Feng Liu

33

Papers

106

Total Citations

Papers (33)

Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection

ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models

AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification

Deep Kernel Relative Test for Machine-generated Text Detection

SapiensID: Foundation for Human Recognition

HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReID

Visual Persona: Foundation Model for Full-Body Human Customization

Attribute-based Visual Reprogramming for Vision-Language Models

CALM: Consensus-Aware Localized Merging for Multi-Task Learning

DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution

Test-Time Multimodal Backdoor Detection by Contrastive Prompting

Long-tailed Recognition with Model Rebalancing

Enhancing Adversarial Transferability by Balancing Exploration and Exploitation with Gradient-Guided Sampling

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

Anchor-based Maximum Discrepancy for Relative Similarity Testing

NLPrompt: Noise-Label Prompt Learning for Vision-Language Models

Privacy-Preserving Low-Rank Adaptation Against Membership Inference Attacks for Latent Diffusion Models

FloNa: Floor Plan Guided Embodied Visual Navigation

SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model

Distilling CLIP with Dual Guidance for Learning Discriminative Human Body Shape Representation

TIGER: Time-Varying Denoising Model for 3D Point Cloud Generation with Diffusion Process

KeyPoint Relative Position Encoding for Face Recognition

NeuroTree: Hierarchical Functional Brain Pathway Decoding for Mental Health Disorders

Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models

Sample-specific Masks for Visual Reprogramming-based Prompting

MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence

Optimal Kernel Choice for Score Function-based Causal Discovery

Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training

Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data

Move-in-2D: 2D-Conditioned Human Motion Generation

VideoGigaGAN: Towards Detail-rich Video Super-Resolution

Progressive Growing of Video Tokenizers for Temporally Compact Latent Spaces

REGEN: Learning Compact Video Embedding with (Re-)Generative Decoder