Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks234 from public data
- 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.
- 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
- The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification401
Experimental results show the superiority of the MC-Loss when implemented on top of common base networks can achieve state-of-the-art performance on all four fine-grained categorization datasets, and ablative studies further demonstrate the supremacy of the loss when compared with other recently proposed general-purpose losses for visual classification.
- Fine-Grained Visual Classification via Progressive Multi-granularity Training of Jigsaw Patches389
This work proposes a novel framework for fine-grained visual classification with a progressive training strategy that effectively fuses features from different granularities, and a random jigsaw patch generator that encourages the network to learn features at specificgranularities.
- 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.
- 261
- 252
- 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.
- Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer243
This work proposes to simplify the meta-learning task by focusing solely on the simplest component – the classifier, whilst leaving the en-coder and decoder to pre-training, and introduces a Classifier Weight Transformer (CWT) designed to dynamically adapt the support-set trained classifier’s weights to each query image in an inductive way.
- Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval217
This paper proposes a novel ZS-SBIR framework to jointly model sketches and photos into a common embedding space, and forms a novel strategy to mine the mutual information among domains is specifically engineered to alleviate the domain gap.
- 214
- Stochastic Classifiers for Unsupervised Domain Adaptation179
This paper introduces a novel method called STochastic clAssifieRs (STAR) for addressing the problem of misaligned local regions between source and target domain, which finds that using more classifiers leads to better performance, but also introduces more model parameters, therefore risking overfitting.
- Text extraction from natural scene image: A survey175
This paper offers the researchers a link to public image database for the algorithm assessment of text extraction from natural scene images and draws attention to studies on the first two steps in the extraction process, since OCR is a well-studied area where powerful algorithms already exist.
- Style-Based Global Appearance Flow for Virtual Try-On174
A novel global appearance flow estimation model is proposed in this work which enables the use of a global style vector to encode a whole-image context to cope with the aforementioned challenges.
- CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not163
The proposed CLIP and prompt learning paradigm carries great promise in tackling other sketch-related tasks (not limited to ZS-SBIR) where data scarcity remains a great challenge.
- 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.
- Your “Flamingo” is My “Bird”: Fine-Grained, or Not155
The key intuition that: coarse- level label prediction exacerbates fine-grained feature learning, yet fine-level feature betters the learning of coarse-level classifier is discovered, which enables the design of a very simple albeit surprisingly effective solution to a new problem.
- 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.
- 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.
- 130
- 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.
- A survey on heterogeneous face recognition: Sketch, infra-red, 3D and low-resolutionReview Article120
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.
- 117
- StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval111
This model can not only disentangle the cross-modal shared semantic content for SBIR, but can adapt the disentanglement to any unseen user style as well, making the SBIr model truly style-agnostic.
- 110
- 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.
- 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.
- 95
- SketchyScene: Richly-Annotated Scene Sketches93
The potential impact of SketchyScene is demonstrated by training new computational models for semantic segmentation of scene sketches and showing how the new dataset enables several applications including image retrieval, sketch colorization, editing, and captioning, etc.
- 92
- Cross-modal subspace learning for fine-grained sketch-based image retrieval90
Through thorough examination of the experimental results, it is demonstrated that the subspace learning can effectively model the sketch-photo domain-gap, and a few key insights to drive future research are drawn.
- FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks86
This work proposes a novel FAshion-focused Multi-task Efficient learning method for Vision-and-Language tasks (FAME-ViL), which applies a single model for multiple heterogeneous fashion tasks, therefore being much more parameter-efficient.
- Hybrid Graph Neural Networks for Few-Shot Learning78
A novel hybrid GNN (HGNN) model consisting of two GNNs, an instance GNN and a prototype GNN designed to deal with a fundamental yet often neglected challenge in FSL, that is, with only a handful of shots per class, any few-shot classifier would be sensitive to badly sampled shots.
- Sketch Recognition by Ensemble Matching of Structured Features78
This work presents a method for the representation and matching of sketches by exploiting not only local features but also global structures of sketches, through a star graph based ensemble matching strategy, and shows that by encapsulating holistic structure matching and learned bag-of-features models into a single framework, notable recognition performance improvement can be observed.
- 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 Adversarial Feature Learning for Sketch Re-identification77
This paper addresses the Sketch Re-ID problem by proposing a cross-domain adversarial feature learning approach to jointly learn the identity features and domain-invariant features and shows that the proposed method outperforms the state-of-the-arts.
- 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.
- Picture that Sketch: Photorealistic Image Generation from Abstract Sketches74
This paper turns an abstract, deformed, ordinary sketch from untrained amateurs like you and me into a photorealistic image, and proposes an autoregressive sketch mapper trained on sketch-photo pairs that maps a sketch to the StyleGAN latent space.
- A Tree-Structured Decoder for Image-to-Markup Generation74
Key to the success of the proposed tree decoder is twofold, it strictly respects the parent-child relationship of trees, and it explicitly outputs trees as oppose to a linear string.
- Sketch3T: Test-Time Training for Zero-Shot SBIR73
This paper extends ZS-SBIR to include a test-time training paradigm that can adapt using just one sketch, and designs a novel meta-learning based training paradigm to learn a separation between model updates incurred by this auxiliary task from those off the primary objective of discriminative learning.
- 73
- 71
- More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval71
This paper introduces a novel semi-supervised framework for cross-modal retrieval that can additionally leverage large-scale unlabelled photos to account for data scarcity, and treats generation and retrieval as two conjugate problems, where a joint learning procedure is devised for each module to mutually benefit from each other.
- Modeling and generating moving trees from video70
This work presents a probabilistic approach for the automatic production of tree models with convincing 3D appearance and motion, and provides a generative model that creates multiple trees in 3D, given a single example model.
- 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.
- Virtual visual sensors and their application in structural health monitoring69
Use of a sub-pixel accuracy marker extraction algorithm to construct virtual sensors in the spatial domain, embedding dynamic marker linking within a tracking-by-correspondence paradigm that offers benefits in computational efficiency and registration accuracy over traditional tracking- by-searching systems and validation of virtual visual sensor in the context of a structural health monitoring application are presented.
- 67
- Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning65
The TAGS model differs significantly from the conventional proposal-based methods by focusing on global temporal representation learning to directly detect local start and end points of action instances without proposals, and needs a much simpler model architecture with lower computational cost.
- 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.
- Context-Aware Layout to Image Generation with Enhanced Object Appearance64
A context-aware feature transformation module is introduced in the generator to ensure that the generated feature encoding of either object or stuff is aware of other coexisting objects/stuff in the scene.
- 63
- Cross-Modal Hierarchical Modelling for Fine-Grained Sketch Based Image Retrieval62
A novel network is designed that is capable of cultivating sketch-specific hierarchies and exploiting them to match sketch with photo at corresponding hierarchical levels, and enriched using cross-modal co-attention and hierarchical node fusion at every level to form a better embedding space to conduct retrieval.
- 61
- Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition61
It is argued that semantic information offers a complementary role in addition to visual only by proposing a multi-stage multi-scale attentional decoder that performs joint visual-semantic reasoning in a stage-wise manner.
- Semi-Heterogeneous Three-Way Joint Embedding Network for Sketch-Based Image Retrieval61
A novel semi-heterogeneous three-way joint embedding network (Semi3-Net) is proposed, which integrates three branches (a sketch branch, a natural image branch, and an edgemap branch) to learn more discriminative cross-domain feature representations for the SBIR task.
- Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval59
This paper proposes an auxiliary module for existing retrieval models that predominantly lets the users sketch without having to worry, and designs a stroke subset selector that detects noisy strokes, leaving only those which make a positive contribution towards successful retrieval.
- 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.
- AI + Art = Human54
This work draws from philosophy of art and science arguing that AI as a technical object is always intertwined with human nature despite its level of autonomy, and the use of creative autonomous agents has cultural and social implications in the way the authors experience art as creators as well as audience.
- Dynamic Instance Domain Adaptation53
A dynamic neural network with adaptive convolutional kernels is developed to generate instance-adaptive residuals to adapt domain-agnostic deep features to each individual instance in a dynamic instance domain adaptation (DIDA).
- 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.
- Deep Self-Supervised Representation Learning for Free-Hand Sketch52
This paper proposes a set of pretext tasks specifically designed for sketches that mimic different drawing styles, and exploits the use of the textual convolution network together with the convolutional neural network in a dual-branch architecture for sketch feature learning, as means to accommodate the sequential stroke nature of sketches.
- It's All About Your Sketch: Democratising Sketch Control in Diffusion Models50
This paper unravels the potential of sketches for diffusion models, addressing the deceptive promise of direct sketch control in generative AI, and introduces an abstraction-aware framework, using a sketch adapter, adaptive time-step sampling, and discriminative guidance from a pre-trained fine-grained sketch-based image retrieval model, working synergistically to reinforce fine-grained sketch-photo association.
- 47
- Finding Semantic Structures in Image Hierarchies Using Laplacian Graph Energy47
This paper shows Laplacian graph energy is a generic measure that can be used to identify semantic structures within hierarchies, independently of the algorithm that produces them.
- What Can Human Sketches Do for Object Detection?46
A sketch-enabled object detection framework that detects based on what you sketch, and outperforms both supervised (SOD) and weakly-supervised object detectors (WSOD) on zero-shot setups.
- 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
- 44
- 44
- MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition44
This paper proposes to meta-learn instance specific weights for a character-wise cross-entropy loss, which is specifically designed to work with the sequential nature of text data, and proposes a writer-adaptive MetaHTR framework which can be easily implemented on the top of most state-of-the-art HTR models.
- Arty Shapes43
This paper shows that shape simplification is a tool useful in Non-Photorealistic rendering from photographs, because it permits a level of abstraction otherwise unreachable.
- Sequential Learning for Domain Generalization42
This paper proposes a sequential learning framework for Domain Generalization (DG), the problem of training a model that is robust to domain shift by design, and shows that for MLDG it leads to a simple to implement and fast algorithm that provides consistent performance improvement on a variety of DG benchmarks.
- 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.
- SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text40
This paper extends scene understanding to include that of human sketch and creates a complete trilogy of scene representation from three diverse and complementary modalities – sketch, photo, and text by learning a flexible joint embedding that fully supports the “optionality” that this complementarity brings.
- 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.
- 39
- 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.
- 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
- DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion37
A new formulation of temporal action detection with denoising diffusion with denoising diffusion, DiffTAD, which can yield action proposals accurately given an untrimmed long video, presents a generative modeling perspective, against previous discriminative learning manners.
- SketchHealer: A Graph-to-Sequence Network for Recreating Partial Human Sketches36
Both qualitative and quantitative results show that the proposed model significantly outperforms state-of-the-art alternatives.
- 36
- 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).
- Prediction Calibration for Generalized Few-Shot Semantic Segmentation35
To make the proposed cross-attention module training tractable at the pixel level, this module is designed based on feature-score cross-covariance and episodically trained to be generalizable at inference time.
- Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation35
This paper aims for a single model that can compete favourably with two separate state-of-the-art STR and HTR models, and proposes four distillation losses, all of which are specifically designed to cope with the aforementioned unique characteristics of text recognition.
- How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval?34
This paper proposes a novel abstraction-aware sketch-based image retrieval framework capable of handling sketch abstraction at varied levels, and proposes feature-level and retrieval granularity-level designs so that the system builds into its DNA the necessary means to interpret abstraction.
- Semantic Embedding for Sketch-Based 3D Shape Retrieval.34
This work argues that the large domain gap cannot be effectively bridged in a shared feature space and proposes a novel deep cross-domain semantic embedding model that drastically improves over the state-of-the-art alternatives.
- Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches33
This paper addresses two key questions that bottleneck its ubiquitous application of FSCIL: can the model learn from diverse modalities other than just photo, and what if photos are not readily accessible (due to ethical and privacy constraints).
- Disentangled Lifespan Face Synthesis33
A novel LFS model is proposed to disentangle the key face characteristics including shape, texture and identity so that the unique shape and texture age transformations can be modeled effectively.
- 33
- Doodle Your 3D: from Abstract Freehand Sketches to Precise 3D Shapes32
This paper introduces a novel part-level modelling and alignment framework that facilitates abstraction modelling and cross-modal correspondence that seamlessly extends to sketch modelling by establishing correspondence between CLIPasso edgemaps and projected 3D part regions.
- Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR32
This paper advances the fine-grained sketch-based image retrieval (FG-SBIR) literature by putting forward a strong baseline that overshoots prior state-of-the-arts by ≈11 % and proposes a simple modification to the standard triplet loss, that explicitly enforces separation amongst photos/sketch instances.
- SketchLattice: Latticed Representation for Sketch Manipulation32
This paper proposes a lattice structured sketch representation that not only removes the bottleneck of requiring vector data but also preserves the structural cues that vector data provides, and shows that the lattice structure is particularly amenable to structural changes that largely benefits sketch abstraction modeling for generation tasks.
- Partially Does It: Towards Scene-Level FG-SBIR with Partial Input31
This work advocates for a simple set-based approach using optimal transport (OT) to model cross-modal region associativity in a partially-aware fashion and improves upon OT to further account for holistic partialness by comparing intra- modal adjacency matrices.
- Adaptive Fine-Grained Sketch-Based Image Retrieval31
This paper introduces a novel model-agnostic meta-learning (MAML) based framework with several key modifications, and proposes a novel perspective -- instead of asking for a model that generalises, it advocates for one that quickly adapts, with just very few samples during testing (in a few-shot manner).
- You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval30
A novel compositionality framework is introduced, effectively combining sketches and text using pre-trained CLIP models, while eliminating the need for extensive fine-grained textual descriptions, providing solutions for various real-world scenarios.
- 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.
- Im2Sketch: Sketch generation by unconflicted perceptual grouping30
This paper studies how multiple Gestalt rules can be encapsulated into a unified perceptual grouping framework for sketch generation and shows that by solving the problem of Gestalt confliction, more similar to human-made sketches can be generated.
- 29
- 29
- 29
- Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers27
This paper introduces a straightforward yet powerful strategy focused on two key aspects: selecting optimal feature layers and utilising visual and textual prompts to guide the model's feature extraction process, enabling it to generate more discriminative and contextually relevant cross-modal representations.
- On-the-Fly Category Discovery27
This paper designs a hash coding-based expandable recognition model and proposes a novel Sign-Magnitude dIsentangLEment (SMILE) architecture to alleviate the disturbance it brings, and experimental results demonstrate the superiority of SMILE against the baseline model and prior art.
- Sketch2Saliency: Learning to Detect Salient Objects from Human Drawings27
A photo-to-sketch generation model that aims to generate sequential sketch coordinates corresponding to a given visual photo through a 2D attention mechanism to study how sketches can be used as a weak label to detect salient objects present in an image.
- Instance-Level Coupled Subspace Learning for Fine-Grained Sketch-Based Image Retrieval27
This paper forms a cross-domain framework specifically designed for the task of FG-SBIR that simultaneously conducts instance-level retrieval and attribute prediction and proposes a joint view selection and attribute subspace learning algorithm to learn domain projection matrices for photo and sketch, respectively.
- 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
- Data-Free Sketch-Based Image Retrieval24
This work proposes Data-Free (DF)-SBIR, where, unlike existing DFL problems, pre-trained, single-modality classification models have to be leveraged to learn a cross-modal metric-space for retrieval without access to any training data.
- Task-aware Adaptive Learning for Cross-domain Few-shot Learning24
The Task-aware Adaptive Network (TA2-Net) is proposed, which is trained by reinforcement learning to adaptively estimate the optimal task-specific parameter configuration for each test task, and outperforms existing state-of-the-art methods.
- Learning invariant structure for object identification by using graph methods24
This paper describes a classifier which is unique in being able to learn class identity no matter how the class instances are depicted, and depends on spectral graph analysis of a hierarchical description of an image to construct a feature vector of fixed dimension.
- Making a Bird AI Expert Work for You and Me22
This paper proposes to represent knowledge as highly discriminative visual regions that are expert-exclusive and instantiate it via a novel multi-stage learning framework and proposes a crude but benchmarkable metric TEMI to allow future efforts in this direction to be comparable to the authors' without the need of large-scale human studies.
- 22
- 21
- 3D VR Sketch Guided 3D Shape Prototyping and Exploration21
A 3D shape generation network that takes a 3D VR sketch as a condition, assuming that sketches are created by novices without art training and aim to reconstruct geometrically realistic 3D shapes of a given category is proposed.
- Towards the Unseen: Iterative Text Recognition by Distilling from Errors21
This framework is iterative in nature, in that it utilises predicted knowledge of character sequences from a previous iteration, to augment the main network in improving the next prediction, thus showcasing the capability of generalising onto unseen words.
- Wired Perspectives: Multi-View Wire Art Embraces Generative AI20
This work presents DreamWire, an AI system enabling everyone to craft MVWA easily, which synergises 3D Bézier curves, Prim's algorithm, and knowledge distillation from diffusion models or their variants (e.g., ControlNet).
- 20
- 20
- 20
- 20
- NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training19
NitroFusion significantly outperforms existing single-step methods across multiple evaluation metrics, particularly excelling in preserving fine details and global consistency.
- 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.
- SketchDreamer: Interactive Text-Augmented Creative Sketch Ideation19
The objective is to empower non-professional users to create sketches and, through a series of optimisation processes, transform a narrative into a storyboard by expanding the text prompt while making minor adjustments to the sketch input.
- One Sketch for All: One-Shot Personalized Sketch Segmentation19
The first one-shot personalized sketch segmentation method, which aims to segment all sketches belonging to the same category provisioned with a single sketch with a given part annotation while preserving the parts semantics embedded in the exemplar, and being robust to input style and abstraction is presented.
- 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.
- 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.
- SketchXAI: A First Look at Explainability for Human Sketches18
It is argued that sketch as a “human-centred” data form, represents a natural interface to study explainability, and a simple explainability-friendly sketch encoder is designed that accommodates the intrinsic properties of strokes: shape, location, and order.
- 18
- 18
- Towards 3D VR-Sketch to 3D Shape Retrieval18
This paper studies the use of 3D sketches as an input modality and advocates a VR-scenario where retrieval is conducted, and shows that volumetric point-based approaches exhibit superior performance on 3D sketch to 3D shape retrieval due to the sparse and abstract nature of3D VR-sketches.
- Multi-label learning with prior knowledge for facial expression analysis18
A multi-label learning algorithm for FEA is proposed to solve the problem of depicting facial expressions more effectively and model FEA as a multi- label problem, which depicts all facial expressions with multiple continuous values and labels of predefined affective states.
- 17
- 16
- Fine-Grained VR Sketching: Dataset and Insights16
The first fine-grained dataset of 1,497 3D VR sketch and 3D shape pairs of a chair category with large shapes diversity is presented, and it is argued for the most convenient sketching scenario where the sketch consists of sparse lines and does not require any sketching skills, prior training or time-consuming accurate drawing.
- SketchDesc: Learning Local Sketch Descriptors for Multi-View Correspondence16
A novel multi-branch neural network is designed that integrates a patch-based representation and a multi-scale strategy to learn the pixel-level correspondence among multi-view sketches.
- DifferSketching15
A new dataset of 3,620 freehand multi-view sketches, which are registered with their corresponding 3D objects under certain views and found that the drawings by professionals and novices show significant differences at stroke-level, both intrinsically and extrinsically.
- FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations14
FlipSketch is presented, a system that brings back the magic of flip-book animation – just draw your idea and describe how you want it to move, while maintaining the artistic essence of hand-drawn animation.
- DemoCaricature: Democratising Caricature Generation with a Rough Sketch14
The aim is to strike a delicate balance between abstraction and identity, while preserving the creativity and subjectivity inherent in a sketch, by presenting Explicit Rank-1 Model Editing alongside single-image personalisation and proposing Random Mask Reconstruction to enhance robustness.
- 14
- What Sketch Explainability Really Means for Downstream Tasks?13
A lightweight and portable explainability solution - a seamless plugin that integrates effortlessly with any pre-trained model, elim-inating the need for re-training is proposed, and the centrepiece to the solution is a stroke-level attribution map that takes different forms when linked with downstream tasks.
- Generative Sketch Healing13
This paper teaches machines to perform a similar task by recreating a vectorised human sketch from its incomplete parts, dubbed as sketch healing, and suggests that the proposed method significantly outperforms the state-of-the-art alternatives on sketch healing.
- Structure-Aware 3D VR Sketch to 3D Shape Retrieval13
This work proposes to use a triplet loss with an adaptive margin value driven by a ‘fitting gap’, which is the similarity of two shapes under structure-preserving deformations, and introduces a dataset of 202 VR sketches for 202 3D shapes drawn from memory rather than from observation.
- 13
- PQA: Perceptual Question Answering12
This paper presents the first dataset of perceptual question-answer pairs, each generated specifically for a particular Gestalt principle, and designs an agent that casts perceptual organization as a self-attention problem, where a proposed grid-to-grid mapping network directly generates answer patterns from scratch.
- 12
- 11
- 11
- 10
- 10
- Post-Processing Temporal Action Detection10
This work introduces a novel model-agnostic post-processing method without model redesign and retraining, dubbed as Gaussian Approximated Post-processing (GAP), which enables lower temporal resolutions for more efficient inference, facilitating low-resource application.
- Now You See Me: Deep Face Hallucination for Unviewed Sketches10
A new deep learning approach trained with a combination of content and adversarial losses to generate crisp photorealistic images, and it contains an integrated spatial transformer network to deal with non-rigid alignment between the domains.
- Robust visual tracking using structural region hierarchy and graph matching10
This paper investigates the fusion of state-of-the-art image segmentation hierarchies and graph matching and proposes a novel and robust algorithm to address the problem of object tracking.
- 9
- 9
- 9
- DreamCreature: Crafting Photorealistic Virtual Creatures from Imagination9
This work proposes a new method called DreamCreature, which identifies and extracts the underlying sub-concepts in an unsupervised manner, and adapts to generate novel concepts with faithful structures and photorealistic appearance by seamlessly and flexibly composing learned sub- Concepts.
- 9
- Multi-Modal Few-Shot Temporal Action Detection8
A novel MUlti-modality PromPt mETa-learning (MUPPET) method that bridges pretrained vision and language models whilst maximally reusing already learned capacity to tackle few-shot object detection problem and achieves the state-of-the-art performance on MS-COCO dataset.
- 8
- 7
- 7
- UIGR: Unified Interactive Garment Retrieval7
This paper proposes a Unified Interactive Garment Retrieval (UIGR) framework to unify TGR and VCR, and contributes a large-scale benchmark suited for both problems.
- 7
- 7
- 7
- LOW COST MULTI-SENSOR ROBOT LASER SCANNING SYSTEM AND ITS ACCURACY INVESTIGATIONS FOR INDOOR MAPPING APPLICATION7
The proposed multiple-sensor robot laser scanning system includes a panorama camera, a laser scanner, and an inertial measurement unit and etc., which are calibrated and synchronized together to achieve simultaneously collection of 3D indoor data.
- Simple art as abstractions of photographs7
It is shown that it is possible to semi-automatically process photographs into Simple Art, a term that is used to refer to a group of artistic styles such a child art, cave art, and Fine Artists as exemplified by Joan Miró.
- 6
- SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models6
This work addresses Stable Diffusion’s fundamental limitations by strategically combining SD with CLIP, whose strong semantic understanding naturally compensates for SD’s spatial-frequency biases, and achieves state-of-the-art performance in sketch retrieval, recognition, segmentation, and correspondence learning.
- 6
- IEEE Access Special Section Editorial: AI-Driven Big Data Processing: Theory, Methodology, and Applications6
This paper discusses how to analyze and process big data in a way that is more effective and reduces costs, how to discover and understand knowledge from the data, and how to generalize and transfer these discoveries into other application fields.
- 5
- Single Stage Multi-Pose Virtual Try-On5
A novel single stage model for MPVTON with a parallel flow estimation module that predicts the flow fields for both person and garment images conditioned on the target pose is proposed, resulting in new SOTA performance on existing MPVton benchmarks.
- 5
- ConceptHash: Interpretable Fine-Grained Hashing via Concept Discovery4
Existing fine-grained hashing methods typically lack code interpretability as they compute hash code bits holistically using both global and local features, so this approach allows us to develop hash codes that exhibit similarity within families of species while remaining distinct from species in other families.
- 4
- Robust Target Training for Multi-Source Domain Adaptation4
A novel Bi-level Optimization based Robust Target Training (BORT) method for MSDA which turns any existing fully-trained one-step MSDA model into a labeling function to generate pseudo-labels for the target data and trains a target model using pseudo-labeled target data only.
- Recent advances in machine learning for non-Gaussian data processing4
The scope of this special issue of the Elsevier's Journal on Neurocomputing is to provide theoretical foundations and ground-breaking models and algorithms to solve the challenge of analyzing and understanding non-Gaussian distributed data.
- 4
- Structure Is a Visual Class Invariant4
A classifier is described which is unique in being able to learn class identity no matter how the class instances are depicted, the key to this is the proposition that topological structure is a class invariant.
- 3
- 3
- 3
- Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch3
This paper first demonstrates existing state-of-the-art efficient light-weight models designed for photos do not work on sketches, then proposes two sketch-specific components which work in a plug-n-play manner on any photo efficient network to adapt them to work on sketch data.
- Adaptive evolutionary neural architecture search based on one-dimensional convolutional neural network for electric rudder fault diagnosis3
A fault diagnosis framework for the electric rudder based on an adaptive evolutionary neural architecture search (AENAS-FD) is proposed, demonstrating that AENAS-FD can generate superior network architectures for diagnosing rudder faults, exhibiting better diagnostic accuracy when compared to manually designed networks.
- Annotation-Free Human Sketch Quality Assessment3
This paper proposes Geometry-Aware Classification Layer (GACL), a generic method that makes feature-magnitude-as-quality-metric possible and importantly does it without the need for specific quality annotations from humans and demonstrates its applications in vertical problems such as noisy label cleansing.
- SketchAnimator: Animate Sketch via Motion Customization of Text-to-Video Diffusion Models3
A novel sketch animation model, SketchAnimator, which enables adding creative motion to a given sketch, like "a jumping car", and produces a sketch video that not only retains the original appearance of the sketch but also mirrors the dynamic movements of the reference video.
- 3
- 3
- IEEE Access Special Section Editorial: Recent Advantages of Computer Vision3
With the emergence of big vision data and the development of artificial intelligence, it is important to investigate new theories, methods, and applications in computer vision.
- 3
- Non-invasive damage detection in composite beams using marker extraction and wavelets3
A wavelet-based damage detection framework that locates damage on cantilevered composite beams via NDE using computer vision technologies is presented and it is demonstrated that modal shapes of cantilever beams can be readily reconstructed by extracting markers using Hough Transform from images captured using conventional slow motion cameras.
- Stable Image Descriptions Using Gestalt Principles3
This paper addresses the problem of grouping image primitives with an explicit definition of the Gestalt principle of Pragnanz, which organizes primitives into descriptions of images that are both simple and stable.
- Shapes Fit For Purpose3
The shape classier is used in both discriminative (matching) and generative (image synthesis) tasks and the level of abstraction offered by the shape classifier is novel and useful.
- 2
- Generative Model Based Noise Robust Training for Unsupervised Domain Adaptation2
This paper proposes a Generative model-based Noise-Robust Training method (GeNRT), which eliminates domain shift while mitigating label noise, and gets theoretically linked to the Ben-David domain adaptation theorem for reducing the domain gap.
- Unsupervised Hashing with Similarity Distribution Calibration2
A novel Similarity Distribution Calibration (SDC) method is introduced, which aligns the hash code similarity distribution towards a calibration distribution with sufficient spread across the entire similarity capacity/range, to alleviate the similarity collapse problem.
- Learning to Augment via Implicit Differentiation for Domain Generalization2
This paper proposes a novel augmentation-based DG approach, dubbed AugLearn, which views a data augmentation module as hyper-parameters of a classification model and optimizes the module together with the model via meta-learning, and formulate an efficient joint training algorithm, for both the augmentation modules and the classification model, based on the implicit function theorem.
- 2
- 2
- Your "Labrador" is My "Dog": Fine-Grained, or Not.2
The key intuition that: coarse-level label prediction exacerbates fine-grained feature learning, yet fine-level feature betters the learning of coarse- level classifier is discovered, which enables the design of a very simple albeit surprisingly effective solution to a new problem.
- 2
- One-Shot Learning of Sketch Categories with Co-regularized Sparse Coding2
A transfer learning framework which enables one-shot learning of sketch categories and is based on a novel co-regularized sparse coding model which exploits common/shareable parts among human sketches of seen categories and transfer them to unseen categories.
- 2
- Learning object classes from structure2
This work does not build a codebook of interest regions but instead makes use of a hierarchical description of an image based on a watershed transform, which allows it to classify not just photographs, but also paintings and drawings of visual objects.
- PerfGuard: A Performance-Aware Agent for Visual Content Generation1
Experimental comparisons against state-of-the-art methods demonstrate PerfGuard's advantages in tool selection accuracy, execution reliability, and alignment with user intent, validating its robustness and practical utility for complex AIGC tasks.
- 1
- Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection1
This work proposes a prototypical setup for keypoint detection that overcomes hurdles in mastering crossmodal embeddings and handling user-specific sketch styles, and demonstrates success in few-shot convergence across novel keypoints and classes through extensive experiments.
- 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
- Visual Recognition of Man-made Materials and Structures in an Office Environment1
This paper demonstrates a new approach towards object recognition founded on the development of Neural Network classifiers and Bayesian Networks that makes use of an intermediate level of image representation and demonstrates how object recognition can be achieved.
- –
- –
- –
- –
- DreamColour: Controllable Video Colour Editing without Training–
This work presents a practical, training-free framework that makes precise video colour editing accessible through an intuitive interface while maintaining professional-quality output, and demonstrates that it matches or exceeds state-of-the-art methods while eliminating the need for training or specialized hardware.
- –
- –
- –
- –
- –
- Discovering Social Relationship between City Regions using Human Mobility–
A Region Activation Entropy Model (RAEM) is proposed to discover the social relations hidden between the regions, which can benefit a variety of applications, including city planning, location choosing for a business and predicting the spread of human.
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 2026-10-14. 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.