Picture for Feng Lin

Feng Lin

Peter

Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical Interactions

Add code
May 28, 2024
Viaarxiv icon

MOSS: Motion-based 3D Clothed Human Synthesis from Monocular Video

Add code
May 21, 2024
Viaarxiv icon

Gaussian Control with Hierarchical Semantic Graphs in 3D Human Recovery

Add code
May 21, 2024
Figure 1 for Gaussian Control with Hierarchical Semantic Graphs in 3D Human Recovery
Figure 2 for Gaussian Control with Hierarchical Semantic Graphs in 3D Human Recovery
Figure 3 for Gaussian Control with Hierarchical Semantic Graphs in 3D Human Recovery
Figure 4 for Gaussian Control with Hierarchical Semantic Graphs in 3D Human Recovery
Viaarxiv icon

NieR: Normal-Based Lighting Scene Rendering

Add code
May 21, 2024
Figure 1 for NieR: Normal-Based Lighting Scene Rendering
Figure 2 for NieR: Normal-Based Lighting Scene Rendering
Figure 3 for NieR: Normal-Based Lighting Scene Rendering
Figure 4 for NieR: Normal-Based Lighting Scene Rendering
Viaarxiv icon

RemoCap: Disentangled Representation Learning for Motion Capture

Add code
May 21, 2024
Viaarxiv icon

NOVA-3D: Non-overlapped Views for 3D Anime Character Reconstruction

Add code
May 21, 2024
Viaarxiv icon

When LLM-based Code Generation Meets the Software Development Process

Add code
Mar 23, 2024
Viaarxiv icon

Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection

Add code
Mar 04, 2024
Figure 1 for Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection
Figure 2 for Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection
Figure 3 for Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection
Figure 4 for Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection
Viaarxiv icon

CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge

Add code
Feb 24, 2024
Figure 1 for CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge
Figure 2 for CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge
Figure 3 for CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge
Figure 4 for CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge
Viaarxiv icon

Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding

Add code
Feb 19, 2024
Figure 1 for Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding
Figure 2 for Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding
Figure 3 for Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding
Figure 4 for Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding
Viaarxiv icon