Jinheng Xie

12

Papers

102

Total Citations

Papers (12)

Show-o2: Improved Native Unified Multimodal Models

MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities

FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editing

Tune-An-Ellipse: CLIP Has Potential to Find What You Want

CLIMS: Cross Language Image Matching for Weakly Supervised Semantic Segmentation

C2AM: Contrastive Learning of Class-Agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation

Online Refinement of Low-Level Feature Based Activation Map for Weakly Supervised Object Localization

BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

Frequency-Driven Imperceptible Adversarial Attack on Semantic Similarity

A Simple Data Augmentation for Feature Distribution Skewed Federated Learning

Dynamically Masked Discriminator for GANs

Learning Visual Prior via Generative Pre-Training