Yuanjun Xiong

papers

1,694

total citations

papers (17)

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models

ICLR 2025arXiv

citations

Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models

CVPR 2022arXiv

citations

Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data

ICCV 2025arXiv

citations

Towards Regression-Free Neural Networks for Diverse Compute Platforms

ECCV 2022arXiv

citations

X-Prompt: Generalizable Auto-Regressive Visual Learning with In-Context Prompting

ICCV 2025

citations

Yuanjun Xiong

papers (17)

Learning Self-Consistency for Deepfake Detection

Motion Guided 3D Pose Estimation from Videos

MeMOT: Multi-Object Tracking With Memory

Long Short-Term Transformer for Online Action Detection

Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

Omni-sourced Webly-supervised Learning for Video Recognition

Towards causal benchmarking of bias in face analysis algorithms

Towards Backward-Compatible Representation Learning

TubeR: Tubelet Transformer for Video Action Detection

Positive-Congruent Training: Towards Regression-Free Model Updates

Learning Hierarchical Graph Neural Networks for Image Clustering

Compatibility-Aware Heterogeneous Visual Search

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models

Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models

Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data

Towards Regression-Free Neural Networks for Diverse Compute Platforms

X-Prompt: Generalizable Auto-Regressive Visual Learning with In-Context Prompting

papers (17)

Learning Self-Consistency for Deepfake Detection

Motion Guided 3D Pose Estimation from Videos

MeMOT: Multi-Object Tracking With Memory

Long Short-Term Transformer for Online Action Detection

Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

Omni-sourced Webly-supervised Learning for Video Recognition

Towards causal benchmarking of bias in face analysis algorithms

Towards Backward-Compatible Representation Learning

TubeR: Tubelet Transformer for Video Action Detection

Positive-Congruent Training: Towards Regression-Free Model Updates

Learning Hierarchical Graph Neural Networks for Image Clustering

Compatibility-Aware Heterogeneous Visual Search

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models

Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models

Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data

Towards Regression-Free Neural Networks for Diverse Compute Platforms

X-Prompt: Generalizable Auto-Regressive Visual Learning with In-Context Prompting