Picture for Yu Hu

Yu Hu

DCF-DS: Deep Cascade Fusion of Diarization and Separation for Speech Recognition under Realistic Single-Channel Conditions

Add code
Nov 11, 2024
Viaarxiv icon

Seeing Through Pixel Motion: Learning Obstacle Avoidance from Optical Flow with One Camera

Add code
Nov 07, 2024
Figure 1 for Seeing Through Pixel Motion: Learning Obstacle Avoidance from Optical Flow with One Camera
Figure 2 for Seeing Through Pixel Motion: Learning Obstacle Avoidance from Optical Flow with One Camera
Figure 3 for Seeing Through Pixel Motion: Learning Obstacle Avoidance from Optical Flow with One Camera
Figure 4 for Seeing Through Pixel Motion: Learning Obstacle Avoidance from Optical Flow with One Camera
Viaarxiv icon

WildOcc: A Benchmark for Off-Road 3D Semantic Occupancy Prediction

Add code
Oct 21, 2024
Viaarxiv icon

Autonomous Driving in Unstructured Environments: How Far Have We Come?

Add code
Oct 10, 2024
Viaarxiv icon

Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity

Add code
Sep 09, 2024
Figure 1 for Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity
Figure 2 for Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity
Figure 3 for Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity
Figure 4 for Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity
Viaarxiv icon

TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Semantic Segmentation

Add code
Aug 28, 2024
Figure 1 for TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Semantic Segmentation
Figure 2 for TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Semantic Segmentation
Figure 3 for TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Semantic Segmentation
Figure 4 for TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Semantic Segmentation
Viaarxiv icon

Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physics

Add code
Jul 16, 2024
Figure 1 for Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physics
Figure 2 for Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physics
Figure 3 for Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physics
Figure 4 for Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physics
Viaarxiv icon

PID: Physics-Informed Diffusion Model for Infrared Image Generation

Add code
Jul 12, 2024
Viaarxiv icon

SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding

Add code
Jun 13, 2024
Viaarxiv icon

FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining

Add code
Apr 15, 2024
Viaarxiv icon