Li Cheng

18

Papers

8

Total Citations

Papers (18)

MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer

CASAGPT: Cuboid Arrangement and Scene Assembly for Interior Design

HiPoser: 3D Human Pose Estimation with Hierarchical Shared Learning at Parts-Level Using Inertial Measurement Units

MoMask: Generative Masked Modeling of 3D Human Motions

Towards Natural and Accurate Future Motion Prediction of Humans and Animals

Learning Calibrated Medical Image Segmentation via Multi-Rater Agreement Modeling

Calibrated RGB-D Salient Object Detection

Generating Diverse and Natural 3D Human Motions From Text

Contrastive Learning for Unsupervised Video Highlight Detection

Exploring Denoised Cross-Video Contrast for Weakly-Supervised Temporal Action Localization

Multispectral Video Semantic Segmentation: A Benchmark Dataset and Baseline

Learning to Boost Filamentary Structure Segmentation

EventHPE: Event-Based 3D Human Pose and Shape Estimation

Joint Visual and Audio Learning for Video Highlight Detection

3D Human Shape Reconstruction from a Polarization Image

Object Wake-Up: 3D Object Rigging from a Single Image

TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts

BOOTPLACE: Bootstrapped Object Placement with Detection Transformers