Ming-Ming Cheng

28

Papers

217

Total Citations

Papers (28)

DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation

VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning

Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation

TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes

Fine-Grained Knowledge Selection and Restoration for Non-exemplar Class Incremental Learning

From Words to Worth: Newborn Article Impact Prediction with LLM

DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data

Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning

TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction

Towards RAW Object Detection in Diverse Conditions

KAC: Kolmogorov-Arnold Classifier for Continual Learning

Re-Aligning Language to Visual Objects with an Agentic Workflow

DISTA-Net: Dynamic Closely-Spaced Infrared Small Target Unmixing

Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning

GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery

RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark

TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction

Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing

Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment

Advancing Textual Prompt Learning with Anchored Attributes

AR-1-to-3: Single Image to Consistent 3D Object via Next-View Prediction

DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation

CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation

CrossKD: Cross-Head Knowledge Distillation for Object Detection

Traffic Scene Parsing through the TSP6K Dataset

PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding

Generative Multi-modal Models are Good Class Incremental Learners