Huchuan Lu

30

Papers

342

Total Citations

Papers (30)

Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification

TOP-ReID: Multi-Spectral Object Re-identification with Token Permutation

Multi-view Aggregation Network for Dichotomous Image Segmentation

SUTrack: Towards Simple and Unified Single Object Tracking

Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM

UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory

The Devil is in Temporal Token: High Quality Video Reasoning Segmentation

EVEv2: Improved Baselines for Encoder-Free Vision-Language Models

VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior

Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking

EvSign: Sign Language Recognition and Translation with Streaming Events

CLIMB-ReID: A Hybrid CLIP-Mamba Framework for Person Re-Identification

High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity

ReNeg: Learning Negative Embedding with Reward Guidance

Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding

Mono2Stereo: A Benchmark and Empirical Study for Stereo Conversion

CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting

Efficient Motion Prompt Learning for Robust Visual Tracking

DME: Unveiling the Bias for Better Generalized Monocular Depth Estimation

Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking

CAT: A Unified Click-and-Track Framework for Realistic Tracking

Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters

Towards Automatic Power Battery Detection: New Challenge Benchmark Dataset and Baseline

IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification

DefMamba: Deformable Visual State Space Model

Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception

MambaPro: Multi-Modal Object Re-identification with Mamba Aggregation and Synergistic Prompt

Spider: A Unified Framework for Context-dependent Concept Segmentation

FineRS: Fine-grained Reasoning and Segmentation of Small Objects with Reinforcement Learning

Large Occluded Human Image Completion via Image-Prior Cooperating