193 citations · 298 across the 20 of their papers we have counts for
21 papers
COSMO: Consensus-Driven Shift Modulation for Source-Free Domain Adaptation
Bo Li, Junjie Peng, Xiaohua Xie +1
Source-free domain adaptation (SFDA) adapts a source-trained model to an unlabeled target domain without source data, a practical setting under privacy or storage constraints. Yet…
Physics-Grounded Fluid Video Generation with a Simulation Dataset and Dual-Stream Optical-Flow Supervision
Ruijie Su, Yuanzhi Liang, Xiaohua Xie +1
Video diffusion models generate visually compelling content but routinely violate elementary physics when the subject involves fluids: liquid columns break apart in mid-air, contai…
GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs
Junjie Peng, You Wu, Haoyi Wu +4
Large language models (LLMs) with extended context lengths rely on the key-value (KV) cache to support attention over prior tokens. However, maintaining the KV cache incurs substan…
Thinking Before Matching: A Reinforcement Reasoning Paradigm Towards General Person Re-Identification
Quan Zhang, Jingze Wu, Jialong Wang +3
Learning identity-discriminative representations with multi-scene generality has become a critical objective in person re-identification (ReID). However, mainstream perception-driv…
Training-Free Class Purification for Open-Vocabulary Semantic Segmentation
Qi Chen, Lingxiao Yang, Yun Chen +4
Fine-tuning pre-trained vision-language models has emerged as a powerful approach for enhancing open-vocabulary semantic segmentation (OVSS). However, the substantial computational…
GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting
Zixuan Chen, Guangcong Wang, Jiahao Zhu +2
3D Gaussian Splatting (3DGS) has recently created impressive 3D assets for various applications. However, considering security, capacity, invisibility, and training efficiency, the…
Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion
Yun Chen, Lingxiao Yang, Qi Chen +2
Emotional Voice Conversion aims to manipulate a speech according to a given emotion while preserving non-emotion components. Existing approaches cannot well express fine-grained em…
APRF: Anti-Aliasing Projection Representation Field for Inverse Problem in Imaging
Zixuan Chen, Lingxiao Yang, Jianhuang Lai +1
Sparse-view Computed Tomography (SVCT) reconstruction is an ill-posed inverse problem in imaging that aims to acquire high-quality CT images based on sparsely-sampled measurements.…
CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution
Zixuan Chen, Jian-Huang Lai, Lingxiao Yang +1
Medical image arbitrary-scale super-resolution (MIASSR) has recently gained widespread attention, aiming to super sample medical volumes at arbitrary scales via a single model. How…
Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection
Zixuan Chen, Xiaohua Xie, Lingxiao Yang +1
Anomaly detectors are widely used in industrial manufacturing to detect and localize unknown defects in query images. These detectors are trained on anomaly-free samples and have s…
Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challenges
Junhao Dong, Junxi Chen, Xiaohua Xie +2
Deep learning techniques have achieved superior performance in computer-aided medical image analysis, yet they are still vulnerable to imperceptible adversarial attacks, resulting…
The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training
Junhao Dong, Seyed-Mohsen Moosavi-Dezfooli, Jianhuang Lai +1
Although current deep learning techniques have yielded superior performance on various computer vision tasks, yet they are still vulnerable to adversarial examples. Adversarial tra…
Understanding Weight Similarity of Neural Networks via Chain Normalization Rule and Hypothesis-Training-Testing
Guangcong Wang, Guangrun Wang, Wenqi Liang +1
We present a weight similarity measure method that can quantify the weight similarity of non-convex neural networks. To understand the weight similarity of different trained models…
Texture-guided Saliency Distilling for Unsupervised Salient Object Detection
Huajun Zhou, Bo Qiao, Lingxiao Yang +2
Deep Learning-based Unsupervised Salient Object Detection (USOD) mainly relies on the noisy saliency pseudo labels that have been generated from traditional handcraft methods or pr…
SNN2ANN: A Fast and Memory-Efficient Training Framework for Spiking Neural Networks
Jianxiong Tang, Jianhuang Lai, Xiaohua Xie +2
Spiking neural networks are efficient computation models for low-power environments. Spike-based BP algorithms and ANN-to-SNN (ANN2SNN) conversions are successful techniques for SN…
Restricted Black-box Adversarial Attack Against DeepFake Face Swapping
Junhao Dong, Yuan Wang, Jianhuang Lai +1
DeepFake face swapping presents a significant threat to online security and social media, which can replace the source face in an arbitrary photo/video with the target face of an e…
Cross-Camera Trajectories Help Person Retrieval in a Camera Network
Xin Zhang, Xiaohua Xie, Jianhuang Lai +1
We are concerned with retrieving a query person from multiple videos captured by a non-overlapping camera network. Existing methods often rely on purely visual matching or consider…
Exploring Dual-task Correlation for Pose Guided Person Image Generation
Pengze Zhang, Lingxiao Yang, Jianhuang Lai +1
Pose Guided Person Image Generation (PGPIG) is the task of transforming a person image from the source pose to a given target pose. Most of the existing methods only focus on the i…
Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation
Qi Chen, Lingxiao Yang, Jianhuang Lai +1
Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels has attracted much attention due to low annotation costs. Existing methods often rely on Class Activation…
Benchmarking Deep Models for Salient Object Detection
Huajun Zhou, Yang Lin, Lingxiao Yang +2
In recent years, deep network-based methods have continuously refreshed state-of-the-art performance on Salient Object Detection (SOD) task. However, the performance discrepancy ca…
Activation to Saliency: Forming High-Quality Labels for Completely Unsupervised Salient Object Detection
Huajun Zhou, Peijia Chen, Lingxiao Yang +2
Existing deep learning-based Unsupervised Salient Object Detection (USOD) methods rely on supervised pre-trained deep models. Moreover, they generate pseudo labels based on hand-cr…