Kris Kitani

ExpertAF: Expert Actionable Feedback from Video CVPR 2025 ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping CVPR 2025 HOIGPT: Learning Long-Sequence Hand-Object Interaction with Language Models CVPR 2025 Leveraging Temporal Cues for Semi-Supervised Multi-View 3D Object Detection CVPR 2025 ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills RSS 2025 ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling ICCV 2025 "Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos" ECCV 2024 Zero-Shot Multi-Object Scene Completion ECCV 2024 G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis CVPR 2024 Real-Time Simulated Avatar from Head-Mounted Sensors CVPR 2024 Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives CVPR 2024 Flexible Depth Completion for Sparse and Varying Point Densities CVPR 2024 Video Question Answering with Procedural Programs ECCV 2024 Omnigrasp: Grasping Diverse Objects with Simulated Humanoids NIPS 2024 MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction NIPS 2024 Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions NIPS 2024 Ego-Humans: An Ego-Centric 3D Multi-Human Benchmark ICCV 2023 Type-to-Track: Retrieve Any Object via Prompt-based Tracking NIPS 2023 Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion CVPR 2023 Azimuth Super-Resolution for FMCW Radar in Autonomous Driving CVPR 2023 Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking CVPR 2023 Perpetual Humanoid Control for Real-time Simulated Avatars ICCV 2023 Joint Metrics Matter: A Better Standard for Trajectory Forecasting ICCV 2023 DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion CVPR 2022 Cross-Domain Adaptive Teacher for Object Detection CVPR 2022 Ego4D: Around the World in 3,000 Hours of Egocentric Video CVPR 2022 Sequential Voting With Relational Box Fields for Active Object Detection CVPR 2022 Embodied Scene-aware Human Pose Estimation NIPS 2022 Occluded Human Mesh Recovery CVPR 2022 Online No-regret Model-Based Meta RL for Personalized Navigation L4DC 2022 Whose Track Is It Anyway? Improving Robustness to Tracking Errors With Affinity-Based Trajectory Prediction CVPR 2022 GLAMR: Global Occlusion-Aware Human Mesh Recovery With Dynamic Cameras CVPR 2022 Modality-Agnostic Learning for Radar-Lidar Fusion in Vehicle Detection CVPR 2022 REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer ICML 2022 Dynamics-regulated kinematic policy for egocentric pose estimation NIPS 2021 SimPoE: Simulated Character Control for 3D Human Pose Estimation CVPR 2021 Wide-Baseline Multi-Camera Calibration Using Person Re-Identification CVPR 2021 Inverse Reinforcement Learning with Explicit Policy Estimates AAAI 2021 IDOL: Inertial Deep Orientation-Estimation and Localization AAAI 2021 Estimate 3D Camera Pose from 2D Pedestrian Trajectories WACV 2020 DLow: Diversifying Latent Flows for Diverse Human Motion Prediction ECCV 2020 Inverting the Pose Forecasting Pipeline with SPF2: Sequential Pointcloud Forecasting for Sequential Pose Forecasting CORL 2020 Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis NIPS 2020 Efficient Non-Line-of-Sight Imaging from Transient Sinograms ECCV 2020 Incremental Class Discovery for Semantic Segmentation With RGBD Sensing ICCV 2019 PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings ICCV 2019 Ego-Pose Estimation and Forecasting As Real-Time PD Control ICCV 2019 Personalized Dynamics Models for Adaptive Assistive Navigation Systems CORL 2018 3D Ego-Pose Estimation via Imitation Learning ECCV 2018 Predictive-State Decoders: Encoding the Future into Recurrent Networks NIPS 2017