Yonghong Tian

61

Papers

440

Total Citations

Papers (61)

Multiple Expert Brainstorming for Domain Adaptive Person Re-identification

Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline

HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors

EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images

Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset

Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations

Multimodal Quantitative Language for Generative Recommendation

Visual Reinforcement Learning with Residual Action

When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network

From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoning

Multiplication-Free Parallelizable Spiking Neurons with Efficient Spatio-Temporal Dynamics

DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning

Event-based Visible and Infrared Fusion via Multi-task Collaboration

High-Performance Temporal Reversible Spiking Neural Networks with $\mathcal{O}(L)$ Training Memory and $\mathcal{O}(1)$ Inference Cost

Unsupervised Cross-Dataset Transfer Learning for Person Re-Identification

Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles

Part-Regularized Near-Duplicate Vehicle Re-Identification

HRank: Filter Pruning Using High-Rank Feature Map

Retina-Like Visual Image Reconstruction via Spiking Neural Model

AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification

Rethinking Performance Estimation in Neural Architecture Search

High-Speed Image Reconstruction Through Short-Term Plasticity for Spiking Cameras

Towards More Flexible and Accurate Object Tracking With Natural Language: Algorithms and Benchmark

Fine-Grained Object Classification via Self-Supervised Pose Alignment

Unsupervised Deraining: Where Contrastive Learning Meets Self-Similarity

Neural Architecture Search With Representation Mutual Information

Training-Free Transformer Architecture Search

IntraQ: Learning Synthetic Images With Intra-Class Heterogeneity for Zero-Shot Network Quantization

Event-Based Video Reconstruction via Potential-Assisted Spiking Neural Network

Meta Architecture for Point Cloud Analysis

Learning With Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning

Exploiting Multi-Grain Ranking Constraints for Precisely Searching Visually-Similar Vehicles

Learning Long-Term Dependencies for Action Recognition With a Biologically-Inspired Deep Network

Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning

Selectivity or Invariance: Boundary-Aware Salient Object Detection

Multi-Class Part Parsing With Joint Boundary-Semantic Awareness

ReCU: Reviving the Dead Weights in Binary Neural Networks

NeuSpike-Net: High Speed Video Reconstruction via Bio-Inspired Neuromorphic Cameras

Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain

Incorporating Learnable Membrane Time Constant To Enhance Learning of Spiking Neural Networks

Stabilizing Visual Reinforcement Learning via Asymmetric Interactive Cooperation

Simoun: Synergizing Interactive Motion-appearance Understanding for Vision-based Reinforcement Learning

Learning Open Set Network with Discriminative Reciprocal Points

Masked Autoencoders for Point Cloud Self-Supervised Learning

Heterogeneous Relational Complement for Vehicle Re-Identification

Self-Supervised Learning for Color Spike Camera Reconstruction

Asynchronous Collaborative Graph Representation for Frames and Events

RoomPainter: View-Integrated Diffusion for Consistent Indoor Scene Texturing

VLMs-Guided Representation Distillation for Efficient Vision-Based Reinforcement Learning

Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body

AllGCD: Leveraging All Unlabeled Data for Generalized Category Discovery

Efficient Event Camera Data Pretraining with Adaptive Prompt Fusion

AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scenes

Adaptive Discovering and Merging for Incremental Novel Class Discovery

Solving the Catastrophic Forgetting Problem in Generalized Category Discovery

Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN

Deep Residual Learning in Spiking Neural Networks

Spectrum Random Masking for Generalization in Image-based Reinforcement Learning

Hierarchical Adaptive Value Estimation for Multi-modal Visual Reinforcement Learning

Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies

Spike-driven Transformer