Yuanjun Xiong

Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data ICCV 2025 Image and Video Tokenization with Binary Spherical Quantization ICLR 2025 MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models ICLR 2025 X-Prompt: Generalizable Auto-Regressive Visual Learning with In-Context Prompting ICCV 2025 A Full-duplex Speech Dialogue Scheme Based On Large Language Model NeurIPS 2024 Alpha-CLIP: A CLIP Model Focusing on Wherever You Want CVPR 2024 MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs NeurIPS 2024 Harnessing Unrecognizable Faces for Improving Face Recognition WACV 2023 MeMOT: Multi-Object Tracking With Memory CVPR 2022 SSCAP: Self-Supervised Co-Occurrence Action Parsing for Unsupervised Temporal Action Segmentation WACV 2022 Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models CVPR 2022 Towards Regression-Free Neural Networks for Diverse Compute Platforms ECCV 2022 TubeR: Tubelet Transformer for Video Action Detection CVPR 2022 Compatibility-Aware Heterogeneous Visual Search CVPR 2021 Learning Hierarchical Graph Neural Networks for Image Clustering ICCV 2021 Learning Self-Consistency for Deepfake Detection ICCV 2021 Long Short-Term Transformer for Online Action Detection NeurIPS 2021 Positive-Congruent Training: Towards Regression-Free Model Updates CVPR 2021 Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates ACL 2021 Motion Guided 3D Pose Estimation from Videos ECCV 2020 Omni-sourced Webly-supervised Learning for Video Recognition ECCV 2020 Towards Backward-Compatible Representation Learning CVPR 2020 Towards causal benchmarking of bias in face analysis algorithms ECCV 2020 Action Recognition With Spatial-Temporal Discriminative Filter Banks ICCV 2019 Convolutional Sequence Generation for Skeleton-Based Action Synthesis ICCV 2019 Optimizing Video Object Detection via a Scale-Time Lattice CVPR 2018 Recognize Actions by Disentangling Components of Dynamics CVPR 2018 Trajectory Convolution for Action Recognition NeurIPS 2018 Unsupervised Feature Learning via Non-Parametric Instance Discrimination CVPR 2018 Temporal Action Detection With Structured Segment Networks ICCV 2017 UntrimmedNets for Weakly Supervised Action Recognition and Detection CVPR 2017 Recognize Complex Events From Static Images by Fusing Deep Channels CVPR 2015 Zeta Hull Pursuits: Learning Nonconvex Data Hulls NeurIPS 2014 Face Recognition via Archetype Hull Ranking ICCV 2013