Picture for Chenhang He

Chenhang He

Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding

Add code
Jul 13, 2024
Viaarxiv icon

LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models

Add code
Jul 12, 2024
Viaarxiv icon

Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection

Add code
Jun 18, 2024
Viaarxiv icon

VoxGenesis: Unsupervised Discovery of Latent Speaker Manifold for Speech Synthesis

Add code
Mar 01, 2024
Viaarxiv icon

ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attention

Add code
Jan 01, 2024
Viaarxiv icon

Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution

Add code
Dec 01, 2023
Viaarxiv icon

Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations

Add code
May 18, 2023
Viaarxiv icon

One-to-Few Label Assignment for End-to-End Dense Detection

Add code
Mar 21, 2023
Viaarxiv icon

MSF: Motion-guided Sequential Fusion for Efficient 3D Object Detection from Point Cloud Sequences

Add code
Mar 15, 2023
Viaarxiv icon

DynaMask: Dynamic Mask Selection for Instance Segmentation

Add code
Mar 14, 2023
Viaarxiv icon