284 citations · 637 across the 43 of their papers we have counts for
44 papers
Learning Expressive And Generalizable Motion Features For Face Forgery Detection
Jingyi Zhang, Peng Zhang, Jingjing Wang +2
Previous face forgery detection methods mainly focus on appearance features, which may be easily attacked by sophisticated manipulation. Considering the majority of current face ma…
"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach
Lingyu Gu, Yongqi Du, Yuan Zhang +4
Modern deep neural networks (DNNs) are extremely powerful; however, this comes at the price of increased depth and having more parameters per layer, making their training and infer…
Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation
Hang Du, Xuejun Yan, Jingjing Wang +2
Most existing approaches for point cloud normal estimation aim to locally fit a geometric surface and calculate the normal from the fitted surface. Recently, learning-based methods…
1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection Track
Wei Zhao, Binbin Chen, Weijie Chen +4
OOD-CV challenge is an out-of-distribution generalization task. To solve this problem in object detection track, we propose a simple yet effective Generalize-then-Adapt (G&A) frame…
1st Place Solution for ECCV 2022 OOD-CV Challenge Image Classification Track
Yilu Guo, Xingyue Shi, Weijie Chen +4
OOD-CV challenge is an out-of-distribution generalization task. In this challenge, our core solution can be summarized as that Noisy Label Learning Is A Strong Test-Time Domain Ada…
NeRF-Gaze: A Head-Eye Redirection Parametric Model for Gaze Estimation
Pengwei Yin, Jiawu Dai, Jingjing Wang +2
Gaze estimation is the fundamental basis for many visual tasks. Yet, the high cost of acquiring gaze datasets with 3D annotations hinders the optimization and application of gaze e…
Attention Diversification for Domain Generalization
Rang Meng, Xianfeng Li, Weijie Chen +7
Convolutional neural networks (CNNs) have demonstrated gratifying results at learning discriminative features. However, when applied to unseen domains, state-of-the-art models are…
FBNet: Feedback Network for Point Cloud Completion
Xuejun Yan, Hongyu Yan, Jingjing Wang +5
The rapid development of point cloud learning has driven point cloud completion into a new era. However, the information flows of most existing completion methods are solely feedfo…
Point Cloud Upsampling via Cascaded Refinement Network
Hang Du, Xuejun Yan, Jingjing Wang +2
Point cloud upsampling focuses on generating a dense, uniform and proximity-to-surface point set. Most previous approaches accomplish these objectives by carefully designing a sing…
Multi-Scale Wavelet Transformer for Face Forgery Detection
Jie Liu, Jingjing Wang, Peng Zhang +3
Currently, many face forgery detection methods aggregate spatial and frequency features to enhance the generalization ability and gain promising performance under the cross-dataset…
Semi-supervised Ranking for Object Image Blur Assessment
Qiang Li, Zhaoliang Yao, Jingjing Wang +4
Assessing the blurriness of an object image is fundamentally important to improve the performance for object recognition and retrieval. The main challenge lies in the lack of abund…
Slimmable Domain Adaptation
Rang Meng, Weijie Chen, Shicai Yang +7
Vanilla unsupervised domain adaptation methods tend to optimize the model with fixed neural architecture, which is not very practical in real-world scenarios since the target data…
Label Matching Semi-Supervised Object Detection
Binbin Chen, Weijie Chen, Shicai Yang +6
Semi-supervised object detection has made significant progress with the development of mean teacher driven self-training. Despite the promising results, the label mismatch problem…
Learning Domain Adaptive Object Detection with Probabilistic Teacher
Meilin Chen, Weijie Chen, Shicai Yang +8
Self-training for unsupervised domain adaptive object detection is a challenging task, of which the performance depends heavily on the quality of pseudo boxes. Despite the promisin…
Transductive CLIP with Class-Conditional Contrastive Learning
Junchu Huang, Weijie Chen, Shicai Yang +3
Inspired by the remarkable zero-shot generalization capacity of vision-language pre-trained model, we seek to leverage the supervision from CLIP model to alleviate the burden of da…
2nd Place Solution for ICCV 2021 VIPriors Image Classification Challenge: An Attract-and-Repulse Learning Approach
Yilu Guo, Shicai Yang, Weijie Chen +3
Convolutional neural networks (CNNs) have achieved significant success in image classification by utilizing large-scale datasets. However, it is still of great challenge to learn f…
KRNet: Towards Efficient Knowledge Replay
Yingying Zhang, Qiaoyong Zhong, Di Xie +1
The knowledge replay technique has been widely used in many tasks such as continual learning and continuous domain adaptation. The key lies in how to effectively encode the knowled…
Self-distilled Knowledge Delegator for Exemplar-free Class Incremental Learning
Fanfan Ye, Liang Ma, Qiaoyong Zhong +2
Exemplar-free incremental learning is extremely challenging due to inaccessibility of data from old tasks. In this paper, we attempt to exploit the knowledge encoded in a previousl…
Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition
Kailin Xu, Fanfan Ye, Qiaoyong Zhong +1
In the context of skeleton-based action recognition, graph convolutional networks (GCNs) have been rapidly developed, whereas convolutional neural networks (CNNs) have received les…
Hindsight Reward Tweaking via Conditional Deep Reinforcement Learning
Ning Wei, Jiahua Liang, Di Xie +1
Designing optimal reward functions has been desired but extremely difficult in reinforcement learning (RL). When it comes to modern complex tasks, sophisticated reward functions ar…
TransForensics: Image Forgery Localization with Dense Self-Attention
Jing Hao, Zhixin Zhang, Shicai Yang +2
Nowadays advanced image editing tools and technical skills produce tampered images more realistically, which can easily evade image forensic systems and make authenticity verificat…
Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection
Jinlei Hou, Yingying Zhang, Qiaoyong Zhong +3
Reconstruction-based methods play an important role in unsupervised anomaly detection in images. Ideally, we expect a perfect reconstruction for normal samples and poor reconstruct…
Modulating Localization and Classification for Harmonized Object Detection
Taiheng Zhang, Qiaoyong Zhong, Shiliang Pu +1
Object detection involves two sub-tasks, i.e. localizing objects in an image and classifying them into various categories. For existing CNN-based detectors, we notice the widesprea…
Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptation
Weijie Chen, Luojun Lin, Shicai Yang +4
It is a strong prerequisite to access source data freely in many existing unsupervised domain adaptation approaches. However, source data is agnostic in many practical scenarios du…