Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks277 from public data
- Going deeper into action recognition: A survey651
This survey provides a comprehensive review of the notable steps taken towards recognizing human actions, starting with the pioneering methods that use handcrafted representations, and then, navigating into the realm of deep learning based approaches.
- 463
- 450
- Hierarchical Neural Architecture Search for Deep Stereo Matching438
This paper proposes the first end-to-end hierarchical NAS framework for deep stereo matching by incorporating task-specific human knowledge into the neural architecture search framework and optimizing the architectures of the entire pipeline jointly.
- Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices316
To encode the geometry of the manifold in the mapping, a family of provably positive definite kernels on the Riemannian manifold of SPD matrices is introduced, derived from the Gaussian kernel, but exploit different metrics on the manifold.
- 308
- Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels270
It is shown that many popular algorithms designed for Euclidean spaces, such as support vector machines, discriminant analysis and principal component analysis can be generalized to Riemannian manifolds with the help of such positive definite Gaussian kernels.
- A Robust Volumetric Transformer for Accurate 3D Tumor Segmentation241
A Transformer architecture for volumetric segmentation, a challenging task that requires keeping a complex balance in encoding local and global spatial cues, and preserving information along all axes of the volume, is proposed.
- Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning240
A distillation algorithm is introduced to address the problem of FSCIL and a method based on an attention mechanism on multiple parallel embeddings of visual data to align visual and semantic vectors, which reduces issues related to catastrophic forgetting.
- Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods228
This paper proposes to model the mapping from the high-dimensional SPD manifold to the low-dimensional one with an orthonormal projection and shows that learning can be expressed as an optimization problem on a Grassmann manifold and discusses fast solutions for special cases.
- From Manifold to Manifold: Geometry-Aware Dimensionality Reduction for SPD Matrices214
An approach that lets us handle high-dimensional SPD matrices by constructing a lower-dimensional, more discriminative SPD manifold is introduced and leads to a significant accuracy gain over state-of-the-art methods.
- 214
- Sparse Coding and Dictionary Learning for Symmetric Positive Definite Matrices: A Kernel Approach212
Experiments show that the proposed sparse coding approach achieves notable improvements in discrimination accuracy, in comparison to state-of-the-art methods such as tensor sparse coding, Riemannian locality preserving projection, and symmetry-driven accumulation of local features.
- Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective207
This work presents a novel perspective to unsupervised saliency detection through learning from multiple noisy labeling generated by "weak" and "noisy" unsuper supervised handcrafted saliency methods.
- Spatio-temporal covariance descriptors for action and gesture recognition173
A new action and gesture recognition method based on spatio-temporal covariance descriptors and a weighted Riemannian locality preserving projection approach that takes into account the curved space formed by the descriptors is proposed.
- Dictionary Learning and Sparse Coding on Grassmann Manifolds: An Extrinsic Solution165
To handle non-linearity in data, this paper proposes to embed Grassmann manifolds into the space of symmetric matrices by an isometric mapping, which enables it to devise a closed-form solution for updating a Grassmann dictionary, atom by atom.
- On Learning the Geodesic Path for Incremental Learning164
This work proposes to firstly construct low-dimensional manifolds for previous and current responses and minimize the dissimilarity between the responses along the geodesic connecting the manifolds which induces a more formidable knowledge distillation with smooth properties which preserves the past knowledge more efficiently as observed by the comprehensive empirical study.
- 161
- 145
- Distribution-matching embedding for visual domain adaptation119
This paper introduces a Distribution-Matching Embedding approach: An unsupervised domain adaptation method that overcomes this issue by mapping the data to a latent space where the distance between the empirical distributions of the source and target examples is minimized.
- Bregman Divergences for Infinite Dimensional Covariance Matrices114
This work proposes an approach to computing and comparing Covariance Descriptors (CovDs) in infinite-dimensional spaces by first mapping the original data to a high-dimensional Hilbert space, and only then compute the CovDs.
- Uncertainty-guided dual-views for semi-supervised volumetric medical image segmentation113
Empirical results suggest that an uncertainty-guided co-training framework can make two neural networks robust to data artefacts and have the ability to generate plausible segmentation masks that can be helpful for semi-automated segmentation processes.
- Learning an Invariant Hilbert Space for Domain Adaptation112
This paper introduces a learning scheme to construct a Hilbert space (i.e., a vector space along its inner product) to address both unsupervised and semi-supervised domain adaptation problems to simultaneously minimizing a notion of domain variance while maximizing a measure of discriminatory power.
- Implicit Motion Handling for Video Camouflaged Object Detection111
A new video camouflaged object detection framework that can exploit both short-term dynamics and long-term temporal consistency to detect camouflaged objects from video frames is proposed and unifies motion estimation and object segmentation within a single optimization framework.
- 109
- 101
- Expanding the Family of Grassmannian Kernels: An Embedding Perspective101
This work introduces several positive definite Grassmannian kernels, including universal ones, and demonstrates their superiority over previously-known kernels in various tasks, such as classification, clustering, sparse coding and hashing.
- 96
- Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds93
The aim of building a bridge between the two realms is to address the problem of sparse coding and dictionary learning in Grassmann manifolds, i.e., the space of linear subspaces by embedding into higher dimensional Hilbert spaces by an isometric mapping.
- Generalized Rank Pooling for Activity Recognition87
A novel pooling method, generalized rank pooling (GRP), that takes as input, features from the intermediate layers of a CNN that is trained on tiny sub-sequences, and produces as output the parameters of a subspace which provides a low-rank approximation to the features and preserves their temporal order is proposed.
- 84
- Face Recognition from Still Images to Video Sequences: A Local-Feature-Based Framework84
The experimental results show that Multi-region Histogram (MRH) feature is more discriminative for face recognition compared to Local Binary Patterns (LBP) and raw pixel intensity and is more suitable for CCTV surveillance systems with constraints on the number of images and the speed of processing.
- 82
- 81
- Sparse Coding on Symmetric Positive Definite Manifolds Using Bregman Divergences78
This paper proposes to seek sparse coding by embedding the space of SPD matrices into the Hilbert spaces through two types of the Bregman matrix divergences, which not only leads to an efficient way of performing sparse coding but also an online and iterative scheme for dictionary learning.
- 77
- HAC++: Towards 100X Compression of 3D Gaussian Splatting75
This paper proposes HAC++, which explicitly minimizes the 3D Gaussian Splatting representation’s entropy during optimization, enabling efficient arithmetic coding after training for compressed storage and incorporating an adaptive masking strategy to eliminate non-effective Gaussians and anchors.
- 75
- Automatic derivation of formal software specifications from informal descriptions75
An interactive system which derives formal specifications of data types and programs from their informal descriptions using common problem-solving techniques such as schemas, analogy, and difference-based reasoning to derive formal specifications.
- Fisher tensors for classifying human epithelial cells74
The conventional bag of word models from Euclidean space to non-Euclidean Riemannian manifolds are extended and utilize them to classify the HEp-2 cells and the proposed framework, while hand-crafted towards cell classification, is a generic framework for object recognition.
- Joint dimensionality reduction and metric learning: a geometric take69
A Riemannian framework is developed to jointly learn a mapping performing dimensionality reduction and a metric in the induced space and it is shown that this approach yields competitive runtimes with and higher accuracy than state-of-the-art metric learning algorithms.
- Fast Feedforward 3D Gaussian Splatting Compression67
This work introduces Fast Compression of 3D Gaussian Splatting (FCGS), an optimization-free model that can compress 3DGS representations rapidly in a single feed-forward pass, which significantly reduces compression time from minutes to seconds.
- Adaptive Poincaré Point to Set Distance for Few-Shot Classification64
This paper proposes to learn a context-aware hyperbolic metric to characterize the distance between a point and a set associated with a learned set to set distance and empirically shows that such metric yields robustness in the presence of outliers and achieves a tangible improvement over baseline models.
- Duo-SegNet: Adversarial Dual-Views for Semi-supervised Medical Image Segmentation62
Thorough quantitative and qualitative evaluations on several datasets indicate that the proposed semi-supervised image segmentation technique based on the concept of multi-view learning outperforms state-of-the-art medical images segmentation algorithms consistently and comfortably.
- 61
- On Modulating the Gradient for Meta-learning57
A novel meta-learning algorithm with gradient modulation to encourage fast-adaptation of neural networks in the absence of abundant data and which outperforms baselines comfortably while enjoying faster convergence is proposed.
- 57
- Kernel analysis on Grassmann manifolds for action recognition57
This paper proposes graph-based local discriminant analysis that utilises within-class and between-class similarity graphs to characterise intra-class compactness and inter-class separability, respectively and obtains marked improvements in discrimination accuracy.
- Reinforced Attention for Few-Shot Learning and Beyond54
This paper proposes to equip the backbone network with an attention agent, which is trained by reinforcement learning, and designs a reward function based on the prediction of the held-out data, thus helping the attention mechanism to generalize better across the unseen classes.
- Reciprocal Adversarial Learning for Brain Tumor Segmentation: A Solution to BraTS Challenge 2021 Segmentation Task51
The proposed approach yielded better performance in segmentation accuracy for each tumor sub-region, and adhere to the Virtual Adversarial Training approach by generating more adversarial examples via adding some noise on original patient data.
- A knowledge-based approach to automatic program analysis50
A knowledge-based approach for automating the analysis of program source code, called PAT, is proposed, which represents the program information as events and the program analysis knowledge as plans.
- 50
- 49
- Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs49
This work proposes to go beyond state-of-the-art image-set matching techniques and model image-sets as probability distribution functions (PDFs) using kernel density estimators and introduces valid positive definite kernels on the statistical manifolds.
- Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond48
An open problem of artwork identification is studied and a new dataset dubbed Open Museum Identification Challenge (Open MIC), which contains photos of exhibits captured in 10 distinct exhibition spaces of several museums is proposed to stimulate research in domain adaptation, egocentric recognition and few-shot learning.
- Online Dictionary Learning on Symmetric Positive Definite Manifolds with Vision Applications47
This work makes use of the Stein divergence to recast the problem of online dictionary learning on the manifolds to a problem in Reproducing Kernel Hilbert Spaces, for which, efficient algorithms are developed by taking into account the geometric structure of the SPD manifolds.
- 47
- On Generalizing Beyond Domains in Cross-Domain Continual Learning46
It is demonstrated that, to a great extent, existing continual learning algorithms fail to handle the forgetting issue under multiple distributions, while the proposed approach learns new tasks under domain shift with accuracy boosts up to 10% on challenging datasets such as DomainNet and OfficeHome.
- 46
- 44
- 42
- Scalable Deep k-Subspace Clustering41
This paper introduces a method that simultaneously learns an embedding space along subspaces within a deep neural network to minimize a notion of reconstruction error, thus addressing the problem of subspace clustering in an end-to-end learning paradigm.
- Optimizing over Radial Kernels on Compact Manifolds41
It is shown that positive definite radial kernels on the unit n-sphere, the Grassmann manifold and Kendall's shape manifold can be expressed in a simple form whose parameters can be automatically optimized within a support vector machine framework.
- Optimal Local Basis: A Reinforcement Learning Approach for Face Recognition41
Experiments indicate that the proposed method facilitates robust face recognition under pose, illumination and expression variations and is compared with that of Eigenface, Fisherface, Subclass Discriminant Analysis, and Random Subspace LDA methods as well.
- Revisiting Bilinear Pooling: A Coding Perspective39
A new feature fusion algorithm, the factorized bilinear coding (FBC) method, is devised, which can generate compact and discriminative representations with substantially fewer parameters.
- 37
- 36
- A Framework for Shape Analysis via Hilbert Space Embedding35
This work proposes to map shapes on Kendall's shape manifold to a high dimensional Hilbert space where Euclidean geometry applies, and introduces a kernel on this manifold that permits such a mapping, and proves its positive definiteness.
- 33
- 32
- Learning Saliency From Single Noisy Labelling: A Robust Model Fitting Perspective31
This paper calls on the theory of robust model fitting and formulate deep saliency prediction from a single noisy labelling as robust network learning and exploit model consistency across iterations to identify inliers and outliers.
- 30
- 29
- 29
- 29
- Towards fair decentralized benchmarking of healthcare AI algorithms with the Federated Tumor Segmentation (FeTS) challenge28
The authors describe the Federated Tumor Segmentation (FeTS) challenge for the decentralised benchmarking of FL algorithms and evaluation of Healthcare AI algorithm generalizability in real-world cancer imaging datasets.
- Vector Quantized Wasserstein Auto-Encoder28
This work endow discrete distributions over sequences of codewords and learn a deterministic decoder that transports the distribution over the sequences ofcodewords to the data distribution via minimizing a WS distance between them to have a better and more controllable clustering solution.
- 28
- 27
- 27
- 26
- 25
- 24
- 24
- 24
- 24
- On robust biometric identity verification via sparse encoding of faces: Holistic vs local approaches23
- 22
- 21
- 19
- 19
- 19
- 18
- 18
- 18
- 17
- 16
- 16
- 16
- 15
- 15
- 15
- 14
- 14
- 14
- No fuss metric learning, a Hilbert space scenario14
A kernel version of the recently introduced keep it simple and straightforward metric learning method is devised, hence adding a novel dimension to its applicability in scenarios where input data is non-linearly distributed, and proposes two techniques towards projecting on the positive cone in a reproducing kernel Hilbert space.
- Combined Learning of Salient Local Descriptors and Distance Metrics for Image Set Face Verification14
A novel image set matching technique, comprised of robust descriptors of face regions based on local features, partly inspired by the hierarchy in the human visual system, and jointly learning which regions are the most discriminative while finding the optimal mixing weights for combining metrics is proposed.
- 13
- 13
- 13
- 13
- 13
- 13
- On robust face recognition via sparse coding: the good, the bad and the ugly13
Thorough experiments show that the proposed local SR approach obtains considerably better and more robust performance than several previous state-of-the-art holistic SR methods, in both verification and closed-set identification problems.
- 12
- 12
- 12
- 12
- 12
- 12
- 11
- 11
- Using temporal information for recognizing actions from still images11
The use of derived temporal information from the authors' TSN and Embedding learning improves still image action recognition and explores three well established transfer learning frameworks in place of the temporal knowledge transfer method.
- 11
- 11
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation5
MUlti-reSolution data-freE (MUSE) is introduced, which generates images at lower resolutions while using Class Activation Maps (CAMs) to ensure that the generated images retain critical, class-specific features, leading to significant performance improvements.
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- LAVA:Label-efficient Visual Learning and Adaptation2
LAVA learns self-supervised visual representations on the source dataset and ground them using class label semantics to overcome transfer collapse problems associated with supervised pretraining and maximises the gains from unlabelled target data via a novel method which uses multi-crop augmentations to obtain highly robust pseudo-labels.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- DIET: Machine Unlearning on a Data-Diet1
DIET is proposed, a principled retain-data-free unlearning method for VLMs that addresses challenges by leveraging the geometry of hyperbolic space and develops an adaptive scheme based on optimal transport that selects mismatched prototypes for each forget embedding, enabling flexible unlearning dynamics.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- When VLAD Met Hilbert1
This paper addresses two fundamental limitations of VLAD: its requirement for the local descriptors to have vector form and its restriction to linear classifiers due to its high-dimensionality and proposes an approximate formulation that allows us to accelerate the coding process while still benefiting from the properties of kernel VL AD.
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-13. 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.