Ziyan Wu

27

Papers

10

Total Citations

Papers (27)

Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding

7DGS: Unified Spatial-Temporal-Angular Gaussian Splatting

Implicit Modeling of Non-rigid Objects with Cross-Category Signals

Disguise without Disruption: Utility-Preserving Face De-identification

DaReNeRF: Direction-aware Representation for Dynamic Scenes

End-to-End Learning of Keypoint Detector and Descriptor for Pose Invariant 3D Matching

Learning Compositional Visual Concepts With Mutual Consistency

Tell Me Where to Look: Guided Attention Inference Network

Learning Without Memorizing

Re-Identification With Consistent Attentive Siamese Networks

Towards Visually Explaining Variational Autoencoders

A Peek Into the Reasoning of Neural Networks: Interpreting With Structural Visual Concepts

Weakly Supervised Summarization of Web Videos

Sharpen Focus: Learning With Attention Separability and Consistency

Learning Local RGB-to-CAD Correspondences for Object Pose Estimation

Ensemble Attention Distillation for Privacy-Preserving Federated Learning

Spatio-Temporal Representation Factorization for Video-Based Person Re-Identification

CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation

Hierarchical Kinematic Human Mesh Recovery

Self-supervised Human Mesh Recovery with Cross-Representation Alignment

PseudoClick: Interactive Image Segmentation with Click Imitation

PREF: Predictability Regularized Neural Motion Fields

SMPL-A: Modeling Person-Specific Deformable Anatomy

CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image

Incremental Scene Synthesis

Forecasting Human Trajectory from Scene History

Counterfactual Visual Explanations