Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Xilin ChenSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works68 from public data
- A Riemannian Network for SPD Matrix Learning564
A Riemannian network architecture is built to open up a new direction of SPD matrix non-linear learning in a deep model and it is shown that the proposed SPD matrix network can be simply trained and outperform existing SPD matrix learning and state-of-the-art methods in three typical visual classification tasks.
- Deep Learning on Lie Groups for Skeleton-Based Action Recognition300
The Lie group structure is incorporated into a deep network architecture to learn more appropriate Lie group features for 3D action recognition and a logarithm mapping layer is proposed to map the resulting manifold data into a tangent space that facilitates the application of regular output layers for the final classification.
- Log-Euclidean metric learning on symmetric positive definite Manifold with application to image set classification269
This paper proposes a novel metric learning approach to work directly on logarithms of SPD matrices by learning a tangent map that can directly transform the matrix Log-Euclidean Metric from the original tangent space to a new tangentspace of more discriminability.
- 250
- Combining Multiple Kernel Methods on Riemannian Manifold for Emotion Recognition in the Wild213
The method for the Emotion Recognition in the Wild Challenge (EmotiW 2014) is presented, and an optimal fusion of classifiers learned from different kernels and different modalities (video and audio) is conducted at the decision level for further boosting the performance.
- Building Deep Networks on Grassmann Manifolds206
This paper proposes a deep network architecture by generalizing the Euclidean network paradigm to Grassmann manifolds and designs full rank mapping layers to transform input Grassmannian data to more desirable ones, and exploits re-orthonormalization layers to normalize the resulting matrices.
- Covariance Pooling for Facial Expression Recognition181
The benefits of using a manifold network structure for covariance pooling to improve facial expression recognition are explored and the advantage of pooling image-set features temporally by stacking the designed manifold network of covariance Pooling on top of convolutional network layers is demonstrated.
- Wasserstein Divergence for GANs167
A novel Wasserstein divergence (W-div) is proposed, which is a relaxed version of W-met and does not require the k-Lipschitz constraint and is introduced as a concrete application, which can faithfully approximate W-div through optimization.
- 161
- 153
- Sliced Wasserstein Generative Models150
This paper proposes to approximate SWDs with a small number of parameterized orthogonal projections in an end-to-end deep learning fashion and designs two types of differentiable SWD blocks to equip modern generative frameworks---Auto-Encoders and Generative Adversarial Networks.
- Face recognition on large-scale video in the wild with hybrid Euclidean-and-Riemannian metric learning102
A novel Hybrid Euclidean-and-Riemannian Metric Learning (HERML) method to fuse multiple statistics of image set that has a clear superiority over the state-of-the-art set-based methods for large-scale video-based face recognition.
- Freestyle Layout-to-Image Synthesis95
This work introduces a new module called Rectified Cross-Attention (RCA) that can be conveniently plugged in the diffusion model to integrate semantic masks, and opts to leverage large-scale pre-trained text-to-image diffusion models to achieve the generation of unseen semantics.
- 93
- A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials91
A continual deepfake detection benchmark (CDDB) over a new collection of deepfakes from both known and unknown generative models is suggested, which is clearly more challenging than the existing benchmarks, and offers a suitable evaluation avenue to the future research.
- Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search76
A new reinforcement learning (RL) based neural architecture search (NAS) methodology for effective and efficient generative adversarial network (GAN) architecture search that exploits an off-policy GAN architecture search algorithm that makes efficient use of the samples generated by previous policies.
- Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video76
A novel metric learning framework to learn a distance metric across a Euclidean space and a Riemannian manifold to fuse average appearance and pattern variation of faces within one video to improve face recognition from videos is proposed.
- 71
- Partial least squares regression on grassmannian manifold for emotion recognition65
For each video clip, all frames are represented as an image set, which can be modeled as a linear subspace to be embedded in Grassmannian manifold and an optimal fusion of classifiers learned from both modalities is conducted at decision level.
- 53
- 50
- Direct Differentiable Augmentation Search48
This paper proposes an efficient differentiable search algorithm called Direct Differentiable Augmentation Search (DDAS), which exploits meta-learning with one-step gradient update and continuous relaxation to the expected training loss for efficient search.
- Riemannian Local Mechanism for SPD Neural Networks43
This work first analyses the convolution operator commonly used for capturing local information in Euclidean deep networks from the perspective of a higher level of abstraction afforded by category theory, and defines the local Information in the SPD manifold and designs a multi-scale submanifold block for mining local geometry.
- 43
- Geometry-Aware Similarity Learning on SPD Manifolds for Visual Recognition43
A geometry-aware SPD similarity learning (SPDSL) framework to learn discriminative SPD features by directly pursuing a manifold-manifold transformation matrix of full column rank is proposed.
- 40
- 37
- Benchmarking Still-to-Video Face Recognition via Partial and Local Linear Discriminant Analysis on COX-S2V Dataset36
Evaluation results not only show the grand challenges of the COX-S2V, but also validate the effectiveness of the proposed PaLo-LDA method over the competitive methods.
- Hybrid Euclidean-and-Riemannian Metric Learning for Image Set Classification30
A Hybrid Euclidean-and-Riemannian Metric Learning (HERML) method to exploit both Euclidan and Riemannia metrics for embedding their original spaces into high dimensional Hilbert spaces and then jointly learn hybrid metrics with discriminant constraint is proposed.
- Efficient Conditional GAN Transfer with Knowledge Propagation across Classes29
A new GAN transfer method to explicitly propagate the knowledge from the old classes to the new classes, with the BN parameters increasing linearly with the number of new classes.
- 29
- OpenSDI: Spotting Diffusion-Generated Images in the Open World28
MaskCLIP is introduced, an SPM-based model that aligns Contrastive Language-Image Pre-Training (CLIP) with Masked Autoencoder with Masked Autoencoder (MAE) and significantly outperforms current state-of-the-art methods for the OpenSDI challenge.
- Neural Architecture Search as Sparse Supernet27
This paper model the NAS problem as a sparse supernet using a new continuous architecture representation with a mixture of sparsity constraints to optimize the proposed sparse supernets using a hierarchical accelerated proximal gradient algorithm within a bi-level optimization framework.
- AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results24
This paper reviews the video extreme super-resolution challenge associated with the AIM 2020 workshop at ECCV 2020 and gauges the state-of-the-art for such a demanding task, where fidelity to the ground truth is measured by PSNR and SSIM.
- Manifold-Valued Image Generation with Wasserstein Generative Adversarial Nets21
This paper formulates the problem of generating manifold-valued images and exploits three typical instances: hue-saturation-value (HSV) color image generation, chromaticity-brightness (CB) colorimage generation, and diffusion-tensor (DT) image generation and introduces a theorem of optimal transport to derive a new Wasserstein distance of data distributions on complete manifolds.
- Adaptive Log-Euclidean Metrics for SPD Matrix Learning20
Adaptive Log-Euclidean Metrics (ALEMs) are proposed, which extend the widely used Log-Euclidean Metric (LEM) and contain learnable parameters, which can better adapt to the complex dynamics of Riemannian neural networks with minor extra computations.
- Generative Flows with Invertible Attentions19
Two types of invertible attention mechanisms are introduced, i.e., map-based and transformer-based attentions, for both unconditional and conditional generative flows, to exploit a masked scheme of these two attentions to learn long-range data dependencies in the context ofGenerative flows.
- 17
- Benchmarking Deepart Detection16
This paper establishes a deepart detection database (DDDB) that consists of a set of high-quality conventional art images (conarts) and five sets of deepart images generated by five state-of-the-art deepfake models, and suggests four benchmark evaluations and four families of solutions on the constructed DDDB.
- NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results16
This paper reviews the NTIRE 2020 challenge on video quality mapping (VQM), which addresses the issues of quality mapping from source video domain to target video domain, and some existing methods are evaluated, showing promising solutions to the weakly-supervised videoquality mapping problem.
- 15
- Facial Emotion Recognition with Noisy Multi-task Annotations15
This work introduces a new problem of facial emotion recognition with noisy multi-task annotations, and suggests a formulation from the point of joint distribution match view, which aims at learning more reliable correlations among raw facial images and multi- task labels, resulting in the reduction of noise influence.
- Cross-view Graph Embedding15
A new algorithm named Cross-view Local Discriminant Analysis (CLODA) is presented, different from previous cross-view methods only preserving inter-view discriminant information or the intra-view local structure, CLODA preserves the local structure and the discriminant Information of both intra-View and inter-View.
- Towards an Understanding of Our World by GANing Videos in the Wild.14
This work presents the first video generation framework that works in the wild, without making any assumption on the videos' content, and outperforms the state-of-the-art methods even when the static background assumption is valid.
- 13
- 13
- An Efficient Recurrent Adversarial Framework for Unsupervised Real-Time Video Enhancement10
This work proposes an efficient adversarial video enhancement framework that learns directly from unpaired video examples and introduces new recurrent cells that consist of interleaved local and global modules for implicit integration of spatial and temporal information.
- Neural Architecture Search for Efficient Uncalibrated Deep Photometric Stereo10
This work uses differentiable neural architecture search (NAS) strategy to find uncalibrated PS architecture automatically, and defines a discrete search space for a light calibration network and a normal estimation network, respectively.
- 9
- 8
- 8
- 7
- 6
- Weakly Paired Multi-Domain Image Translation5
The proposed multi-domain image translation method consists of an attention-based generator and a two-stream discriminator that deals with misalignment between source and target images, including foreground objects such as cars and pedestrians.
- 5
- Manifold-valued Image Generation with Wasserstein Adversarial Networks.4
This paper makes the first attempt to formulate the problem of generating manifold-valued images, which are frequently encountered in real-world applications and generalize the state-of-the-art technique of Wasserstein GANs to the manifold context with exploiting Riemannian geometry.
- 3
- Penny-Wise and Pound-Foolish in Deepfake Detection1
A novel learning framework (PoundNet) is proposed for generalization of deepfake detection on a pre-trained vision-language model that incorporates a learnable prompt design and a balanced objective to preserve broad knowledge from upstream tasks (object classification) while enhancing generalization for downstream tasks (deepfake detection).
- 1
- 1
- –
- –
- –
- In-Context Translation: Towards Unifying Image Recognition, Processing, and Generation–
In-Context Translation (ICT), a general learning framework to unify visual recognition, low-level image processing, and conditional image generation, and edge-to-image synthesis, is proposed.
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.