15 citations · 29 across the 25 of their papers we have counts for
27 papers
TGuide: Faster Autoregressive Video Diffusion via Historical Trajectory Guidance
Zhuo Chen, Bin Zou, Fanyue Wei +3
Can autoregressive video diffusion be accelerated further when only four denoising steps remain? Existing feature caching approaches struggle in this regime, as large feature chang…
SA-Homo: Scale Adaptive Homography Estimation for Scale Variation Scenarios
Shangxuan Xie, Haifeng Wu, Yuhang Wang +2
Homography estimation, as one of the fundamental problems in computer vision, remains challenged by scale variation scenarios where image pairs potentially exhibit significant scal…
MixRea: Benchmarking Explicit-Implicit Reasoning in Large Language Models
Yuanqing Cai, Ziyi Huang, Minhao Liu +3
Large language models (LLMs) are increasingly integrated into high-stakes decision-making. Inspired by the theory of \emph{inattentional blindness} in human cognition, we investiga…
The Devil is in Attention Sharing: Improving Complex Non-rigid Image Editing Faithfulness via Attention Synergy
Zhuo Chen, Fanyue Wei, Runze Xu +4
Training-free image editing with large diffusion models has become practical, yet faithfully performing complex non-rigid edits (e.g., pose or shape changes) remains highly challen…
OmniMotion-X: Versatile Multimodal Whole-Body Motion Generation
Guowei Xu, Yuxuan Bian, Ailing Zeng +6
This paper introduces OmniMotion-X, a versatile multimodal framework for whole-body human motion generation, leveraging an autoregressive diffusion transformer in a unified sequenc…
Balanced Sharpness-Aware Minimization for Imbalanced Regression
Yahao Liu, Qin Wang, Lixin Duan +1
Regression is fundamental in computer vision and is widely used in various tasks including age estimation, depth estimation, target localization, \etc However, real-world data ofte…
S-INF: Towards Realistic Indoor Scene Synthesis via Scene Implicit Neural Field
Zixi Liang, Guowei Xu, Haifeng Wu +3
Learning-based methods have become increasingly popular in 3D indoor scene synthesis (ISS), showing superior performance over traditional optimization-based approaches. These learn…
The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learning
Xinyang Zhou, Fanyue Wei, Lixin Duan +2
Given a textual query along with a corresponding video, the objective of moment retrieval aims to localize the moments relevant to the query within the video. While commendable res…
Towards Unsupervised Model Selection for Domain Adaptive Object Detection
Hengfu Yu, Jinhong Deng, Wen Li +1
Evaluating the performance of deep models in new scenarios has drawn increasing attention in recent years. However, while it is possible to collect data from new scenarios, the ann…
ResCLIP: Residual Attention for Training-free Dense Vision-language Inference
Yuhang Yang, Jinhong Deng, Wen Li +1
While vision-language models like CLIP have shown remarkable success in open-vocabulary tasks, their application is currently confined to image-level tasks, and they still struggle…
Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning
Fanyue Wei, Wei Zeng, Zhenyang Li +3
Personalized text-to-image models allow users to generate varied styles of images (specified with a sentence) for an object (specified with a set of reference images). While remark…
Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction
Guowei Xu, Jiale Tao, Wen Li +1
In the realm of stochastic human motion prediction (SHMP), researchers have often turned to generative models like GANS, VAEs and diffusion models. However, most previous approache…
Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition
Xunsong Li, Pengzhan Sun, Yangcen Liu +2
The interactions between human and objects are important for recognizing object-centric actions. Existing methods usually adopt a two-stage pipeline, where object proposals are fir…
Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer
Yanqi Ge, Jiaqi Liu, Qingnan Fan +6
In this work, we target the task of text-driven style transfer in the context of text-to-image (T2I) diffusion models. The main challenge is consistent structure preservation while…
SSR: SAM is a Strong Regularizer for domain adaptive semantic segmentation
Yanqi Ge, Ye Huang, Wen Li +1
We introduced SSR, which utilizes SAM (segment-anything) as a strong regularizer during training, to greatly enhance the robustness of the image encoder for handling various domain…
Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning
Yanqi Ge, Qiang Nie, Ye Huang +5
One of the ultimate goals of representation learning is to achieve compactness within a class and well-separability between classes. Many outstanding metric-based and prototype-bas…
Learning Motion Refinement for Unsupervised Face Animation
Jiale Tao, Shuhang Gu, Wen Li +1
Unsupervised face animation aims to generate a human face video based on the appearance of a source image, mimicking the motion from a driving video. Existing methods typically ado…
High-level Feature Guided Decoding for Semantic Segmentation
Ye Huang, Di Kang, Shenghua Gao +2
Existing pyramid-based upsamplers (e.g. SemanticFPN), although efficient, usually produce less accurate results compared to dilation-based models when using the same backbone. This…
Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks
Anqi Zhao, Tong Chu, Yahao Liu +3
In this work, we study the black-box targeted attack problem from the model discrepancy perspective. On the theoretical side, we present a generalization error bound for black-box…
Motion and Appearance Adaptation for Cross-Domain Motion Transfer
Borun Xu, Biao Wang, Jinhong Deng +5
Motion transfer aims to transfer the motion of a driving video to a source image. When there are considerable differences between object in the driving video and that in the source…
Motion Transformer for Unsupervised Image Animation
Jiale Tao, Biao Wang, Tiezheng Ge +3
Image animation aims to animate a source image by using motion learned from a driving video. Current state-of-the-art methods typically use convolutional neural networks (CNNs) to…
Cross-domain Detection Transformer based on Spatial-aware and Semantic-aware Token Alignment
Jinhong Deng, Xiaoyue Zhang, Wen Li +1
Detection transformers like DETR have recently shown promising performance on many object detection tasks, but the generalization ability of those methods is still quite challengin…
Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation
Yahao Liu, Jinhong Deng, Jiale Tao +3
Existing works typically treat cross-domain semantic segmentation (CDSS) as a data distribution mismatch problem and focus on aligning the marginal distribution or conditional dist…
Structure-Aware Motion Transfer with Deformable Anchor Model
Jiale Tao, Biao Wang, Borun Xu +4
Given a source image and a driving video depicting the same object type, the motion transfer task aims to generate a video by learning the motion from the driving video while prese…