Li Li

26

Papers

94

Total Citations

Papers (26)

How to Configure Good In-Context Sequence for Visual Question Answering

Offline and Online Optical Flow Enhancement for Deep Video Compression

DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering

Neural Video Compression with Context Modulation

Learned Image Compression with Hierarchical Progressive Context Modeling

StableCodec: Taming One-Step Diffusion for Extreme Image Compression

Few-Shot Domain Adaptation for Learned Image Compression

Flexible Group Count Enables Hassle-Free Structured Pruning

Less Is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation

HandNeRF: Neural Radiance Fields for Animatable Interacting Hands

SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning

Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection

Neural Characteristic Function Learning for Conditional Image Generation

Active Crowd Counting with Limited Supervision

Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation

Augmented Deep Contexts for Spatially Embedded Video Coding

DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection

Secure On-Device Video OOD Detection Without Backpropagation

Unsupervised Kernel-based Multi-view Feature Selection with Robust Self-representation and Binary Hashing

Panoptic Scene Graph Generation with Semantics-Prototype Learning

Ranking-based Client Imitation Selection for Efficient Federated Learning

FedDC: Federated Learning With Non-IID Data via Local Drift Decoupling and Correction

Towards understanding retrosynthesis by energy-based models

Dirichlet Energy Constrained Learning for Deep Graph Neural Networks

VPGTrans: Transfer Visual Prompt Generator across LLMs

CLIP4HOI: Towards Adapting CLIP for Practical Zero-Shot HOI Detection