManiVideo: Generating Hand-Object Manipulation Video with Dexterous and Generalizable Grasping","created":"2024-12-18","cited_by_count":18},{"id":"2502.09614","title":"DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References","created":"2025-02-13","cited_by_count":17},{"id":"2505.18947","title":"OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model","created":"2025-05-25","cited_by_count":17},{"id":"2508.05506","title":"MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips","created":"2025-08-07","cited_by_count":17},{"id":"2407.06250","title":"FairDiff: Fair Segmentation with Point-Image Diffusion","created":"2024-07-08","cited_by_count":15},{"id":"2406.02230","title":"I4VGen: Image as Free Stepping Stone for Text-to-Video Generation","created":"2024-06-04","cited_by_count":14},{"id":"2410.11236","title":"Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling","created":"2024-10-15","cited_by_count":14},{"id":"2311.05599","title":"SynH2R: Synthesizing Hand-Object Motions for Learning Human-to-Robot Handovers","created":"2023-11-09","cited_by_count":13},{"id":"2403.10731","title":"Giving a Hand to Diffusion Models: a Two-Stage Approach to Improving Conditional Human Image Generation","created":"2024-03-15","cited_by_count":13},{"id":"2506.02444","title":"SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios","created":"2025-06-03","cited_by_count":12},{"id":"2503.21313","title":"HORT: Monocular Hand-held Objects Reconstruction with Transformers","created":"2025-03-27","cited_by_count":11},{"id":"2409.03644","title":"RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images","created":"2024-09-05","cited_by_count":10},{"id":"2504.12284","title":"How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions","created":"2025-04-16","cited_by_count":10},{"id":"2412.01537","title":"HandOS: 3D Hand Reconstruction in One Stage","created":"2024-12-02","cited_by_count":9},{"id":"2505.16602","title":"MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation","created":"2025-05-22","cited_by_count":9},{"id":"2410.13911","title":"GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction","created":"2024-10-17","cited_by_count":8},{"id":"2411.09572","title":"Dynamic Reconstruction of Hand-Object Interaction with Distributed Force-aware Contact Representation","created":"2024-11-14","cited_by_count":8},{"id":"2412.02690","title":"FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation","created":"2024-12-03","cited_by_count":8},{"id":"2412.13393","title":"MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild","created":"2024-12-18","cited_by_count":5},{"id":"2503.19307","title":"Analyzing the Synthetic-to-Real Domain Gap in 3D Hand Pose Estimation","created":"2025-03-25","cited_by_count":5},{"id":"2508.01835","title":"Diffusion-based 3D Hand Motion Recovery with Intuitive Physics","created":"2025-08-03","cited_by_count":5},{"id":"2406.17774","title":"Uncertainty for SVBRDF Acquisition using Frequency Analysis","created":"2024-06-25","cited_by_count":4}],"next_cursor":null}