Cewu Lu

91

Papers

293

Total Citations

Papers (91)

Pairwise Body-Part Attention for Recognizing Human-Object Interactions

Asynchronous Interaction Aggregation for Action Detection

Distill Gold from Massive Ores: Bi-level Data Pruning towards Efficient Dataset Distillation

Interacted Object Grounding in Spatio-Temporal Human-Object Interactions

The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMs

Dynamic Reconstruction of Hand-Object Interaction with Distributed Force-aware Contact Representation

Discovering Conceptual Knowledge with Analytic Ontology Templates for Articulated Objects

PACE: Pose Annotations in Cluttered Environments

Homogeneous Dynamics Space for Heterogeneous Humans

EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints

Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement

OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion

Low-Rank Similarity Mining for Multimodal Dataset Distillation

Complexity-Adaptive Distance Metric for Object Proposals Generation

Deep LAC: Deep Localization, Alignment and Classification for Fine-Grained Recognition

Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer

Recurrent Residual Module for Fast Inference in Videos

Environment Upgrade Reinforcement Learning for Non-Differentiable Multi-Stage Pipelines

LiDAR-Video Driving Dataset: Learning Driving Policies Effectively

Beyond Holistic Object Recognition: Enriching Image Understanding With Part States

Deep RNN Framework for Visual Sequential Applications

DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion

Transferable Interactiveness Knowledge for Human-Object Interaction Detection

CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmark

Recursive Social Behavior Graph for Trajectory Prediction

PaStaNet: Toward Human Activity Knowledge Engine

TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model

KeypointNet: A Large-Scale 3D Keypoint Dataset Aggregated From Numerous Human Annotations

Symmetry and Group in Attribute-Object Compositions

GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping

Detailed 2D-3D Joint Representation for Human-Object Interaction

Skeleton Merger: An Unsupervised Aligned Keypoint Detector

HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation

PGT: A Progressive Method for Training Models on Long Videos

Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes

ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis

CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild

Human Trajectory Prediction With Momentary Observation

Semantic Segmentation by Early Region Proxy

Learning To Anticipate Future With Dynamic Context Removal

OakInk: A Large-Scale Knowledge Repository for Understanding Hand-Object Interaction

Interactiveness Field in Human-Object Interactions

UKPGAN: A General Self-Supervised Keypoint Detector

AKB-48: A Real-World Articulated Object Knowledge Base

Target-Referenced Reactive Grasping for Dynamic Objects

Stimulus Verification Is a Universal and Effective Sampler in Multi-Modal Human Trajectory Prediction

Unsupervised 3D Point Cloud Representation Learning by Triangle Constrained Contrast for Autonomous Driving

Upcycling Models Under Domain and Category Shift

Visual-Tactile Sensing for In-Hand Object Reconstruction

GarmentTracking: Category-Level Garment Pose Tracking

NIKI: Neural Inverse Kinematics With Invertible Neural Networks for 3D Human Pose and Shape Estimation

POEM: Reconstructing Hand in a Point Embedded Multi-View Stereo

Contour Box: Rejecting Object Proposals Without Explicit Closed Contours

Square Localization for Efficient and Accurate Object Detection

Box Aggregation for Proposal Decimation: Last Mile of Object Detection

RMPE: Regional Multi-Person Pose Estimation

Online Video Object Detection Using Association LSTM

InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting

Approximated Bilinear Modules for Temporal Modeling

Explicit Shape Encoding for Real-Time Instance Segmentation

ChatGarment: Garment Estimation, Generation and Editing via Large Language Models

H2O: A Benchmark for Visual Human-Human Object Handover Analysis

Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesis

Graspness Discovery in Clutters for Fast and Accurate Grasp Detection

Human Pose Regression With Residual Log-Likelihood Estimation

CPF: Learning a Contact Potential Field To Model the Hand-Object Interaction

EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding

ClothPose: A Real-world Benchmark for Visual Analysis of Garment Pose via An Indirect Recording Solution

Beyond Object Recognition: A New Benchmark towards Object Concept Learning

ClothesNet: An Information-Rich 3D Garment Model Repository with Simulated Clothes Environment

CHORD: Category-level Hand-held Object Reconstruction via Shape Deformation

HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation

Human Correspondence Consensus for 3D Object Semantic Understanding

Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection

D&D: Learning Human Dynamics from Dynamic Camera

Constructing Balance from Imbalance for Long-Tailed Image Recognition

Unsupervised Visual Representation Learning by Synchronous Momentum Grouping

Cross-Domain Adaptation for Animal Pose Estimation

GaPT-DAR: Category-level Garments Pose Tracking via Integrated 2D Deformation and 3D Reconstruction

M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation

Arti-PG: A Toolbox for Procedurally Synthesizing Large-Scale and Diverse Articulated Objects with Rich Annotations

Dense Policy: Bidirectional Autoregressive Learning of Actions

Primitive-Based 3D Human-Object Interaction Modelling and Programming

ShapeBoost: Boosting Human Shape Estimation with Part-Based Parameterization and Clothing-Preserving Augmentation

FAVOR: Full-Body AR-Driven Virtual Object Rearrangement Guided by Instruction Text

From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding

HOI Analysis: Integrating and Decomposing Human-Object Interaction

Localization with Sampling-Argmax

DART: Articulated Hand Model with Diverse Accessories and Rich Textures

Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning