Jinheng Xie

papers

1,140

total citations

papers (14)

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

ICCV 2021arXiv

citations

A Simple Data Augmentation for Feature Distribution Skewed Federated Learning

CVPR 2025arXiv

citations

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

CVPR 2025arXiv

citations

Learning Video Context as Interleaved Multimodal Sequences

ECCV 2024arXiv

citations

Learning Visual Prior via Generative Pre-Training

NEURIPS 2023arXiv

citations

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

ICCV 2025arXiv

citations

CLIMS: Cross Language Image Matching for Weakly Supervised Semantic Segmentation

CVPR 2022

citations

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

CVPR 2022

citations

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

CVPR 2024

citations

Dynamically Masked Discriminator for GANs

NEURIPS 2023

citations

Jinheng Xie

papers (14)

Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

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

Frequency-Driven Imperceptible Adversarial Attack on Semantic Similarity

Show-o2: Improved Native Unified Multimodal Models

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

A Simple Data Augmentation for Feature Distribution Skewed Federated Learning

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

Learning Video Context as Interleaved Multimodal Sequences

Learning Visual Prior via Generative Pre-Training

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

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

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

Dynamically Masked Discriminator for GANs

papers (14)

Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

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

Frequency-Driven Imperceptible Adversarial Attack on Semantic Similarity

Show-o2: Improved Native Unified Multimodal Models

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

A Simple Data Augmentation for Feature Distribution Skewed Federated Learning

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

Learning Video Context as Interleaved Multimodal Sequences

Learning Visual Prior via Generative Pre-Training

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

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

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

Dynamically Masked Discriminator for GANs