Picture for Hao Shi

Hao Shi

EgoEvGesture: Gesture Recognition Based on Egocentric Event Camera

Add code
Mar 16, 2025
Viaarxiv icon

HierDAMap: Towards Universal Domain Adaptive BEV Mapping via Hierarchical Perspective Priors

Add code
Mar 10, 2025
Viaarxiv icon

Omnidirectional Multi-Object Tracking

Add code
Mar 06, 2025
Viaarxiv icon

TS-CGNet: Temporal-Spatial Fusion Meets Centerline-Guided Diffusion for BEV Mapping

Add code
Mar 04, 2025
Viaarxiv icon

Resource-Efficient Affordance Grounding with Complementary Depth and Semantic Prompts

Add code
Mar 04, 2025
Viaarxiv icon

Event-aided Semantic Scene Completion

Add code
Feb 04, 2025
Figure 1 for Event-aided Semantic Scene Completion
Figure 2 for Event-aided Semantic Scene Completion
Figure 3 for Event-aided Semantic Scene Completion
Figure 4 for Event-aided Semantic Scene Completion
Viaarxiv icon

Reducing the Gap Between Pretrained Speech Enhancement and Recognition Models Using a Real Speech-Trained Bridging Module

Add code
Jan 05, 2025
Viaarxiv icon

Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decoding

Add code
Dec 24, 2024
Figure 1 for Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decoding
Figure 2 for Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decoding
Figure 3 for Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decoding
Viaarxiv icon

Benchmarking the Robustness of Optical Flow Estimation to Corruptions

Add code
Nov 22, 2024
Figure 1 for Benchmarking the Robustness of Optical Flow Estimation to Corruptions
Figure 2 for Benchmarking the Robustness of Optical Flow Estimation to Corruptions
Figure 3 for Benchmarking the Robustness of Optical Flow Estimation to Corruptions
Figure 4 for Benchmarking the Robustness of Optical Flow Estimation to Corruptions
Viaarxiv icon

EI-Nexus: Towards Unmediated and Flexible Inter-Modality Local Feature Extraction and Matching for Event-Image Data

Add code
Oct 29, 2024
Figure 1 for EI-Nexus: Towards Unmediated and Flexible Inter-Modality Local Feature Extraction and Matching for Event-Image Data
Figure 2 for EI-Nexus: Towards Unmediated and Flexible Inter-Modality Local Feature Extraction and Matching for Event-Image Data
Figure 3 for EI-Nexus: Towards Unmediated and Flexible Inter-Modality Local Feature Extraction and Matching for Event-Image Data
Figure 4 for EI-Nexus: Towards Unmediated and Flexible Inter-Modality Local Feature Extraction and Matching for Event-Image Data
Viaarxiv icon