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
- Alex J. SmolaSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works186 from public data
- Image-Based Recommendations on Styles and Substitutes3,040
The approach is not based on fine-grained modeling of user annotations but rather on capturing the largest dataset possible and developing a scalable method for uncovering human notions of the visual relationships within.
- A Survey on Deep Neural Network Pruning: Taxonomy, Comparison, Analysis, and Recommendations599
This survey provides a comprehensive review of existing research works on deep neural network pruning in a taxonomy of 1) universal/specific speedup, 2) when to prune, 3) how to prune, and 4) fusion of pruning and other compression techniques.
- 497
- From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur439
This work directly estimates the motion flow from the blurred image through a fully-convolutional deep neural network (FCN) and recovers the unblurred image from the estimated motion flow and is the first universal end-to-end mapping from the blur image to the dense motion flow.
- Fast Supervised Hashing with Decision Trees for High-Dimensional Data430
Experiments demonstrate that the proposed method significantly outperforms most state-of-the-art methods in retrieval precision and training time, and is orders of magnitude faster than many methods in terms of training time.
- 371
- 314
- Attention-Guided Network for Ghost-Free High Dynamic Range Imaging313
The proposed AHDRNet is a non-flow-based method, which can also avoid the artifacts generated by optical-flow estimation error, and can achieve state-of-the-art quantitative and qualitative results.
- 287
- 271
- Hash Kernels for Structured Data241
This work generalizes previous work using sampling and shows a principled way to compute the kernel matrix for data streams and sparse feature spaces and gives deviation bounds from the exact kernel matrix.
- 209
- 194
- Seeing Deeply and Bidirectionally: A Deep Learning Approach for Single Image Reflection Removal191
This work argues that, to remove reflection truly well, it should estimate the reflection and utilize it to estimate the background image, and proposes a cascade deep neural network, which estimates both the Background image and the reflection.
- Human Action Segmentation and Recognition Using Discriminative Semi-Markov Models148
This paper proposes a discriminative semi-Markov model approach, and defines a set of features over boundary frames, segments, as well as neighboring segments that enable it to conveniently capture a combination of local and global features that best represent each specific action type.
- 146
- Implicit Sample Extension for Unsupervised Person Re-Identification144
An Implicit Sample Extension method to generate support samples from actual samples and their neighbouring clusters in the embedding space through a progressive linear interpolation (PLI) strategy, which reduces the “sub and mixed” clustering errors, thus improving the Re-ID performance.
- 142
- 137
- Active Learning by Feature Mixing135
This paper proposes a novel method for batch AL called ALFA-Mix, which identifies unlabelled instances with sufficiently-distinct features by seeking inconsistencies in predictions resulting from interventions on their representations, and derives an efficient implementation based on a closed-form solution to the optimal interpolation causing changes in predictions.
- 134
- 133
- 129
- Wind turbine power output prediction using a new hybrid neuro-evolutionary method121
A novel composite deep learning-based evolutionary approach for accurate forecasting of the power output in wind-turbine farms, developed in three stages, supported the superiority of the proposed hybrid model in terms of accurate forecasting and computational runtime compared with earlier published hybrid models.
- Learning Deep Gradient Descent Optimization for Image Deconvolution120
A recurrent gradient descent network (RGDN) is proposed by systematically incorporating deep neural networks into a fully parameterized gradient descent scheme and learns an implicit image prior and a universal update rule through recursive supervision.
- 110
- COVID-19 Chest CT Image Segmentation Network by Multi-Scale Fusion and Enhancement Operations109
A new deep convolutional neural network tailored for segmenting the chest CT images with COVID-19 infections is established and achieves state-of-the-art performance.
- Efficient dense labelling of human activity sequences from wearables using fully convolutional networks109
The proposed approach is able to outperform the state-of-the-arts in terms of sample-based classification and activity-based label misalignment measures on three challenging datasets: Opportunity, Hand Gesture, and the new dataset—an activity dataset the authors release based on a wearable sensor worn by hospitalised patients.
- 108
- RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion107
A light-weight Dimensional Decomposition Residual network (DDR) for 3D dense prediction tasks is introduced and the proposed multi-scale fusion mechanism for depth and color image can improve the completion and segmentation accuracy simultaneously.
- Attend and Discriminate105
This work proposes learning to exploit the latent relationships between multi-channel sensor modalities and specific activities, and incorporates a classification loss criterion to encourage minimal intra-class representation differences whilst maximising inter-class differences to achieve more discriminative features.
- 97
- Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos90
This paper proposes an end-to-end trainable framework for the social task, and sets the state-of-the-art results on two widely adopted benchmarks for the traditional group activity recognition task.
- 85
- 84
- Cluster Sparsity Field: An Internal Hyperspectral Imagery Prior for Reconstruction84
A novel cluster sparsity field based HSI reconstruction framework which explicitly models both the intrinsic correlation between measurements within the spectrum for a particular pixel, and the similarity between pixels due to the spatial structure of the HSI, thus combating the effects of noise corruption or undersampling.
- Non-sparse linear representations for visual tracking with online reservoir metric learning80
This work proposes a visual tracker based on non-sparse linear representations, which admit an efficient closed-form solution without sacrificing accuracy, and shows that online metric learning using proximity comparison significantly improves the robustness of the tracking.
- Auto-Embedding Generative Adversarial Networks For High Resolution Image Synthesis74
A novel GAN is developed called auto-embedding generative adversarial network, which simultaneously encodes the global structure features and captures the fine-grained details of real images, and is able to produce high-resolution images of promising quality directly from the input noise.
- 63
- 59
- 57
- Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning56
A Sparse neural Network for Continual Learning (SNCL), which employs variational Bayesian sparsity priors on the activations of the neurons in all layers and achieves state-of-the-art result for mitigating forgetting.
- 56
- Dual-Attention-Guided Network for Ghost-Free High Dynamic Range Imaging51
This work proposes a novel dual-attention-guided end-to-end deep neural network, called DAHDRNet, which produces high-quality ghost-free HDR images and employs a hybrid loss function, which consists of a perceptual loss, a total variation loss, and a content loss to recover photo-realistic images.
- 51
- 50
- Deep Auto-Set46
This paper addresses HAR more naturally as a set prediction problem where the predictions are sets of ongoing activity elements with unfixed and unknown cardinality for the first time, and presents a novel HAR approach that learns to output activity sets using deep neural networks.
- 46
- 46
- NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results45
This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022, and the competition set-up, datasets, proposed methods and their results.
- Robust Tracking with Weighted Online Structured Learning45
This work develops a novel weighted form of online risk which allows more subtlety in its representation and proposes a principled approach to weighted online learning using weighted reservoir sampling and a weighted regret bound as a theoretical guarantee of performance.
- 44
- 42
- 41
- Dimensionality reduction via compressive sensing40
This paper proposes novel unsupervised and semi-supervised dimensionality reduction algorithms by exploiting sparse data representations and shows that the proposed approaches outperform state-of-the-art dimensionality Reduction methods.
- 38
- High dynamic range imaging via gradient-aware context aggregation network38
The proposed HDR imaging approach that aggregates the information from multiple LDR images with guidance from image gradient domain generates artifact-free images by integrating the image gradient information and the image context information in the pixel domain.
- Learning to Zoom-In via Learning to Zoom-Out: Real-World Super-Resolution by Generating and Adapting Degradation35
A framework to learn SR from an arbitrary set of unpaired LR and HR images and to see how far a step can go in such a realistic and “unsupervised” setting is proposed.
- Multi-way backpropagation for training compact deep neural networks33
This paper first investigates the supervision vanishing issue in existing backpropagation (BP) methods and proposes to address it via an effective method, called Multi-way BP (MW-BP), which relies on multiple auxiliary losses added to the intermediate layers of the network.
- 32
- Deblurring Natural Image Using Super-Gaussian Fields31
A novel image prior for image deblurring based on a Super-Gaussian field model with adaptive structures is presented, which captures the complicated structures in natural images by integrating potentials on all cliques into a joint probabilistic distribution.
- 29
- 28
- 27
- 26
- 26
- 25
- 23
- Augmented Commonsense Knowledge for Remote Object Grounding23
This work proposes an augmented commonsense knowledge model (ACK), which consists of knowledge graph-aware cross-modal and concept aggregation modules to enhance visual representation and visual-textual data alignment by integrating visible objects, commonsense knowledge, and concept history, which includes object and knowledge temporal information.
- 22
- 22
- 22
- 21
- 21
- What's to Know? Uncertainty as a Guide to Asking Goal-Oriented Questions20
A Bayesian model of the uncertainty in the implicit model maintained by the visual dialogue agent, and in the function used to select an appropriate output, enables a principled method for identifying when enough information has been acquired, and an action should be selected.
- 19
- 19
- 18
- 18
- 18
- 18
- 18
- 17
- 16
- Joint Learning of Set Cardinality and State Distribution16
This work derives in a principled way, a mathematical formulation for set prediction where the output is permutation invariant, and jointly learns both the cardinality and the state distribution of the target set.
- Efficient Orthogonal Non-negative Matrix Factorization over Stiefel Manifold16
A method is proposed, called Nonlinear Riemannian Conjugate Gradient ONMF (NRCG-ONMF), which updates U and V alternatively and preserves the orthogonality of U while achieving fast convergence speed.
- 15
- MPGL: An Efficient Matching Pursuit Method for Generalized LASSO15
This work formulate the GL problem as a convex quadratic constrained linear programming (QCLP) problem and tailor-make a cutting plane method, and proposes an efficient Matching Pursuit Generalized LASSO (MPGL) method, which overcomes issues, and is guaranteed to converge to a global optimum.
- 15
- Scalable maximum margin matrix factorization by active Riemannian subspace search14
This paper forms M3F with a known number of latent factors as the Riemannian optimization problem on a fixed-rank matrix manifold and presents a block-wise nonlinear RiemANNian conjugate gradient method to solve it efficiently.
- 13
- 13
- 13
- 12
- 12
- 12
- 12
- 12
- 12
- 12
- 11
- 11
- 11
- 10
- 9
- An Active Information Seeking Model for Goal-oriented Vision-and-Language Tasks.9
This work proposes an reinforcement-learning approach that maintains an distribution over its internal information, thus explicitly representing the ambiguity in what it knows, and needs to know, towards achieving its goal.
- 8
- 8
- 8
- GADE: A Generative Adversarial Approach to Density Estimation and its Applications8
A generative adversarial density estimator (GADE) is proposed, a density estimation approach that bridges the gap between the two likelihood-free models and a Bayesian model where the predictive variance can be leveraged to measure the confidence in the likelihood.
- 8
- 8
- 8
- 7
- 7
- Gold Seeker: Information Gain From Policy Distributions for Goal-Oriented Vision-and-Langauge Reasoning6
This work proposes a reinforcement-learning approach that maintains a distribution over its internal information, thus explicitly representing the ambiguity in what it knows, and needs to know, towards achieving its goal.
- 6
- 6
- 6
- 6
- 6
- Learning Sparse Confidence-Weighted Classifier on Very High Dimensional Data6
This paper presents an online-batch CW learning scheme, and then presents a novel paradigm to learn sparse CW classifiers, which essentially identifies feature groups and naturally builds a block diagonal covariance structure, making it very suitable for CW learning over very high-dimensional data.
- 6
- 6
- A Simple-but-Effective Baseline for Training-Free Class-Agnostic Counting5
This work suggests employing a superpixel algorithm to generate more precise initial point prompts, utilizing an image encoder with richer semantic knowledge to replace the SAM encoder for representing candidate objects, and adopting a multiscale mechanism and a transductive prototype scheme to update the representation of reference examples.
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- Utilising Prior Knowledge for Visual Navigation: Distil and Adapt4
This paper proposes to decompose the value function in the actor-critic reinforcement learning algorithm and incorporate the prior in the critic in a novel way that reduces the model complexity and improves model generalisation.
- 4
- 4
- 4
- 4
- 3
- A Generative Approach for Comprehensive Financial Event Extraction at the Document Level3
This paper proposes a generative solution for document-level event extraction, which is more challenging due to the presence of scattered arguments and multiple events, and introduces an encoding scheme to capture entity-to-document level information and a decoding scheme that makes the generative process aware of all relevant contexts.
- 3
- 3
- 2
- Categorical Keypoint Positional Embedding for Robust Animal Re-Identification2
This work introduces an innovative keypoint propagation mechanism, which utilizes a single annotated image and a pre-trained diffusion model to propagate keypoints across an entire dataset, significantly reducing the cost of manual annotation.
- 2
- Revisiting Image Reconstruction for Semi-supervised Semantic Segmentation2
This paper revisits the idea of using image reconstruction as the auxiliary task and incorporate it with a modern semi-supervised semantic segmentation framework and shows that using reconstruction as auxiliary loss can lead to consistent improvements in various datasets and methods.
- 2
- 2
- Dilated Convolutional Model for Melody Extraction2
A simple dilated convolutional model that achieves the-state-of-the-art performance on most datasets, for both general and vocal melody extraction, and gets the best performance with the least training data is proposed.
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- UOA at the FinNLP-2022 ERAI Task: Leveraging the Class Label Description for Financial Opinion Mining–
This paper summarizes the solutions to the ERAI shared task, which is co-located with the FinNLP workshop at EMNLP 2022, and proposes a BERT-based pre-trained model projecting opinion pairs in a common space for classification.
- Damage Classification of In-Service Steel Railway Bridges Using a Novel Convolutional Neural Network–
- –
- –
- –
- –
- –
- –
- –
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.