{"list":"other","total":90,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1904.08755","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","created":"2019-04-18","cited_by_count":1208},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1711.10275","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","created":"2017-11-28","cited_by_count":748},{"id":"2112.00724","title":"RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs","created":"2021-12-01","cited_by_count":615},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"1811.11742","title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","created":"2018-11-28","cited_by_count":403},{"id":"1611.05009","title":"OctNet: Learning Deep 3D Representations at High Resolutions","created":"2016-11-15","cited_by_count":342},{"id":"1503.04069","title":"LSTM: A Search Space Odyssey","created":"2015-03-13","cited_by_count":316},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"1807.10267","title":"Generating 3D faces using Convolutional Mesh Autoencoders","created":"2018-07-26","cited_by_count":268},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","cited_by_count":239},{"id":"1808.00278","title":"Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm","created":"2018-08-01","cited_by_count":235},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"2212.08333","title":"AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains","created":"2022-12-16","cited_by_count":208},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180},{"id":"2012.11581","title":"Populating 3D Scenes by Learning Human-Scene Interaction","created":"2020-12-21","cited_by_count":164},{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158},{"id":"2007.15649","title":"Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild","created":"2020-07-30","cited_by_count":152},{"id":"2203.08528","title":"Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensors","created":"2022-03-16","cited_by_count":146},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"2207.13751","title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","created":"2022-07-27","cited_by_count":136},{"id":"2205.00541","title":"COUCH: Towards Controllable Human-Chair Interactions","created":"2022-05-01","cited_by_count":135},{"id":"2105.01794","title":"Real-time Deep Dynamic Characters","created":"2021-05-04","cited_by_count":133},{"id":"1912.02923","title":"Generating 3D People in Scenes without People","created":"2019-12-05","cited_by_count":127},{"id":"2112.02789","title":"HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs","created":"2021-12-06","cited_by_count":112},{"id":"2303.12538","title":"Affordance Diffusion: Synthesizing Hand-Object Interactions","created":"2023-03-21","cited_by_count":110},{"id":"2303.18246","title":"3D Human Pose Estimation via Intuitive Physics","created":"2023-03-31","cited_by_count":103},{"id":"2205.13001","title":"Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis","created":"2022-05-25","cited_by_count":91},{"id":"2411.16575","title":"Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression","created":"2024-11-25","cited_by_count":85},{"id":"2207.12824","title":"Compositional Human-Scene Interaction Synthesis with Semantic Control","created":"2022-07-26","cited_by_count":83},{"id":"2204.09443","title":"GIMO: Gaze-Informed Human Motion Prediction in Context","created":"2022-04-20","cited_by_count":81},{"id":"2403.18036","title":"Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance","created":"2024-03-26","cited_by_count":80},{"id":"1909.04977","title":"CARS: Continuous Evolution for Efficient Neural Architecture Search","created":"2019-09-11","cited_by_count":79},{"id":"1903.05690","title":"Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments","created":"2019-03-13","cited_by_count":72},{"id":"2205.07982","title":"TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement","created":"2022-05-16","cited_by_count":70},{"id":"2403.19652","title":"InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction","created":"2024-03-28","cited_by_count":64},{"id":"2405.02280","title":"DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos","created":"2024-05-03","cited_by_count":63},{"id":"2303.16479","title":"Visibility Aware Human-Object Interaction Tracking from Single RGB Camera","created":"2023-03-29","cited_by_count":58},{"id":"2212.04360","title":"MIME: Human-Aware 3D Scene Generation","created":"2022-12-08","cited_by_count":57},{"id":"2203.03609","title":"Human-Aware Object Placement for Visual Environment Reconstruction","created":"2022-03-07","cited_by_count":56},{"id":"2410.03187","title":"Autonomous Character-Scene Interaction Synthesis from Text Instruction","created":"2024-10-04","cited_by_count":56},{"id":"2501.14729","title":"HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation","created":"2025-01-24","cited_by_count":56},{"id":"2509.20414","title":"SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent","created":"2025-09-24","cited_by_count":56},{"id":"2304.14406","title":"Putting People in Their Place: Affordance-Aware Human Insertion into Scenes","created":"2023-04-27","cited_by_count":53},{"id":"2405.07784","title":"Generating Human Motion in 3D Scenes from Text Descriptions","created":"2024-05-13","cited_by_count":49},{"id":"2202.12825","title":"NeuralHOFusion: Neural Volumetric Rendering under Human-object Interactions","created":"2022-02-25","cited_by_count":44},{"id":"2303.03361","title":"Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervision","created":"2023-03-06","cited_by_count":44},{"id":"1811.01335","title":"Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance","created":"2018-11-04","cited_by_count":42},{"id":"1804.03080","title":"Binge Watching: Scaling Affordance Learning from Sitcoms","created":"2018-04-09","cited_by_count":41},{"id":"2303.03373","title":"Detecting Human-Object Contact in Images","created":"2023-03-06","cited_by_count":41},{"id":"2311.17737","title":"GenZI: Zero-Shot 3D Human-Scene Interaction Generation","created":"2023-11-29","cited_by_count":40},{"id":"2306.00777","title":"Object pop-up: Can we infer 3D objects and their poses from human interactions alone?","created":"2023-06-01","cited_by_count":37},{"id":"1808.02473","title":"SketchyScene: Richly-Annotated Scene Sketches","created":"2018-08-07","cited_by_count":32},{"id":"2003.11818","title":"Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection","created":"2020-03-26","cited_by_count":32},{"id":"2504.10414","title":"HUMOTO: A 4D Dataset of Mocap Human Object Interactions","created":"2025-04-14","cited_by_count":31},{"id":"2209.02485","title":"Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors","created":"2022-09-06","cited_by_count":30},{"id":"2502.02358","title":"MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm","created":"2025-02-04","cited_by_count":30},{"id":"2104.14837","title":"RobustFusion: Robust Volumetric Performance Reconstruction under Human-object Interactions from Monocular RGBD Stream","created":"2021-04-30","cited_by_count":26},{"id":"2111.08960","title":"Compositional Transformers for Scene Generation","created":"2021-11-17","cited_by_count":24},{"id":"2512.23180","title":"GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation","created":"2025-12-29","cited_by_count":23},{"id":"2112.03030","title":"Pose2Room: Understanding 3D Scenes from Human Activities","created":"2021-12-01","cited_by_count":22},{"id":"1412.5474","title":"Flattened Convolutional Neural Networks for Feedforward Acceleration","created":"2014-12-17","cited_by_count":20},{"id":"2301.01424","title":"Scene Synthesis from Human Motion","created":"2023-01-04","cited_by_count":20},{"id":"1804.10112","title":"Format Abstraction for Sparse Tensor Algebra Compilers","created":"2018-04-23","cited_by_count":16},{"id":"2103.02758","title":"Learning Asynchronous and Sparse Human-Object Interaction in Videos","created":"2021-03-03","cited_by_count":16},{"id":"2108.00505","title":"DeepTrack: Lightweight Deep Learning for Vehicle Path Prediction in Highways","created":"2021-08-01","cited_by_count":16},{"id":"2503.01291","title":"SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance","created":"2025-03-03","cited_by_count":16},{"id":"2501.01770","title":"TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation","created":"2025-01-03","cited_by_count":14},{"id":"2306.03847","title":"Learning Human Mesh Recovery in 3D Scenes","created":"2023-06-06","cited_by_count":13},{"id":"1802.10280","title":"Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs","created":"2018-02-28","cited_by_count":11},{"id":"2005.05659","title":"Stillleben: Realistic Scene Synthesis for Deep Learning in Robotics","created":"2020-05-12","cited_by_count":11},{"id":"2503.16289","title":"SceneMI: Motion In-betweening for Modeling Human-Scene Interactions","created":"2025-03-20","cited_by_count":11},{"id":"2504.06827","title":"IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments","created":"2025-04-09","cited_by_count":11},{"id":"2507.07781","title":"SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes","created":"2025-07-10","cited_by_count":11},{"id":"2602.06035","title":"InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactions","created":"2026-02-05","cited_by_count":11},{"id":"2310.15948","title":"Language-driven Scene Synthesis using Multi-conditional Diffusion Model","created":"2023-10-24","cited_by_count":10},{"id":"2405.12460","title":"Physics-based Scene Layout Generation from Human Motion","created":"2024-05-21","cited_by_count":10},{"id":"2209.06314","title":"Placing Human Animations into 3D Scenes by Learning Interaction- and Geometry-Driven Keyframes","created":"2022-09-13","cited_by_count":8},{"id":"2412.13185","title":"Move-in-2D: 2D-Conditioned Human Motion Generation","created":"2024-12-17","cited_by_count":8},{"id":"2312.09641","title":"Ins-HOI: Instance Aware Human-Object Interactions Recovery","created":"2023-12-15","cited_by_count":7},{"id":"2112.07022","title":"Learning Body-Aware 3D Shape Generative Models","created":"2021-12-13","cited_by_count":5},{"id":"2510.18357","title":"Learning Human-Object Interaction as Groups","created":"2025-10-21","cited_by_count":5},{"id":"2308.01164","title":"Virtual Reality Based Robot Teleoperation via Human-Scene Interaction","created":"2023-08-02","cited_by_count":3},{"id":"2202.05868","title":"Blocking Techniques for Sparse Matrix Multiplication on Tensor Accelerators","created":"2022-02-11","cited_by_count":1}],"next_cursor":null}