Wenguan Wang

25

Papers

171

Total Citations

Papers (25)

IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection

Clustering Propagation for Universal Medical Image Segmentation

LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels

Controllable Navigation Instruction Generation with Chain of Thought Prompting

Multi-view Reconstruction via SfM-guided Monocular Depth Estimation

Clustering for Protein Representation Learning

Scene Map-based Prompt Tuning for Navigation Instruction Generation

DiffVsgg: Diffusion-Driven Online Video Scene Graph Generation

A Conditional Probability Framework for Compositional Zero-shot Learning

Dual Reciprocal Learning of Language-based Human Motion Understanding and Generation

Mutual Learning for Acoustic Matching and Dereverberation via Visual Scene-driven Diffusion

Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity

Poly Kernel Inception Network for Remote Sensing Detection

LOGICZSL: Exploring Logic-induced Representation for Compositional Zero-shot Learning

DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)

TAGA: Self-supervised Learning for Template-free Animatable Gaussian Articulated Model

UNIALIGN: Scaling Multimodal Alignment within One Unified Model

3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation

Gaussian-based World Model: Gaussian Priors for Voxel-Based Occupancy Prediction and Future Motion Prediction

Underwater Visual SLAM with Depth Uncertainty and Medium Modeling

Cycle-Consistent Learning for Joint Layout-to-Image Generation and Object Detection

Towards Human-like Virtual Beings: Simulating Human Behavior in 3D Scenes

Interpretable3D: An Ad

Volumetric Environment Representation for Vision-Language Navigation

Neural Clustering based Visual Representation Learning