Bin Li

55

Papers

2,387

Total Citations

Papers (55)

InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks

Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learning

Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detection

Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling

Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transport

Long-term Temporal Context Gathering for Neural Video Compression

Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks

Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios

ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models

CMA: A Chromaticity Map Adapter for Robust Detection of Screen-Recapture Document Images

DLF: Extreme Image Compression with Dual-generative Latent Fusion

Multi-modal Multi-platform Person Re-Identification: Benchmark and Method

Fast Adaptation for Human Pose Estimation via Meta-Optimization

DiffForensics: Leveraging Diffusion Prior to Image Forgery Detection and Localization

MoML: Online Meta Adaptation for 3D Human Motion Prediction

Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning

Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models

Text Guided Person Image Synthesis

Dual-Stream Multiple Instance Learning Network for Whole Slide Image Classification With Self-Supervised Contrastive Learning

Scene Text Telescope: Text-Focused Scene Image Super-Resolution

Neural Compression-Based Feature Learning for Video Restoration

Towards All-in-One Pre-Training via Maximizing Multi-Modal Mutual Information

Learning Accurate 3D Shape Based on Stereo Polarimetric Imaging

Siamese Image Modeling for Self-Supervised Vision Representation Learning

DeFeeNet: Consecutive 3D Human Motion Prediction With Deviation Feedback

Neural Video Compression With Diverse Contexts

Motion Information Propagation for Neural Video Compression

Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning

Test-time Personalizable Forecasting of 3D Human Poses

Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction

FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs

SPAC: Sparse Partitioning and Adaptive Core Tensor Pruning Model for Knowledge Graph Completion

Towards Practical Real-Time Neural Video Compression

PICD: Versatile Perceptual Image Compression with Diffusion Rendering

MATE: Motion-Augmented Temporal Consistency for Event-based Point Tracking

Probabilistic Verification of Cybersickness in Virtual Reality Through Bayesian Networks

EVER: Edge-Assisted Auto-Verification for Mobile MR-Aided Operation

Foundation Model Driven Appearance Extraction for Robust Multiple Object Tracking

Query-efficient Attack for Black-box Image Inpainting Forensics via Reinforcement Learning

Enhanced Fine-Grained Motion Diffusion for Text-Driven Human Motion Synthesis

Exploring One-Shot Semi-supervised Federated Learning with Pre-trained Diffusion Models

Discriminative Forests Improve Generative Diversity for Generative Adversarial Networks

Generative Latent Coding for Ultra-Low Bitrate Image Compression

Neural Video Compression with Feature Modulation

Rectangular Bounding Process

Scalable Deep Generative Relational Model with High-Order Node Dependence

Continuous-time edge modelling using non-parametric point processes

Deep Contextual Video Compression

An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints

Roadblocks for Temporarily Disabling Shortcuts and Learning New Knowledge

Domain Re-Modulation for Few-Shot Generative Domain Adaptation

Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis

Metadata Dependent Mondrian Processes

Generative Modeling of Infinite Occluded Objects for Compositional Scene Representation