Li Zhang

73

Papers

635

Total Citations

Papers (73)

Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting

NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields

Calibrating Large Language Models with Sample Consistency

Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning

Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping

GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting

LaneGraph2Seq: Lane Topology Extraction with Language Model via Vertex-Edge Encoding and Connectivity Enhancement

Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition

Improving Gaussian Splatting with Localized Points Management

Dual-view X-ray Detection: Can AI Detect Prohibited Items from Dual-view X-ray Images like Humans?

Effective Lymph Nodes Detection in CT Scans Using Location Debiased Query Selection and Contrastive Query Representation in Transformer

CatmullRom Splines-Based Regression for Image Forgery Localization

FrameQuant: Flexible Low-Bit Quantization for Transformers

TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling

Causal-IQA: Towards the Generalization of Image Quality Assessment Based on Causal Inference

BLO-SAM: Bi-level Optimization Based Finetuning of the Segment Anything Model for Overfitting-Preventing Semantic Segmentation

Learning a Discriminative Null Space for Person Re-Identification

Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation

Spatially Adaptive Computation Time for Residual Networks

Learning a Deep Embedding Model for Zero-Shot Learning

Learning to Compare: Relation Network for Few-Shot Learning

Fast Online Object Tracking and Segmentation: A Unifying Approach

Style Normalization and Restitution for Generalizable Person Re-Identification

Attention Scaling for Crowd Counting

Strip Pooling: Rethinking Spatial Pooling for Scene Parsing

Dynamic Graph Message Passing Networks

Instance Credibility Inference for Few-Shot Learning

What Deep CNNs Benefit From Global Covariance Pooling: An Optimization Perspective

Delving into Data: Effectively Substitute Training for Black-box Attack

Learning Dynamic Alignment via Meta-Filter for Few-Shot Learning

Robust and Accurate Object Detection via Adversarial Learning

Rethinking Semantic Segmentation From a Sequence-to-Sequence Perspective With Transformers

MoViNets: Mobile Video Networks for Efficient Video Recognition

Depth-Conditioned Dynamic Message Propagation for Monocular 3D Object Detection

ONCE-3DLanes: Building Monocular 3D Lane Detection

Generative Semantic Segmentation

Train-Once-for-All Personalization

Devil Is in the Queries: Advancing Mask Transformers for Real-World Medical Image Segmentation and Out-of-Distribution Localization

FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks

Discriminative Low-Rank Tracking

Decoder Network Over Lightweight Reconstructed Feature for Fast Semantic Style Transfer

A Closed-Form Solution to Universal Style Transfer

Simpler Is Better: Few-Shot Semantic Segmentation With Classifier Weight Transformer

The Devil Is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection

PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection

Translating Images to Road Network: A Non-Autoregressive Sequence-to-Sequence Approach

Few-shot Action Recognition with Permutation-invariant Attention

Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation

Improving Semantic Segmentation via Decoupled Body and Edge Supervision

XingGAN for Person Image Generation

CelebV-HQ: A Large-Scale Video Facial Attributes Dataset

Memory-Augmented Model-Driven Network for Pansharpening

Accelerating Score-Based Generative Models with Preconditioned Diffusion Sampling

Learning Ego 3D Representation As Ray Tracing

FashionViL: Fashion-Focused Vision-and-Language Representation Learning

RCLane: Relay Chain Prediction for Lane Detection

Nearly Optimal Private LASSO

Boundary-Sensitive Pre-Training for Temporal Localization in Videos

IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracing

TensoFlow: Tensorial Flow-based Sampler for Inverse Rendering

GaPT-DAR: Category-level Garments Pose Tracking via Integrated 2D Deformation and 3D Reconstruction

UniScene: Unified Occupancy-centric Driving Scene Generation

Driving View Synthesis on Free-form Trajectories with Generative Prior

BézierGS: Dynamic Urban Scene Reconstruction with Bézier Curve Gaussian Splatting

An Information-Theoretic Regularizer for Lossy Neural Image Compression

Rethinking Layered Graphic Design Generation with a Top-Down Approach

R^2-Art: Category-Level Articulation Pose Estimation from Single RGB Image via Cascade Render Strategy

LoGoFair: Post-Processing for Local and Global Fairness in Federated Learning

Rankmax: An Adaptive Projection Alternative to the Softmax Function

Progressive Coordinate Transforms for Monocular 3D Object Detection

SOFT: Softmax-free Transformer with Linear Complexity

DeepInteraction: 3D Object Detection via Modality Interaction

SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling