Shuo Wang

34

Papers

44

Total Citations

Papers (34)

Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing

TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation

Dynamic Multimodal Prototype Learning in Vision-Language Models

Medical Manifestation-Aware De-Identification

DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection

Enhancing Adversarial Transferability with Checkpoints of a Single Model’s Training

Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-Identification

Boosting Few

Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation

Detect Globally, Refine Locally: A Novel Approach to Saliency Detection

CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification

CAFE: Learning To Condense Dataset by Aligning Features

An Efficient Training Approach for Very Large Scale Face Recognition

Towards Domain Generalization for Multi-View 3D Object Detection in Bird-Eye-View

Feature Shrinkage Pyramid for Camouflaged Object Detection With Transformers

Bi-Directional Distribution Alignment for Transductive Zero-Shot Learning

PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data

Co-Mining: Deep Face Recognition With Noisy Labels

Learning Motion-Appearance Co-Attention for Zero-Shot Video Object Segmentation

Learning from Noisy Data for Semi-Supervised 3D Object Detection

Source-free Depth for Object Pop-out

DETRDistill: A Universal Knowledge Distillation Framework for DETR-families

Boosting Whole Slide Image Classification from the Perspectives of Distribution, Correlation and Magnification

Large-Scale Few-Shot Learning via Multi-Modal Knowledge Discovery

Exclusivity-Consistency Regularized Knowledge Distillation for Face Recognition

Dual Adversarial Network for Deep Active Learning

MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing

Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation

EA-Vit: Efficient Adaptation for Elastic Vision Transformer

Accelerating Diffusion Transformer via Gradient-Optimized Cache

Semantic versus Identity: A Divide-and-Conquer Approach towards Adjustable Medical Image De-Identification

MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation

CoDe: Communication Delay-Tolerant Multi-Agent Collaboration via Dual Alignment of Intent and Timeliness