Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks161 from public data
- 1,645
- Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification635
A Multi-crop Convolutional Neural Network (MC-CNN) is presented to automatically extract nodule salient information by employing a novel multi-crop pooling strategy which crops different regions from convolutional feature maps and then applies max-pooling different times.
- Multi-oriented Text Detection with Fully Convolutional Networks596
A novel approach for text detection in natural images that consistently achieves the state-of-the-art performance on three text detection benchmarks: MSRA-TD500, I CDAR2015 and ICDAR2013.
- Few-Shot Image Recognition by Predicting Parameters from Activations594
A novel method that can adapt a pre-trained neural network to novel categories by directly predicting the parameters from the activations is proposed, which achieves the state-of-the-art classification accuracy on Novel categories by a significant margin while keeping comparable performance on the large-scale categories.
- 567
- Deep Co-Training for Semi-Supervised Image Recognition545
This paper presents Deep Co-Training, a deep learning based method inspired by the Co- Training framework, which outperforms the previous state-of-the-art methods by a large margin in semi-supervised image recognition.
- Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation414
It is revealed that the simple mechanism of copy-pasting bidirectionally between labeled and unlabeled data is good enough and the experiments show solid gains compared with other state-of-the-arts on various semi-supervised medical image segmentation datasets.
- PCL: Proposal Cluster Learning for Weakly Supervised Object Detection408
This paper first shows that instances can be assigned object or background labels directly based on proposal clusters for instance classifier refinement, and then shows that treating each cluster as a small new bag yields fewer ambiguities than the directly assigning label method.
- A Fixed-Point Model for Pancreas Segmentation in Abdominal CT Scans317
This paper forms a fixed-point model which uses a predicted segmentation mask to shrink the input region and outperform the state-of-the-art by more than \(4\%\), measured by the average Dice-Sorensen Coefficient (DSC).
- Intriguing Findings of Frequency Selection for Image Deblurring295
This paper reveals an intriguing phenomenon that simply applying ReLU operation on the frequency domain of a blur image followed by inverse Fourier transform provides faithful information about the blur pattern, and builds a block that noticeably improves backbone architectures without introducing many parameters, while maintaining low computational complexity.
- 278
- Spatial–temporal convolutional neural networks for anomaly detection and localization in crowded scenes273
The proposed method for detecting and locating anomalous activities in video sequences of crowded scenes is a coupling of anomaly detection with a spatial-temporal Convolutional Neural Networks (CNN), which to the best of the knowledge has not been previously done.
- Learning Residual Images for Face Attribute Manipulation269
Instead of manipulating the whole image, this work proposes to learn the corresponding residual image defined as the difference between images before and after the manipulation, so that the manipulation can be operated efficiently with modest pixel modification.
- Abdominal multi-organ segmentation with organ-attention networks and statistical fusion255
This work introduces a novel framework for multi-organ segmentation of abdominal regions by using organ-attention networks with reverse connections (OAN-RCs) which are applied to 2D views, of the 3D CT volume, and output estimates which are combined by statistical fusion exploiting structural similarity.
- Single-Shot Object Detection with Enriched Semantics228
A novel single shot object detection network named Detection with Enriched Semantics (DES) is proposed, to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module.
- 201
- Deep Regression Forests for Age Estimation183
The proposed Deep Regression Forests (DRFs), an end-to-end model for age estimation, connect the split nodes to a fully connected layer of a convolutional neural network (CNN) and deal with inhomogeneous data by jointly learning input-dependant data partitions at the split node and data abstractions at the leaf nodes.
- Domain Adaptive Relational Reasoning for 3D Multi-organ Segmentation181
A novel unsupervised domain adaptation (UDA) method, named Domain Adaptive Relational Reasoning (DARR), to generalize 3D multi-organ segmentation models to medical data collected from different scanners and/or protocols (domains).
- Synthesize Then Compare: Detecting Failures and Anomalies for Semantic Segmentation178
This paper systematically study failure and anomaly detection for semantic segmentation and proposes a unified framework, consisting of two modules, to address these two related problems.
- A Survey on Label-Efficient Deep Image Segmentation: Bridging the Gap Between Weak Supervision and Dense Prediction159
A taxonomy is developed to organize the existing label-efficient image segmentation methods according to the supervision provided by different types of weak labels and discusses an important question: how to bridge the gap between weak supervision and dense prediction.
- Semi-Supervised 3D Abdominal Multi-Organ Segmentation Via Deep Multi-Planar Co-Training153
Deep Multi-Planar Co-Training is proposed, whose contributions can be divided into two folds: 1) the deep model is learned in a co-training style which can mine consensus information from multiple planes like the sagittal, coronal, and axial planes; 2) Multi-planar fusion is applied to generate more reliable pseudo-labels, which alleviates the errors occurring in the pseudo-Labels and thus can help to train better segmentation networks.
- A 3D Coarse-to-Fine Framework for Volumetric Medical Image Segmentation152
3D Convolutional Neural Networks are adopted to segment volumetric medical images and outperforms the 2D counterpart to a large margin since it can leverage the rich spatial information along all three axes.
- Weight Standardization148
Weight Standardization is proposed to accelerate deep network training by standardizing the weights in the convolutional layers, which is able to smooth the loss landscape by reducing the Lipschitz constants of the loss and the gradients.
- Deep Distance Transform for Tubular Structure Segmentation in CT Scans136
This work proposes a geometry-aware tubular structure segmentation method, Deep Distance Transform (DDT), which combines intuitions from the classical distance transform for skeletonization and modern deep segmentation networks, and applies it on six medical image datasets.
- 116
- DeepSkeleton: Learning Multi-Task Scale-Associated Deep Side Outputs for Object Skeleton Extraction in Natural Images109
This paper presents a novel fully convolutional network with multiple scale-associated side outputs to address object skeleton extraction from natural images, and achieves promising results on two skeleton extraction datasets, and significantly outperforms other competitors.
- 108
- Object Skeleton Extraction in Natural Images by Fusing Scale-Associated Deep Side Outputs107
A fully convolutional network with multiple scale-associated side outputs is presented to address object skeleton extraction in natural images, and achieves promising results on two skeleton extraction datasets, and significantly outperforms other competitors.
- GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting101
GaussianObject, a framework to represent and render the 3D object with Gaussian splatting that achieves high rendering quality with only 4 input images, is proposed and evaluated on several challenging datasets, achieving superior performance from only four views and significantly outperforming previous SOTA methods.
- Skeleton growing and pruning with bending potential ratio101
A novel significance measure for skeleton pruning, called bending potential ratio (BPR), in which the decision regarding whether a skeletal branch should be pruned or not is based on the context of the boundary segment that corresponds to the branch, is proposed.
- End-to-End Human-Gaze-Target Detection with Transformers96
Unlike existing two-stage methods that require human head locations as input and can predict only one human's gaze target at a time, HGTTR can directly predict the locations of all people and their gaze targets at one time in an end-to-end manner.
- 87
- 80
- Segment Anything in 3D with Radiance Fields78
The research reveals a potential methodology to lift the ability of a 2D segmentation model to 3D and designs an efficient solution, leveraging the radiance field as a cheap and off-the-shelf prior that connects multi-view 2D images to the 3D space.
- 75
- Learning from Experts: Developing Transferable Deep Features for Patient-Level Lung Cancer Prediction71
A domain-adaptation framework that learns transferable deep features for patient-level lung cancer malignancy prediction and can largely reduce the demand for pathologically-proven data is formulated, holding promise to empower cancer diagnosis by leveraging multi-source CT imaging datasets.
- 70
- Multi-stage Multi-recursive-input Fully Convolutional Networks for Neuronal Boundary Detection66
A multi-stage multi-recursiveinput fully convolutional networks to address the segmentation of EM images and achieves promising results on two public available EM segmentation datasets, the mouse piriform cortex dataset and the ISBI 2012 EM dataset.
- MagicNet: Semi-Supervised Multi-Organ Segmentation via Magic-Cube Partition and Recovery62
A novel teacher-student model for semi-supervised multi-organ segmentation that treats the CT volume as amagic-cube and N3-cube partition-and-recovery process matches with the rule of playing a magic-cube, and encourages unlabeled images to learn organ semantics in relative locations from the labeled images and enhances the learning ability for small organs.
- 60
- 57
- Multiple instance subspace learning via partial random projection tree for local reflection symmetry in natural images57
A novel multiple instance learning framework for local reflection symmetry detection, named multiple instance subspace learning (MISL), which instead learns a group of models respectively on well partitioned subspaces, and an efficient dividing strategy under MIL setting, named partial random projection tree (PRPT).
- Hi-Fi: Hierarchical Feature Integration for Skeleton Detection55
A new convolutional neural network architecture is presented by introducing a novel hierarchical feature integration mechanism, named Hi-Fi, to address the object skeleton detection problem and significantly outperforms the state-of-the-art methods in terms of effectively fusing features from very different scales.
- 55
- Skeleton pruning as trade-off between skeleton simplicity and reconstruction error52
This work proposes a simple algorithm to approximate the maximum of the Bayesian posterior probability which defines an order for iteratively removing the end branches to obtain the pruned skeleton and presents experimental results obtained without any parameter tuning.
- ContrastMask: Contrastive Learning to Segment Every Thing51
This paper proposes a new method, named ContrastMask, which learns a mask segmentation model on both base and novel categories under a unified pixel-level contrastive learning framework, and demonstrates the superiority of this method, which outperforms previous state-of-the-arts methods.
- USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation49
This paper proposes a Unified optimization paradigm for Seed Area GEneration (USAGE) for both types of networks, in which the objective function to be optimized consists of two terms: a generation loss and a regularization loss, which ensures the consistency between the seed areas that are generated by self-adaptive network adjustment from different views.
- Text detection in scene images based on exhaustive segmentation49
This paper proposes a novel method, which is based on exhaustive segmentation, to detect text in scene images, and argues that the text line grouping problem can be posed as the edge cut of the fully connected graph.
- Shape clustering: Common structure discovery49
This paper aims to address the problem of shape clustering by discovering the common structure which captures the intrinsic structural information of shapes belonging to the same cluster, based on a skeleton graph, named common structure skeleton graph (CSSG), which expresses possible correspondences between nodes of the individual skeletons of the cluster.
- The FELIX Project: Deep Networks To Detect Pancreatic Neoplasms48
A suite of algorithms (named FELIX) that can recognize pancreatic lesions from CT images without human input are described that may be able to assist radiologists in identifying pancreatic cancers earlier, when surgery and other treatments offer more hope for long-term survival.
- Robust Face Detection via Learning Small Faces on Hard Images46
An anchor-based deep face detector is built, which only outputs a single high-resolution feature map with small anchors, to specifically learn small faces and train it by a novel hard image mining strategy which automatically adjusts training weights on images according to their difficulties.
- Self-supervised Character-to-Character Distillation for Text Recognition45
A novel self-supervised Character-to-Character Distillation method, CCD, which enables versatile augmentations to facilitate general text representation learning and delineate the character structures of unlabeled real images by designing a self- supervised character segmentation module.
- Shape Recognition by Combining Contour and Skeleton into a Mid-Level Representation45
The proposed shape descriptor provides the complementary geometric information from both contour and skeleton parts, including the spatial distribution and the thickness change along the shape part, which achieves the state-of-the-art performances on several standard shape benchmarks.
- Saliency in Augmented Reality43
To better predict the saliency in AR, a vector quantized saliency prediction method is proposed and generalize it for ARSaliency prediction, and experimental results demonstrate the superiority of the proposed method on both of the common saliency predictions problem and the AR saliency Prediction problem over benchmark methods.
- 41
- Self-Supervised Implicit Glyph Attention for Text Recognition41
SICA delineates the glyph structures of text images by jointly self-supervised text seg-mentation and implicit attention alignment, which serve as the supervision to improve attention correctness without extra character-level annotations.
- ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond39
It is argued that estimation of object scales in images is helpful for generating object proposals, especially for supermarket images where object scales are usually within a small range, and a proposed method for predicting object scales is called ScaleNet.
- 38
- 38
- A 3D Coarse-to-Fine Framework for Automatic Pancreas Segmentation.37
A novel 3D-based coarseto-fine framework for volumetric pancreas segmentation that outperforms the 2D counterpart to a large margin since it can leverage the rich spatial information along all three axes.
- Efficient Deformable Tissue Reconstruction via Orthogonal Neural Plane36
Fast Orthogonal Plane (Forplane), a novel, efficient framework based on neural radiance fields (NeRF) for the reconstruction of deformable tissues, is introduced, which substantially accelerates both the optimization process and the inference process while maintaining or even improving the quality across a variety of non-rigid deformations.
- Pancreas Segmentation in Abdominal CT Scan: A Coarse-to-Fine Approach.36
This paper trains two deep neural networks using different regions of the input volume and proposes a coarse-to-fine approach, which outperforms the state-of-the-art by more than 4% measured by the Dice-Sorensen Coefficient (DSC).
- 36
- Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding35
A novel visuallanguage alignment method is introduced that casts the key issue as a Visual Question Answering with Mask generation (VQA-Mask) task, optimizing two tasks simultaneously: VQA-based text parsing and mask generation.
- Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction34
A partially supervised setting, where cheap image-level annotations are provided for all the training data, and the costly per-voxel annotations are only available for a subset of them, is considered, which boosts PDAC segmentation accuracy by more than 5% compared with the state-of-the-arts.
- Fast cascade face detection with pyramid network33
This paper proposes a fast CNNs cascade face detector with multi-task learning and network acceleration techniques, which is comparable in performance with the-state-of-arts while the speed reaches astonishing 165 fps on Titan GPU.
- 31
- 30
- 30
- 28
- Lung nodule malignancy prediction using multi-task convolutional neural network28
Experiments show that the proposed method could predict the lung nodule malignancy likelihood effectively and outperforms the state-of-the-art methods, and demonstrated the possibility of the method facilitating the radiologists for nodule staging assessment and individual therapeutic planning.
- Parameter Efficient Fine-Tuning via Cross Block Orchestration for Segment Anything Model27
This paper equips PEFT with a cross-block orchestration mechanism to enable the adaptation of the Segment Anything Model to various downstream scenarios, and introduces a novel inter-block communication module, which integrates a learnable relation matrix to facilitate communication among different coefficient sets of each PEFT block's parameter space.
- Training Multi-organ Segmentation Networks with Sample Selection by Relaxed Upper Confident Bound27
This paper proposes a new sample selection policy, named Relaxed Upper Confident Bound (RUCB), which exploits a range of hard samples rather than being stuck with a small set of very hard ones, which mitigates the influence of annotation errors during training.
- Multi-oriented text detection from natural scene images based on a CNN and pruning non-adjacent graph edges26
A novel method that effectively and robustly detects multi-oriented text in natural scene images by employing an exhaustive segmentation-based method that can extract characters in arbitrary orientations.
- NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds25
The holistic priors, including pseudo depth maps and view coverage information, from neural reconstruction are utilized to guide the learning of implicit neural representations of 3D indoor scenes to enable free navigation in a room.
- BézierPalm: A Free Lunch for Palmprint Recognition25
An intuitive geometric model which represents palmar creases with parameterized B´ezier curves is introduced, which can synthesize massive training samples of diverse identities, which enables us to pretrain large-scale palmprint recognition models.
- 25
- Towards Unsupervised Learning for Instrument Segmentation in Robotic Surgery with Cycle-Consistent Adversarial Networks25
The proposed approach allows to train image segmentation models without the need to acquire expensive annotations and can potentially exploit large unlabeled endoscopic image collection outside the annotated distributions of image/annotation data.
- Deep learning in bladder cancer imaging: A review24
An overview of the latest progress in the application of deep learning to the imaging assessment of bladder cancer is provided and examples of how deep learning helps in the diagnosis, staging, and treatment management of bladdercancer using medical images are provided.
- 23
- 23
- Detecting Pancreatic Ductal Adenocarcinoma in Multi-phase CT Scans via Alignment Ensemble23
An extensive empirical evaluation on two PDAC datasets is provided and it is shown that the proposed alignment ensemble significantly outperforms previous state-of-the-art approaches, illustrating the strong potential for clinical use.
- TDMPNet: Prototype Network with Recurrent Top-Down Modulation for Robust Object Classification Under Partial Occlusion23
This work integrates inductive priors including prototypes, partial matching and top-down modulation into deep neural networks to realize robust object classification under novel occlusion conditions, with limited Occlusion in training data.
- 22
- 21
- Segmentation for Classification of Screening Pancreatic Neuroendocrine Tumors19
This work presents an intuitive method to detect in the early stage the pancreatic neuroendocrine tumors (PNETs), a group of endocrine tumors arising in the pancreas, which are the second common type of pancreatic cancer, by checking the abdominal CT scans.
- Stability and optimization error of stochastic gradient descent for pairwise learning19
This paper establishes the stability results of SGD for pairwise learning in the convex, strongly convex and non-convex settings, from which generalization bounds can be naturally derived by lower-bounding the sum of stability and optimization error by the minimax statistical error over a prescribed class of pairwise loss functions.
- Proposal pyramid networks for fast face detection19
Results on several public benchmarks show that the proposed face detector achieves comparable accuracy to the-state-of-arts while the detection speed reaches 60 FPS with an i5 CPU, which significantly exceeds previous DCNN-based face detectors.
- Bag of Shape Features with a learned pooling function for shape recognition19
The pooling function is formulated as a weighted sum of max pooling and average pooling, where the weight is expressed by an activation function of the input shape features, and fed into a SVM classifier to minimize a shape classification loss.
- 17
- A Token-Level Text Image Foundation Model for Document Understanding16
TokenFD is the first token-level visual foundation model specifically tailored for text-image-related tasks, designed to support a variety of traditional downstream applications, and seamlessly replaces previous VFMs with TokenFD to construct a token-level visual-language MLLM, TokenVL, for VQA-based document understanding tasks.
- ChildPredictor: A Child Face Prediction Framework With Disentangled Learning15
A new disentangled learning strategy for children's face prediction called ChildPredictor, which transfers human faces to genetic factors by encoders and back by generators, and learns the relationship between the genetic factors of parents and children through a mapping function.
- 15
- Skeleton2Humanoid: Animating Simulated Characters for Physically-plausible Motion In-betweening13
Experiments on the challenging LaFAN1 dataset show the proposed Skeleton2Humanoid system can outperform prior methods significantly in terms of both physical plausibility and accuracy.
- 13
- Abnormal event detection in crowded scenes using two sparse dictionaries with saliency13
A method using two sparse dictionaries with saliency to detect abnormal events in crowded scenes using a multiscale histogram of optical flow and gradient and an abnormal dictionary is added to the traditional sparse model with only a normal dictionary included.
- 12
- Neighborhood geometry based feature matching for geostationary satellite remote sensing image12
Experimental results on 25 pairs of newly annotated images show that the proposed method is competitive to several prior arts with respect to matching accuracy, and significantly more efficient than others.
- 12
- Joint Gaze-Location and Gaze-Object Detection11
GTR is proposed, short for GTR, streamlining the gaze following detection pipeline by eliminating all additional components, leading to the first unified paradigm that unites GL-D and GO-D in a fully end-to-end manner.
- 11
- Face identification using reference-based features with message passing model11
A system for face identification that adopts the one-shot similarity kernel for learning the similarity of two face images and proposes a graph-based method for selecting an optimal set of reference images.
- Recursive spatiotemporal subspace learning for gait recognition11
Experimental result shows that the proposed method achieves highly competitive performance with respect to the published gait recognition approaches on the USF HumanID gait database.
- 10
- 10
- A multi-view face recognition system based on cascade face detector and improved Dlib10
This research presented a framework for multi-view face detect and recognition system based on cascade face detector and improved Dlib, and proposed an improved distance model based on Dlib to improve the accuracy of multiview face recognition.
- Slope-Restricted Multi-Scale Feature Matching for Geostationary Satellite Remote Sensing Images10
This paper proposes a novel algorithm named slope-restricted multi-scale feature matching, which is based on local geometric similarity to enhance the matching performance, and shows that the proposed method is more accurate and efficient than other algorithms.
- Compressing and Accelerating Neural Network for Facial Point Localization10
A novel method is proposed to compress and accelerate large DNN models while maintaining the performance, which achieves 26 × compression and 4 × acceleration while the root mean squared error (RMSE) increases by just 3.6%.
- Appeal: Allow Mislabeled Samples the Chance to be Rectified in Partial Label Learning9
Extensive experiments demonstrate that the performance and disambiguation ability of several well-established stand-alone and deep-learning based PLL approaches can be significantly improved by coupling with this learning paradigm.
- 9
- Learning nonlinear manifolds based on mixtures of localized linear manifolds under a self-organizing framework9
A neural model which learns low-dimensional nonlinear manifolds embedded in higher-dimensional data space based on mixtures of local linear manifolds under a self-organizing framework and it is proved that there is no local extremum for each sub-model.
- Rethinking mask heads for partially supervised instance segmentation8
A teacher-student architecture where the teacher learns general yet comprehensive knowledge and the students, guided by the teacher, delve deeper into specific categories, demonstrating the superiority of the method on the challenging COCO dataset.
- 7
- 7
- 7
- One-shot monochromatic symbol pattern for 3D reconstruction using perfect submap coding7
The symbol density spectrum (SDS) and its features are used to choose symbols for improving resolution and decreasing decoding error of perfect submap symbol patterns.
- Adaptive feature alignment for adversarial training6
This paper proposes the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths by predicting a fusing weight in a dual-BN architecture and improves the model robustness against adversarial samples without incurring much loss in standard accuracy.
- Abnormal events detection in crowded scenes by trajectory cluster6
Experimental results indicated that the proposed algorithm could be used to reliably locate the abnormal events in crowded scenes.
- Regularity Guaranteed Human Pose Correction6
The experimental results demonstrate that the proposed pose correction approach not only improves the accuracy, but also outputs more regular poses, compared to the-state-of-the-art.
- Unsupervised human skeleton extraction from Kinect depth images6
Experimental results show that without any markers for training, human skeletons obtained by the proposed unsupervised skeletonization method can represent both the body parts without occlusion and the main torso under Occlusion.
- Stereo matching based on orthogonal Gaussian-Hermite moments6
A stereo matching cost based on orthogonal Gaussian-Hermite moments (OGHMs) space is proposed and evaluated together with different matching costs with respect to radiometric variations of the input images to guarantee more insensitive result against different kinds of radiometric differences.
- 5
- FATE: Feature-Adapted Parameter Tuning for Vision-Language Models4
A Feature-Adapted parameTer Efficient tuning paradigm for vision-language models, dubbed as FATE, which injects informative features from the vision encoder into language encoder's parameters space and treats them as parameters for fine-tuning each layer of CLIP's language encoder.
- 4
- 4
- Shape-aware Feature Extraction for Instance Segmentation.4
A new region- of-interest (RoI) feature extraction strategy, named Shape-aware RoIAlign, which focuses feature extraction within a region aligned well with the shape of the instance-of-interest rather than a rectangular RoI.
- Lesion Detection by Efficiently Bridging 3D Context4
This work designs a hybrid detector that surpasses the current state-of-the-art by a large margin with comparable speed and GPU memory consumption and can combine 3D knowledge effectively and provide higher quality backbone features.
- Directional Edge Boxes: Exploiting Inner Normal Direction Cues for Effective Object Proposal Generation4
A new representation named directional edges is developed on which each edge pixel is assigned with a direction toward object center, through learning a direction prediction model with convolutional neural networks in a holistic manner.
- Realistic Surgical Simulation from Monocular Videos3
Experiments on various surgical scenarios and interactions demonstrate SurgiSim's ability to perform realistic simulation of soft tissues among surgical procedures, showing its enormous potential for enhancing surgical training, planning, and robotic surgery systems.
- 3
- Learning to Find Correlated Features by Maximizing Information Flow in Convolutional Neural Networks3
This work proposes an information flow maximization (IFM) loss as a regularization term to find the discriminative correlated features and validates the method on the shiftedMNIST dataset and shows the effectiveness of IFM loss in learning representative and discriminatives features.
- Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds2
This paper proposes a quite challenging but valuable task to reconstruct the human body from only two images, i.e., the front and back view, which can largely lower the barrier for users to create their own 3D digital humans.
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 2D-Based Coarse-to-Fine Approaches for Small Target Segmentation in Abdominal CT Scans1
This chapter proposes two coarse-to-fine mechanisms which use prediction from the first (coarse) stage to shrink the input region for the second (fine) stage and inserts a saliency transformation module between the two stages.
- 1
- 1
- Skeletonization in natural images and its application to object recognition1
A fully convolutional network with multiple scale-associated side outputs that can effectively localize skeleton pixels with multiple scales and significantly outperforms other competitors on skeletonization datasets.
- 1
- Fast large-scale object retrieval with binary quantization1
This paper proposes a feature quantization algorithm called binary quantization, which converts a scale-invariant feature transform (SIFT) feature into a descriptive and discriminative bit-vector, which allows itself to adapt to the classic inverted file structure for box indexing.
- Distributed compressive sensing of light field1
Experimental results show that SROMP algorithm could be used to achieve high accuracy reported in the literatures, and a recovery algorithm was proposed for the model -- simultaneous regularized orthogonal matching pursuit algorithm (SROMP), which uses the correlation to reconstruct the light field image sequences.
- –
- –
- –
- –
- –
- Spatial Transformer Introspective Neural Network.–
The spatial transformer introspective neural network (ST-INN) is proposed that explicitly generates samples with the unseen affine transformation variations in the training set that achieves classification accuracy improvements on several benchmark datasets, including MNIST, affNIST, SVHN and CIFAR-10.
- –
- –
- Face Recognition Using Local Variation–
A novel approach, namely local variation projection (LVP), is presented for face recognition, which defines an adjacency graph to model the variation among nearby face images, which includes the within- class variation and between-class variation, also called margin.
- –
- –
- –
- Locally Linear Online Mapping for Mining Low-Dimensional Data Manifolds–
An online-learning neural model which maps nonlinear data structures onto mixtures of low-dimensional linear manifolds that avoids confusion between local sub-models common in other similar networks is proposed.
- A practical method of stereo camera calibration–
A practical approach of the calibration of a stereovision system is proposed, where Chessboard-like patterns are used in the calibration and the grid corners are detected automatically by a new scheme based on the symmetry in the local area.
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 2026-10-15. 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.