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
- Suggested from co-authorship
- Sethu VijayakumarSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works303 from public data
- Learning to Compare: Relation Network for Few-Shot Learning4,817
A conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each, which is easily extended to zero- shot learning.
- Meta-Learning in Neural Networks: A Survey2,833
A new taxonomy is proposed that provides a more comprehensive breakdown of the space of meta-learning methods today and surveys promising applications and successes ofMeta-learning such as few-shot learning and reinforcement learning.
- Deep Mutual Learning2,054
Surprisingly, it is revealed that no prior powerful teacher network is necessary - mutual learning of a collection of simple student networks works, and moreover outperforms distillation from a more powerful yet static teacher.
- 1,883
- Deeper, Broader and Artier Domain Generalization1,831
This paper builds upon the favorable domain shift-robust properties of deep learning methods, and develops a low-rank parameterized CNN model for end-to-end DG learning that outperforms existing DG alternatives.
- Learning to Generalize: Meta-Learning for Domain Generalization1,813
A novel meta-learning method for domain generalization that trains models with good generalization ability to novel domains and achieves state of the art results on a recent cross-domain image classification benchmark, as well demonstrating its potential on two classic reinforcement learning tasks.
- Learning to Generate Novel Domains for Domain Generalization566
This paper employs a data generator to synthesize data from pseudo-novel domains to augment the source domains, and outperforms current state-of-the-art DG methods on four benchmark datasets.
- Multi-level Factorisation Net for Person Re-identification549
Multi-Level Factorisation Net (MLFN), a novel network architecture that factorises the visual appearance of a person into latent discriminative factors at multiple semantic levels without manual annotation, achieves state-of-the-art results on three Re-ID datasets, as well as compelling results on the general object categorisation CIFAR-100 dataset.
- Transductive Multi-View Zero-Shot Learning513
A novel heterogeneous multi-view hypergraph label propagation method is formulated for zero-shot learning in the transductive embedding space that rectifies the projection shift between the auxiliary and target domains, exploits the complementarity of multiple semantic representations, and significantly outperforms existing methods for both zero- shot and N-shot recognition.
- Deep Domain-Adversarial Image Generation for Domain Generalisation511
This paper proposes a novel DG approach based on Deep Domain-Adversarial Image Generation based on augmenting the source training data with the generated unseen domain data to make the label classifier more robust to unknown domain changes.
- Episodic Training for Domain Generalization504
Using the Visual Decathlon benchmark, it is demonstrated that the episodic-DG training improves the performance of such a general purpose feature extractor by explicitly training a feature for robustness to novel problems, showing that DG training can benefit standard practice in computer vision.
- 488
- Self-Supervised Representation Learning: Introduction, advances, and challenges442
This article introduces this vibrant area, including key concepts, the four main families of approaches and associated state-of-the-art techniques, and how self-supervised methods are applied to diverse modalities of data.
- Sketch-a-Net: A Deep Neural Network that Beats Humans345
It is shown that state-of-the-art deep networks specifically engineered for photos of natural objects fail to perform well on sketch recognition, regardless whether they are trained using photos or sketches.
- When Face Recognition Meets with Deep Learning: An Evaluation of Convolutional Neural Networks for Face Recognition334
An extensive evaluation of CNN-based face recognition systems (CNN-FRS) and proposes three CNN architectures which are the first reported architectures trained using LFW data to make the work easily reproducible.
- Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference279
It is shown that a simple transformer-based pipeline yields surprisingly good performance on standard benchmarks such as Mini-ImageNet, CIFAR-FS, CDFSL and Meta-Dataset.
- Incremental Few-Shot Object Detection269
OpeN-ended Centre nEt (ONCE), a detector designed for incrementally learning to detect novel class objects with few examples, is proposed by an elegant adaptation of the efficient CentreNet detector to the few-shot learning scenario, and meta-learning a class-wise code generator model for registering novel classes.
- 269
- 261
- 259
- 252
- Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation251
This paper proposes a novel framework, transductive multi-view embedding, that rectifies the projection shift between the auxiliary and target domains, exploits the complementarity of multiple semantic representations, achieves state-of-the-art recognition results on image and video benchmark datasets, and enables novel cross-view annotation tasks.
- Sketch-a-Net that Beats Humans246
A multi-scale multi-channel deep neural network framework that yields sketch recognition performance surpassing that of humans, and not only delivers the best performance on the largest human sketch dataset to date, but also is small in size making efficient training possible using just CPUs.
- Hypernetwork Knowledge Graph Embeddings220
It is demonstrated that convolution simply offers a convenient computational means of introducing sparsity and parameter tying to find an effective trade-off between non-linear expressiveness and the number of parameters to learn.
- Transferring a semantic representation for person re-identification and search214
This paper presents a new semantic attribute learning approach for person re-identification and search that is trained on existing fashion photography datasets and adapted to provide a powerful semantic description of surveillance person detections, without requiring any surveillance domain supervision.
- Transductive Zero-Shot Action Recognition by Word-Vector Embedding176
This study constructs a mapping between visual features and a semantic descriptor of each action category, allowing new categories to be recognised in the absence of any visual training data, and achieves the state-of-the-art zero-shot action recognition performance with a simple and efficient pipeline, and without supervised annotation of attributes.
- Deep Learning for Free-Hand Sketch: A Survey and A Toolbox160
A comprehensive survey of the deep learning techniques oriented at free-hand sketch data, and the applications that they enable.
- Self-Supervised Multimodal Learning: A Survey158
This survey provides a comprehensive review of the state-of-the-art in SSML, and elucidate three major challenges intrinsic to self-supervised learning with multimodal data: 1) learning representations from multimodal data without labels, 2) fusion of different modalities, and 3) learning with unaligned data.
- 157
- 139
- Learning to Sketch with Shortcut Cycle Consistency137
A novel approach for translating an object photo to a sketch, mimicking the human sketching process, and shows that the synthetic sketches can be used to train a better fine-grained sketch-based image retrieval model, effectively alleviating the problem of sketch data scarcity.
- Frankenstein: Learning Deep Face Representations Using Small Data137
This paper proposes a method to generate very large training data sets of synthetic images by compositing real face images in a given data set and shows that this method enables to learn models from as few as 10 000 training images, which perform on par with models trained from 500 000 images.
- A survey on heterogeneous face recognition: Sketch, infra-red, 3D and low-resolution133
This survey provides a comprehensive review of established techniques and recent developments in HFR, and offers a detailed account of datasets and benchmarks commonly used for evaluation.
- DemoFusion: Democratising High-Resolution Image Generation With No $$$131
This paper aims to democratise high-resolution GenAl by advancing the frontier of high-resolution generation while remaining accessible to a broad audience, and demonstrates that existing Latent Diffusion Models (LDMs) possess untapped potential for higher-resolution image generation.
- Sketch Less for More: On-the-Fly Fine-Grained Sketch-Based Image Retrieval131
A reinforcement learning based cross-modal retrieval framework that directly optimizes rank of the ground-truth photo over a complete sketch drawing episode and introduces a novel reward scheme that circumvents the problems related to irrelevant sketch strokes, and thus provides us with a more consistent rank list during the retrieval.
- SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval130
This work proposes a deep hashing framework for sketch retrieval that, for the first time, works on a multi-million scale human sketch dataset and shows that state-of-the-art hashing models specifically engineered for static images fail to perform well on temporal sketch data.
- Differentiable Automatic Data Augmentation120
Differentiable Automatic Data Augmentation is proposed which dramatically reduces the cost, relaxes the discrete DA policy selection to a differentiable optimization problem via Gumbel-Softmax, and introduces an unbiased gradient estimator, RELAX, leading to an efficient and effective one-pass optimization strategy to learn an efficient and accurate DA policy.
- Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation120
A visual-semantic mapping with better generalisation properties and a dynamic data re-weighting method to prioritise auxiliary data that are relevant to the target classes are introduced and applied to the challenging zero-shot action recognition problem.
- Semantic embedding space for zero-shot action recognition120
This paper addresses zero-shot recognition in contemporary video action recognition tasks, using semantic word vector space as the common space to embed videos and category labels, and demonstrates that a simple self-training and data augmentation strategy can significantly improve the efficacy of this mapping.
- Attribute Learning for Understanding Unstructured Social Activity118
This paper contributes an unstructured social activity attribute (USAA) dataset, introduces the concept of semi-latent attribute space, and proposes a novel model for learning the latent attributes which alleviate the dependence of existing models on exact and exhaustive manual specification of the attribute-space.
- Attributes-Based Re-identification116
This chapter shows how mid-level “semantic attributes” can be computed for person description and shows how this attribute-based description can be used in synergy with low-level feature descriptions to improve re-identification accuracy when an attribute-centric distance measure is employed.
- Video Behaviour Mining Using a Dynamic Topic Model116
The MCTM builds on existing dynamic Bayesian network models and Bayesian topic models, and overcomes their drawbacks on sensitivity, robustness and efficiency, and profiles complex dynamic scenes by robustly clustering visual events into activities and these activities into global behaviours with temporal dynamics.
- Online Meta-learning for Multi-source and Semi-supervised Domain Adaptation113
This paper proposes an online shortest-path meta-learning framework that is both computationally tractable and practically effective for improving DA performance and presents variants for both multi-source unsupervised domain adaptation (MSDA), and semi-superviseddomain adaptation (SSDA).
- Semantic Regularisation for Recurrent Image Annotation111
This work proposes to use a semantically regularised embedding layer as the interface between the CNN and RNN, allowing each to be more effectively trained and jointly training much more efficient.
- 110
- The Re-identification Challenge110
This chapter presents an overview of recent progress and the state-of-the-art approaches to solving some of the fundamental challenges in person re-identification, benefiting from research in computer vision, pattern recognition and machine learning, and drawing insights from video analytics system design considerations for engineering practical solutions.
- Learning Deep Sketch Abstraction109
This work proposes the first stroke-level sketch abstraction model based on the insight of sketch abstraction as a process of trading off between the recognizability of a sketch and the number of strokes used to draw it and shows that the model can be used for various sketch analysis tasks.
- Towards Person Identification and Re-identification with Attributes108
This work shows how mid-level semantic attributes can be used synergistically with low-level features for both identification and re-identification, and learns an attribute-centric representation to describe people, and a metric for comparing attribute profiles to disambiguate individuals.
- Free-hand sketch recognition by multi-kernel feature learning103
This work proposes a Multiple Kernel Learning (MKL) framework for sketch recognition, fusing several features common to sketches, and investigates the use of attributes as a high-level feature for sketches and shows how this complements low-level features for improving recognition performance under the MKL framework.
- 100
- 100
- 99
- 96
- 95
- 93
- Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition92
MetaQDA is introduced, a Bayesian meta-learning generalisation of the classic quadratic discriminant analysis that leads to excellent performance in cross-domain few-shot learning, class-incremental few- shot learning, and crucially for real-world applications, the Bayesian formulation leads to state-of-the-art uncertainty calibration in predictions.
- 92
- Interestingness Prediction by Robust Learning to Rank91
A more principled way to identify annotation outliers is proposed by formulating theinterestingness prediction task as a unified robust learning to rank problem, tackling both the outlier detection and interestingness prediction tasks jointly.
- Factorized Higher-Order CNNs With an Application to Spatio-Temporal Emotion Estimation89
This paper proposes a tensor factorization framework for efficient multidimensional (separable) convolutions of higher-order, coined CP-Higher-Order Convolution (HO-CPConv), and applies the proposed methodology to spatio-temporal facial emotion analysis.
- Neural-Symbolic Integration: A Compositional Perspective88
It is shown that a symbolic module --- with any choice for syntax and semantics, as long as the deduction and abduction methods are exposed --- can be cleanly integrated with a neural module, and facilitate the latter's efficient training, achieving empirical performance that exceeds that of previous work.
- 88
- 87
- 86
- 86
- Open-Ended Learning: A Conceptual Framework Based on Representational Redescription85
This paper describes open-ended learning as the challenge of building the adequate representation of states and actions, i.e., of redescribing available representations, and suggests an iterative approach to this problem based on several successive Representational Redescription processes.
- BézierSketch: A Generative Model for Scalable Vector Sketches77
This paper introduces a novel inverse graphics approach to stroke embedding that trains an encoder to embed each stroke to its best fit Bezier curve, which enables to treat sketches as short sequences of paramaterized strokes and thus train a recurrent sketch generator with greater capacity for longer sketches, while producing scalable high-resolution results.
- Cross-domain Generative Learning for Fine-Grained Sketch-Based Image Retrieval77
A novel discriminative-generative hybrid model is proposed by introducing a generative task of cross-domain image synthesis that enforces the learned embedding space to preserve all the domain invariant information that is useful for cross-domain reconstruction, thus explicitly reducing the domain gap as opposed to existing models.
- 73
- Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting69
This paper proposes two novel cross-modal translation pre-text tasks for self-supervised feature learning: Vectorization and Rasterization and shows that the learned encoder modules benefit both raster-based and vector-based downstream approaches to analysing hand-drawn data.
- 69
- Bayesian Joint Topic Modelling for Weakly Supervised Object Localisation69
All object classes and image backgrounds are modelled jointly together in a single generative model so that "explaining away" inference can resolve ambiguity and lead to better learning and localisation.
- 67
- Fine-Grained Image Retrieval: the Text/Sketch Input Dilemma65
This work introduces a multi-modal FGIR dataset with both sketches and sentences description provided as query modalities and shows that on its own the sketch modality is much more informative than text and each modality can benefit the other when they are modelled jointly.
- Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style64
The all important explainable goal is elegantly achieved by visualizing cross-modal token correspondences, and for the first time, via sketch to photo synthesis by universal replacement of all matched photo patches.
- Fine-grained sketch-based image retrieval by matching deformable part models63
This document is distributed unchanged freely in print or electronic forms because the authors believe it to be of high quality and fit for purpose of publication.
- 62
- Disjoint Label Space Transfer Learning with Common Factorised Space59
A unified approach is presented to transfer learning that addresses several source and target domain label-space and annotation assumptions with a single model that outperforms alternatives in both unsupervised and semi-supervised settings.
- Cross-Modal Face Matching: Beyond Viewed Sketches58
This paper investigates sketch-photo face matching and goes beyond the well-studied viewed sketches to tackle forensic sketches and caricatures where representations are often symbolic, and learns a facial attribute model independently in each domain that represents faces in terms of semantic properties.
- Free-Hand Sketch Synthesis with Deformable Stroke Models57
A generative model which can automatically summarize the stroke composition of free-hand sketches of a given category is presented, which represents both consistent as well as diverse aspects of each sketch category.
- Fine-Grained Instance-Level Sketch-Based Image Retrieval56
A new large-scale FG-SBIR database is introduced which is carefully designed to reflect the real-world application scenarios and a deep cross-domain matching model is formulated to solve the intrinsic drawing style variability, large domain gap issues, and capture instance-level discriminative features.
- Deep Neural Networks for Sketch Recognition.56
This work outlines a sketch image retrieval system in a unified neural network framework that is the first deep neural network model for sketch classification, and it has outperformed state-of-the-art results in the TU-Berlin sketch benchmark.
- 55
- Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels55
A more principled way to identify annotation outliers is proposed by formulating the subjective visual property prediction task as a unified robust learning toRank problem, tackling both the outlier detection and learning to rank jointly.
- iVQA: Inverse Visual Question Answering54
This work poses question generation as a multi-modal dynamic inference process and proposes an iVQA model that can gradually adjust its focus of attention guided by both a partially generated question and the answer.
- 54
- 53
- Universal Sketch Perceptual Grouping53
A universal sketch grouper that can be applied to sketches of any category in any domain to group constituent strokes/segments into semantically meaningful object parts is developed and significantly outperforms the state-of-the-art groupers.
- Weakly-Supervised Image Annotation and Segmentation with Objects and Attributes50
This work proposes a novel Weakly Supervised Markov Random Field Stacked Indian Buffet Process (WS-MRF-SIBP) that models objects and attributes as latent factors and explicitly captures their correlations within and across superpixels.
- Deep Multi-task Learning to Recognise Subtle Facial Expressions of Mental States47
This work addresses subtle expression recognition through convolutional neural networks (CNNs) by developing multi-task learning (MTL) methods to effectively leverage a side task: facial landmark detection and achieves very competitive performance on Oulu-Casia NIR&Vis and CK+ databases via transfer learning.
- Deep Multi-task Attribute-driven Ranking for Fine-grained Sketch-based Image Retrieval46
A fine-grained SBIR model that exploits semantic attributes and deep feature learning in a complementary way is proposed, and the introduction of semantic attribute learning in the model allows for the elimination of the otherwise prohibitive cost of human annotations required for training a fine- grained deep ranking model.
- 45
- Gated Neural Networks for Option Pricing: Rationality by Design44
A class of gated neural networks that automatically learn to divide-and-conquer the problem space for robust and accurate pricing and derive instantiations of these networks that are 'rational by design' in terms of naturally encoding a valid call option surface that enforces no arbitrage principles are introduced.
- Investigating Open-World Person Re-identification Using a Drone44
This paper introduces the first dataset for mobile re-identification, and uses this to elucidate the unique challenges of mobile re,id models and suggest future avenues for research in this area.
- Gaussian Visual-Linguistic Embedding for Zero-Shot Recognition43
A visual-linguistic mapping for ZSL in the case where words and visual categories are both represented by distributions is presented, which shows improved results on ZSL benchmarks due to this better exploiting of intra-concept variability in each modality.
- Pixelor41
The first competitive drawing agent Pixelor is presented that exhibits humanlevel performance at a Pictionary-like sketching game, and is better than the human players of the Quick, Draw! game, under both AI and human judging of early recognition.
- Deep Ranking for Image Zero-Shot Multi-Label Classification40
This work investigates and formalizes a flexible framework consisting of two components, i.e., visual-semantic embedding and zero-shot multi-label prediction, and presents a deep regression model to project the visual features into the semantic space, which explicitly exploits the correlations in the intermediate semantic layer of word vectors and makes label prediction possible.
- Fine-Grained Instance-Level Sketch-Based Video Retrieval40
This work proposes a novel cross-modal retrieval problem of fine-grained instance-level sketch-based video retrieval (FG-SBVR), where a sketch sequence is used as a query to retrieve a specific target video instance.
- Cloud2Curve: Generation and Vectorization of Parametric Sketches39
Cloud2Curve is presented, a generative model for scalable high-resolution vector sketches that can be trained end-to-end using point-cloud data alone and is capable of deterministic vectorization which can map novel raster or waypoint based sketches to their corresponding high- resolution scalable Bézier equivalent.
- Towards Bottom-Up Analysis of Social Food39
This paper performs the first large scale content analysis of Instagram posts, addressing both the image and the associated hashtags, aiming to understand the content of partially-labelled images taken in-the-wild and the relationship with hashtags that individuals use as noisy labels.
- 39
- An Erudite Fine-Grained Visual Classification Model38
This paper proposes an erudite FGVC model jointly trained by several different datasets to reduce negative transfer and boost positive transfer between different datasets, and proposes a meta-learning based dataset-agnostic spatial attention layer to take full advantage of the multi-dataset training data.
- 38
- Multisensory Oddity Detection as Bayesian Inference38
The successful application of structure inference models to the new ‘oddity detection’ paradigm, and the resultant unified explanation of across and within modality cases provide further evidence to suggest that structure inference may be a commonly evolved principle for combining perceptual information in the brain.
- 37
- 36
- When and where to transfer for Bayesian network parameter learning36
This paper introduces the Bayesian network parameter transfer learning (BNPTL) algorithm to reason about both network and fragment (sub-graph) relatedness and demonstrates the superiority of BNPTL at various scarcities and source relevance levels compared to single task learning and other state-of-the-art parameter transfer methods.
- Uncertainty-Aware Source-Free Domain Adaptive Semantic Segmentation35
This paper proposes to use Bayesian Neural Network (BNN) to improve the target self- training by better estimating and exploiting pseudo-label uncertainty and introduces two novel self-training based components: Uncertainty-aware Online Teacher-Student Learning (UOTSL) and Uncertainly-aware FeatureMix (UFM).
- Learning Unsupervised Word Translations Without Adversaries35
This work presents a statistical dependency-based approach to bilingual dictionary induction that is unsupervised – no seed dictionary or parallel corpora required; and introduces no adversary – therefore being much easier to train.
- 34
- 32
- Inverse Visual Question Answering: A New Benchmark and VQA Diagnosis Tool31
This paper proposes a variational iVQA model that can generate diverse, grammatically correct and content correlated questions that match the given answer, and shows that iVZA is an interesting benchmark for visuo-linguistic understanding, and a more challenging alternative to VQA because an iV QA model needs to understand the image better to be successful.
- Bayesian Joint Modelling for Object Localisation in Weakly Labelled Images31
A novel framework based on Bayesian joint topic modelling is proposed, which differs significantly from the existing ones in that all foreground object classes are modelled jointly in a single generative model that encodes multiple object co-existence so that “explaining away” inference can resolve ambiguity and lead to better learning and localisation.
- 30
- Sketch-a-Classifier: Sketch-Based Photo Classifier Generation30
This paper investigates an alternative approach of synthesizing image classifiers: almost directly from a user's imagination, via freehand sketch, which can also be used to enhance the granularity of an existing photo classifier, or as a complement to name-based zero-shot learning.
- 30
- 28
- 27
- 25
- Goal-Driven Sequential Data Abstraction25
This paper studies a general reinforcement learning based framework for learning to abstract sequential data in a goal-driven way and processes the input sequence holistically without being constrained by the original input order.
- 25
- 25
- 23
- 23
- 23
- 23
- 22
- 22
- A Unifying Theory of Active Discovery and Learning21
This study shows with systematic theoretical analysis how the previously disparate tasks of active discovery and learning can be cleanly unified into a single problem, and is able for the first time to develop a unified query algorithm to directly optimise this problem.
- Finding Rare Classes: Adapting Generative and Discriminative Models in Active Learning21
A unified active learning model to jointly discover new categories and learn to classify them; and a classifier combination algorithm that switches generative and discriminative classifiers as learning progresses that demonstrates the superiority of this approach over existing methods.
- 20
- ChiroDiff: Modelling chirographic data with Diffusion Models19
A powerful model-class namely Denoising Diffusion Probabilistic Models or DDPMs for chirographic data that learns to capture holistic concepts and therefore remains resilient to higher temporal sampling rate up to a good extent and it is shown that many important downstream utilities can be flexibly implemented using ChiroDiff.
- Sketch-a-Segmenter: Sketch-Based Photo Segmenter Generation19
It is shown, for the first time, that it is possible to generate a photo-segmentation model of a novel category using just a single sketch and furthermore exploit the unique fine-grained characteristics of sketch to produce more detailed segmentation.
- 19
- 19
- Deep Factorised Inverse-Sketching19
A novel unsupervised image style transfer model based on enforcing a cyclic embedding consistency constraint is proposed and evaluated both qualitatively and quantitatively to demonstrate its superiority over a number of state-of-the-art alternatives for style transfer and FG-SBIR.
- SketchINR: A First Look into Sketches as Implicit Neural Representations18
SketchINR emulates the human ability to reproduce a sketch with varying abstraction in terms of number and complexity of strokes, and its compact high-fidelity representation will support future work in modelling long and complex sketches.
- 18
- 18
- Learning Rare Behaviours18
A novel topic model is proposed: Multi-Class Delta Latent Dirichlet Allocation which learns to model rare behaviours from a few weakly labelled videos as well as typical behaviours from uninteresting videos by collaboratively sharing features among all classes of footage.
- 17
- 17
- 17
- 17
- Weakly Supervised Learning of Objects, Attributes and Their Associations17
This paper models object-attribute associations from weakly labelled images, such as those widely available on media sharing sites (e.g. Flickr), where only image-level labels are given, without their locations and associations.
- 16
- 16
- 15
- 15
- 15
- 15
- Accelerating Self-Supervised Learning via Efficient Training Strategies14
This paper investigates reducing the training time of recent self-supervised methods by various model-agnostic strategies that have not been used for this problem, and studies three strategies: an extendable cyclic learning rate schedule, a matching progressive augmentation magnitude and image resolutions schedule, and a hard positive mining strategy based on augmentation difficulty.
- 14
- 14
- 14
- 13
- 13
- 12
- 12
- 12
- 11
- 11
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- A Unified Bayesian Framework for Adaptive Visual Tracking6
A unified generative model for multi-sensory adaptive tracking which cleanly integrates tracking and the modeling of appearance change across multiple features in the same framework is derived.
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- The Reward Model Selection Crisis in Personalized Alignment3
The findings reveal that the field has been optimizing for proxy metrics that do not predict deployment performance, and that current personalized alignment methods fail to operationalize preferences into behavioral adaptation under realistic deployment constraints, and finds simple in-context learning (ICL) to be highly effective.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- Deep Multi-View Learning with Stochastic Decorrelation Loss.3
A mini-batch based Stochastic Decorrelation Loss (SDL) is proposed which can be applied to any network layer to provide soft decorrelation of the layer's activations and is superior to other decorrelation losses in terms of efficacy and scalability.
- 3
- L1 Graph Based Sparse Model for Label De-noising3
This work proposes a novel robust graph-based approach for label de-noising, built upon a visual similarity graph in a form of L 1 graph regulariser, which is more robust against visual outliers than the conventional L 2 regulariser.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- Sketch-based Video Object Segmentation: Benchmark and Analysis1
Experimental results show sketch is more effective yet annotation-efficient than other references, such as photo masks, language and scribble, and what the most effective design for incorporating a sketch reference is.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 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.