Search Results for author:
Found 470 papers, 185 papers with code
Generalized Canonical Correlation Analysis and Its Application to Blind Source Separation Based on a Dual-Linear Predictor Structure
Blind source separation (BSS) is one of the most important and established research topics in signal processing and many algorithms have been proposed based on different statistical properties of the source signals.
Image Fusion with Local Spectral Consistency and Dynamic Gradient Sparsity
In this paper, we propose a novel method for image fusion from a high resolution panchromatic image and a low resolution multispectral image at the same geographical location.
Unsupervised One-Class Learning for Automatic Outlier Removal
Outliers are pervasive in many computer vision and pattern recognition problems.
Going Deeper with Convolutions
We propose a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC 2014).
Multiple Object Tracking: A Literature Review
We inspect the recent advances in various aspects and propose some interesting directions for future research.
Learning to Rank Binary Codes
Binary codes have been widely used in vision problems as a compact feature representation to achieve both space and time advantages.
SIRF: Simultaneous Image Registration and Fusion in A Unified Framework
In this paper, we propose a novel method for image fusion with a high-resolution panchromatic image and a low-resolution multispectral image at the same geographical location.
Discrete Graph Hashing
Hashing has emerged as a popular technique for fast nearest neighbor search in gigantic databases.
Zeta Hull Pursuits: Learning Nonconvex Data Hulls
Selecting a small informative subset from a given dataset, also called column sampling, has drawn much attention in machine learning.
A new hybrid metric for verifying parallel corpora of Arabic-English
This paper discusses a new metric that has been applied to verify the quality in translation between sentence pairs in parallel corpora of Arabic-English.
Saliency Propagation From Simple to Difficult
In the teaching-to-learn step, a teacher is designed to arrange the regions from simple to difficult and then assign the simplest regions to the learner.
Understanding Image Structure via Hierarchical Shape Parsing
A hierarchical shape parsing strategy is proposed to partition and organize image components into a hierarchical structure in the scale space.
Towards 3D Object Detection With Bimodal Deep Boltzmann Machines Over RGBD Imagery
In particular, we slide a 3D detection window in the 3D point cloud to match the exemplar shape, which the lack of training data in 3D domain is conquered via (1) We collect 3D CAD models and 2D positive samples from Internet.
Discrete Hyper-Graph Matching
Evaluations on both synthetic and real-world data corroborate the efficiency of our method.
ParseNet: Looking Wider to See Better
When we add our proposed global feature, and a technique for learning normalization parameters, accuracy increases consistently even over our improved versions of the baselines.
Ranked #39 on
Semantic Segmentation
on PASCAL VOC 2012 test
Robust High Quality Image Guided Depth Upsampling
A popular solution is upsampling the obtained noisy low resolution depth map with the guidance of the companion high resolution color image.
Stochastic Gradient Made Stable: A Manifold Propagation Approach for Large-Scale Optimization
Stochastic gradient descent (SGD) holds as a classical method to build large scale machine learning models over big data.
Theoretic Analysis and Extremely Easy Algorithms for Domain Adaptive Feature Learning
Domain adaptation problems arise in a variety of applications, where a training dataset from the \textit{source} domain and a test dataset from the \textit{target} domain typically follow different distributions.
Learning to Hash for Indexing Big Data - A Survey
Such learning to hash methods exploit information such as data distributions or class labels when optimizing the hash codes or functions.
Top Rank Supervised Binary Coding for Visual Search
In this paper, we propose a novel supervised binary coding approach, namely Top Rank Supervised Binary Coding (Top-RSBC), which explicitly focuses on optimizing the precision of top positions in a Hamming-distance ranking list towards preserving the supervision information.
Learning Binary Codes for Maximum Inner Product Search
Inspired by the latest advance in asymmetric hashing schemes, we propose an asymmetric binary code learning framework based on inner product fitting.
SSD: Single Shot MultiBox Detector
Experimental results on the PASCAL VOC, MS COCO, and ILSVRC datasets confirm that SSD has comparable accuracy to methods that utilize an additional object proposal step and is much faster, while providing a unified framework for both training and inference.
Ranked #3 on
Object Detection
on PASCAL VOC 2012
Data Driven Robust Image Guided Depth Map Restoration
Depth maps captured by modern depth cameras such as Kinect and Time-of-Flight (ToF) are usually contaminated by missing data, noises and suffer from being of low resolution.
Deep Learning Driven Visual Path Prediction from a Single Image
The highly effective visual representation and deep context models ensure that our framework makes a deep semantic understanding of the scene and motion pattern, consequently improving the performance of the visual path prediction task.
Visual Tracking via Reliable Memories
In this paper, we propose a novel visual tracking framework that intelligently discovers reliable patterns from a wide range of video to resist drift error for long-term tracking tasks.
Scalable Sequential Spectral Clustering
In the past decades, Spectral Clustering (SC) has become one of the most effective clustering approaches.
Feature-Area Optimization: A Novel SAR Image Registration Method
This letter proposes a synthetic aperture radar (SAR) image registration method named Feature-Area Optimization (FAO).
Multimodal Emotion Recognition Using Multimodal Deep Learning
To enhance the performance of affective models and reduce the cost of acquiring physiological signals for real-world applications, we adopt multimodal deep learning approach to construct affective models from multiple physiological signals.
Learning Binary Codes and Binary Weights for Efficient Classification
The optimization alternatively proceeds over the binary classifiers and image hash codes.
Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization
In this paper we study stochastic quasi-Newton methods for nonconvex stochastic optimization, where we assume that noisy information about the gradients of the objective function is available via a stochastic first-order oracle (SFO).
Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction
By noting that sparse SVMs induce sparsities in both feature and sample spaces, we propose a novel approach, which is based on accurate estimations of the primal and dual optima of sparse SVMs, to simultaneously identify the inactive features and samples that are guaranteed to be irrelevant to the outputs.
Fast Single Shot Detection and Pose Estimation
For applications in navigation and robotics, estimating the 3D pose of objects is as important as detection.
SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning
Existing visual attention models are generally spatial, i. e., the attention is modeled as spatial probabilities that re-weight the last conv-layer feature map of a CNN encoding an input image.
Geometric descent method for convex composite minimization
In this paper, we extend the geometric descent method recently proposed by Bubeck, Lee and Singh to tackle nonsmooth and strongly convex composite problems.
DSSD : Deconvolutional Single Shot Detector
The main contribution of this paper is an approach for introducing additional context into state-of-the-art general object detection.
Joint Intermodal and Intramodal Label Transfers for Extremely Rare or Unseen Classes
One of our goals in this paper is to develop a model for revealing the functional relationships between text and image features as to directly transfer intermodal and intramodal labels to annotate the images.
Robust Guided Image Filtering
In this paper, we propose a general framework for Robust Guided Image Filtering (RGIF), which contains a data term and a smoothness term, to solve the two issues mentioned above.
Deep Self-Taught Learning for Weakly Supervised Object Localization
To overcome this issue, we propose a deep self-taught learning approach, which makes the detector learn the object-level features reliable for acquiring tight positive samples and afterwards re-train itself based on them.
End-to-end Active Object Tracking via Reinforcement Learning
We study active object tracking, where a tracker takes as input the visual observation (i. e., frame sequence) and produces the camera control signal (e. g., move forward, turn left, etc.).
Real-Time Neural Style Transfer for Videos
More specifically, a hybrid loss is proposed to capitalize on the content information of input frames, the style information of a given style image, and the temporal information of consecutive frames.
Diverse Image Annotation
To this end, we treat the image annotation as a subset selection problem based on the conditional determinantal point process (DPP) model, which formulates the representation and diversity jointly.
GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization
In addition, we develop a new technique to establish the global convergence of the GSOS algorithm.
Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization
In this work, we prove that under certain suitable assumptions, we can recover both the low-rank and the sparse components exactly by simply solving a convex program whose objective is a weighted combination of the tensor nuclear norm and the $\ell_1$-norm, i. e., $\min_{{\mathcal{L}},\ {\mathcal{E}}} \ \|{{\mathcal{L}}}\|_*+\lambda\|{{\mathcal{E}}}\|_1, \ \text{s. t.}
Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks
The first stage generates videos of realistic contents for each frame.
Learning of Colors from Color Names: Distribution and Point Estimation
Color names are often made up of multiple words.
Detecting Faces Using Inside Cascaded Contextual CNN
Deep Convolutional Neural Networks (CNNs) achieve substantial improvements in face detection in the wild.
Performance optimizations for scalable CFD applications on hybrid CPU+MIC heterogeneous computing system with millions of cores
For computational fluid dynamics (CFD) applications with a large number of grid points/cells, parallel computing is a common efficient strategy to reduce the computational time.
Performance
Dual Skipping Networks
Inspired by the recent neuroscience studies on the left-right asymmetry of the human brain in processing low and high spatial frequency information, this paper introduces a dual skipping network which carries out coarse-to-fine object categorization.
Stochastic Non-convex Ordinal Embedding with Stabilized Barzilai-Borwein Step Size
Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years.
Frustum PointNets for 3D Object Detection from RGB-D Data
In this work, we study 3D object detection from RGB-D data in both indoor and outdoor scenes.
Ranked #1 on
Object Localization
on KITTI Pedestrians Easy
Mixture-Rank Matrix Approximation for Collaborative Filtering
However, our studies show that submatrices with different ranks could coexist in the same user-item rating matrix, so that approximations with fixed ranks cannot perfectly describe the internal structures of the rating matrix, therefore leading to inferior recommendation accuracy.
Ranked #4 on
Recommendation Systems
on MovieLens 10M
Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks
We propose a novel framework called Semantics-Preserving Adversarial Embedding Network (SP-AEN) for zero-shot visual recognition (ZSL), where test images and their classes are both unseen during training.
A Bidirectional Adaptive Bandwidth Mean Shift Strategy for Clustering
The bandwidth of a kernel function is a crucial parameter in the mean shift algorithm.
Experimentally detecting a quantum change point via Bayesian inference
Detecting a change point is a crucial task in statistics that has been recently extended to the quantum realm.
NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction
In this paper, we propose a novel Convolutional Neural Network (CNN) structure for general-purpose multi-task learning (MTL), which enables automatic feature fusing at every layer from different tasks.
Ranked #88 on
Semantic Segmentation
on NYU Depth v2
CosFace: Large Margin Cosine Loss for Deep Face Recognition
The central task of face recognition, including face verification and identification, involves face feature discrimination.
Ranked #3 on
Face Verification
on YouTube Faces DB
An Incremental Path-Following Splitting Method for Linearly Constrained Nonconvex Nonsmooth Programs
The stationary point of Problem 2 is NOT the stationary point of Problem 1.
Salient Object Detection by Lossless Feature Reflection
Inspired by the intrinsic reflection of natural images, in this paper we propose a novel feature learning framework for large-scale salient object detection.
Non-rigid Object Tracking via Deep Multi-scale Spatial-temporal Discriminative Saliency Maps
Extensive experiments demonstrate that the proposed algorithm achieves competitive performance in both saliency detection and visual tracking, especially outperforming other related trackers on the non-rigid object tracking datasets.
Neural Stereoscopic Image Style Transfer
While each view of the stereoscopic pair is processed in an individual path, a novel feature aggregation strategy is proposed to effectively share information between the two paths.
CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF
With temporal dependencies established by optical flow, the resulting MRF model combines both spatial and temporal cues for tackling video object segmentation.
Ranked #3 on
Semi-Supervised Video Object Segmentation
on YouTube
Adversarial Spatio-Temporal Learning for Video Deblurring
To tackle the second challenge, we leverage the developed DBLRNet as a generator in the GAN (generative adversarial network) architecture, and employ a content loss in addition to an adversarial loss for efficient adversarial training.
Reconstruction Network for Video Captioning
Unlike previous video captioning work mainly exploiting the cues of video contents to make a language description, we propose a reconstruction network (RecNet) with a novel encoder-decoder-reconstructor architecture, which leverages both the forward (video to sentence) and backward (sentence to video) flows for video captioning.
Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present
Recently, caption generation with an encoder-decoder framework has been extensively studied and applied in different domains, such as image captioning, code captioning, and so on.
Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning
We propose a bidirectional proposal method that effectively exploits both past and future contexts to make proposal predictions.
Multi-label Learning with Missing Labels using Mixed Dependency Graphs
This work focuses on the problem of multi-label learning with missing labels (MLML), which aims to label each test instance with multiple class labels given training instances that have an incomplete/partial set of these labels.
Tagging like Humans: Diverse and Distinct Image Annotation
In D2IA, we generate a relevant and distinct tag subset, in which the tags are relevant to the image contents and semantically distinct to each other, using sequential sampling from a determinantal point process (DPP) model.
Gated Fusion Network for Single Image Dehazing
The proposed algorithm hinges on an end-to-end trainable neural network that consists of an encoder and a decoder.
Ranked #23 on
Image Dehazing
on SOTS Outdoor
Left-Right Comparative Recurrent Model for Stereo Matching
Left-right consistency check is an effective way to enhance the disparity estimation by referring to the information from the opposite view.
Learning to Guide Decoding for Image Captioning
Recently, much advance has been made in image captioning, and an encoder-decoder framework has achieved outstanding performance for this task.
Fine-grained Video Attractiveness Prediction Using Multimodal Deep Learning on a Large Real-world Dataset
First, we demonstrate that video attractiveness and different engagements present different relationships.
Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval
In addition, we harness a self-supervised semantic network to discover high-level semantic information in the form of multi-label annotations.
Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
We propose an end-to-end deep learning architecture that produces a 3D shape in triangular mesh from a single color image.
Ranked #3 on
3D Object Reconstruction
on Data3D−R2N2
(Avg F1 metric)
Tensor Robust Principal Component Analysis with A New Tensor Nuclear Norm
Equipped with the new tensor nuclear norm, we then solve the TRPCA problem by solving a convex program and provide the theoretical guarantee for the exact recovery.
Neural Compatibility Modeling with Attentive Knowledge Distillation
Nevertheless, existing studies overlook the rich valuable knowledge (rules) accumulated in fashion domain, especially the rules regarding clothing matching.
Char-Net: A Character-Aware Neural Network for Distorted Scene Text Recognition
Unlike previous work which employed a global spatial transformer network to rectify the entire distorted text image, we take an approach of detecting and rectifying individual characters.
Semantic Structure-based Unsupervised Deep Hashing
Hashing is becoming increasingly popular for approximate nearest neighbor searching in massive databases due to its storage and search efficiency.
Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamic
Human motion prediction aims at generating future frames of human motion based on an observed sequence of skeletons.
A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization
In this paper, we propose a deep learning approach to tackle the automatic summarization tasks by incorporating topic information into the convolutional sequence-to-sequence (ConvS2S) model and using self-critical sequence training (SCST) for optimization.
Ranked #6 on
Text Summarization
on DUC 2004 Task 1
An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method
Specifically, we find that a large class of primal and primal-dual operator splitting algorithms are all special cases of VMOR-HPE.
Safe Element Screening for Submodular Function Minimization
Relying on this study, we subsequently propose a novel safe screening method to quickly identify the elements guaranteed to be included (we refer to them as active) or excluded (inactive) in the final optimal solution of SFM during the optimization process.
Unsupervised Learning for Large-Scale Fiber Detection and Tracking in Microscopic Material Images
Constructing 3D structures from serial section data is a long standing problem in microscopy.
Video Description: A Survey of Methods, Datasets and Evaluation Metrics
Video description is the automatic generation of natural language sentences that describe the contents of a given video.
Hierarchical Attention-Based Recurrent Highway Networks for Time Series Prediction
Time series prediction has been studied in a variety of domains.
Nonlocal Neural Networks, Nonlocal Diffusion and Nonlocal Modeling
Nonlocal neural networks have been proposed and shown to be effective in several computer vision tasks, where the nonlocal operations can directly capture long-range dependencies in the feature space.
NovelPerspective: Identifying Point of View Characters
Our tool detects the main character that each section is from the POV of, and allows the user to generate a new ebook with only those sections.
Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks
Recent studies on unsupervised image-to-image translation have made a remarkable progress by training a pair of generative adversarial networks with a cycle-consistent loss.
Recurrent Fusion Network for Image Captioning
In this paper, in order to exploit the complementary information from multiple encoders, we propose a novel Recurrent Fusion Network (RFNet) for tackling image captioning.
Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm
In this work, we study the 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary.
DataDeps.jl: Repeatable Data Setup for Replicable Data Science
We present DataDeps. jl: a julia package for the reproducible handling of static datasets to enhance the repeatability of scripts used in the data and computational sciences.
Software Engineering
Video Re-localization
We first exploit and reorganize the videos in ActivityNet to form a new dataset for video re-localization research, which consists of about 10, 000 videos of diverse visual appearances associated with localized boundary information.
STTM: A Tool for Short Text Topic Modeling
Along with the emergence and popularity of social communications on the Internet, topic discovery from short texts becomes fundamental to many applications that require semantic understanding of textual content.
Information Retrieval
End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning
We further propose an environment augmentation technique and a customized reward function, which are crucial for successful training.
A Unified Analysis of AdaGrad with Weighted Aggregation and Momentum Acceleration
Integrating adaptive learning rate and momentum techniques into SGD leads to a large class of efficiently accelerated adaptive stochastic algorithms, such as AdaGrad, RMSProp, Adam, AccAdaGrad, \textit{etc}.
Reconstruction of a Photonic Qubit State with Reinforcement Learning
An experiment is performed to reconstruct an unknown photonic quantum state with a limited amount of copies.
Quantum Physics
Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting
However, current single-stage detectors (e. g. SSD) have not presented competitive accuracy on common pedestrian detection benchmarks.
Ranked #11 on
Pedestrian Detection
on Caltech
(using extra training data)
Contour Knowledge Transfer for Salient Object Detection
Our goal is to overcome this limitation by automatically converting an existing deep contour detection model into a salient object detection model without using any manual salient object masks.
Incremental Multi-graph Matching via Diversity and Randomness based Graph Clustering
In this paper, we present an incremental multi-graph matching approach, which deals with the arriving graph utilizing the previous matching results under the global consistency constraint.
Temporally Coherent Video Harmonization Using Adversarial Networks
Since existing video datasets which have ground-truth foreground masks and optical flows are not sufficiently large, we propose a simple yet efficient method to build up a synthetic dataset supporting supervised training of the proposed adversarial network.
Distilled Wasserstein Learning for Word Embedding and Topic Modeling
When learning the topic model, we leverage a distilled underlying distance matrix to update the topic distributions and smoothly calculate the corresponding optimal transports.
Modeling Varying Camera-IMU Time Offset in Optimization-Based Visual-Inertial Odometry
Our approach is able to handle the rolling-shutter effects and imperfect sensor synchronization in a unified way.
Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition
Extensive experiments conducted on the three public domain face aging datasets (MORPH Album 2, CACD-VS and FG-NET) have shown the effectiveness of the proposed approach and the value of the constructed CAF dataset on AIFR.
Ranked #3 on
Age-Invariant Face Recognition
on MORPH Album2
PocketFlow: An Automated Framework for Compressing and Accelerating Deep Neural Networks
Deep neural networks are widely used in various domains, but the prohibitive computational complexity prevents their deployment on mobile devices.
Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition
In a Co-LSTM unit, each sub-memory unit stores individual motion information, while this Co-LSTM unit selectively integrates and stores inter-related motion information between multiple interacting persons from multiple sub-memory units via the cell gate and co-memory cell, respectively.
Ranked #1 on
Human Interaction Recognition
on UT
Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance
To address the training difficulty, we propose a training algorithm using a tighter approximation to the derivative of the sign function, a magnitude-aware gradient for weight updating, a better initialization method, and a two-step scheme for training a deep network.
Super-Identity Convolutional Neural Network for Face Hallucination
Face hallucination is a generative task to super-resolve the facial image with low resolution while human perception of face heavily relies on identity information.
A Sufficient Condition for Convergences of Adam and RMSProp
Adam and RMSProp are two of the most influential adaptive stochastic algorithms for training deep neural networks, which have been pointed out to be divergent even in the convex setting via a few simple counterexamples.
Unsupervised Image Captioning
Instead of relying on manually labeled image-sentence pairs, our proposed model merely requires an image set, a sentence corpus, and an existing visual concept detector.
Multi-granularity Generator for Temporal Action Proposal
In this paper, we propose a multi-granularity generator (MGG) to perform the temporal action proposal from different granularity perspectives, relying on the video visual features equipped with the position embedding information.
Ranked #2 on
Action Recognition
on THUMOS’14
Generalizing Graph Matching beyond Quadratic Assignment Model
Graph matching has received persistent attention over decades, which can be formulated as a quadratic assignment problem (QAP).
Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation
In this paper, we present a deep convolutional neural network to capture the inherent properties of image degradation, which can handle different kernels and saturated pixels in a unified framework.
Learning to Compose Dynamic Tree Structures for Visual Contexts
We propose to compose dynamic tree structures that place the objects in an image into a visual context, helping visual reasoning tasks such as scene graph generation and visual Q&A.
Ranked #7 on
Panoptic Scene Graph Generation
on PSG Dataset
Real-Time Referring Expression Comprehension by Single-Stage Grounding Network
Experiments on RefCOCO, RefCOCO+, and RefCOCOg datasets demonstrate that our proposed SSG without relying on any region proposals can achieve comparable performance with other advanced models.
Semi-Supervised Learning for Face Sketch Synthesis in the Wild
Instead of supervising the network with ground truth sketches, we first perform patch matching in feature space between the input photo and photos in a small reference set of photo-sketch pairs.
Ranked #1 on
Face Sketch Synthesis
on CUHK
Hierarchical Macro Strategy Model for MOBA Game AI
In this paper, we propose a novel learning-based Hierarchical Macro Strategy model for mastering MOBA games, a sub-genre of RTS games.
SAFE: Scale Aware Feature Encoder for Scene Text Recognition
We propose a novel scale aware feature encoder (SAFE) that is designed specifically for encoding characters with different scales.
Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss
Inspired by the intrinsic reflection of natural images, in this paper we propose a novel feature learning framework for large-scale salient object detection.
End-to-End Single Image Fog Removal using Enhanced Cycle Consistent Adversarial Networks
In addition, we also contribute the first real world nature fog-fogfree image dataset for defogging research.
Fully-Featured Attribute Transfer
Image attribute transfer aims to change an input image to a target one with expected attributes, which has received significant attention in recent years.
Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning
The final representation is projected to a compact space and fed to a language model.
PFLD: A Practical Facial Landmark Detector
Being accurate, efficient, and compact is essential to a facial landmark detector for practical use.
Stacked Semantic-Guided Network for Zero-Shot Sketch-Based Image Retrieval
Previous works mostly focus on a generative approach that takes a highly abstract and sparse sketch as input and then synthesizes the corresponding natural image.
Center and Scale Prediction: Anchor-free Approach for Pedestrian and Face Detection
Like edges, corners, blobs and other feature detectors, the proposed detector scans for feature points all over the image, for which the convolution is naturally suited.
Ranked #8 on
Pedestrian Detection
on Caltech
(using extra training data)
Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics
We conduct extensive experiments with C3D to validate the effectiveness of our proposed approach.
Ranked #47 on
Self-Supervised Action Recognition
on HMDB51
Efficient Decision-based Black-box Adversarial Attacks on Face Recognition
In this paper, we evaluate the robustness of state-of-the-art face recognition models in the decision-based black-box attack setting, where the attackers have no access to the model parameters and gradients, but can only acquire hard-label predictions by sending queries to the target model.
MVF-Net: Multi-View 3D Face Morphable Model Regression
The main ingredient of the view alignment loss is a differentiable dense optical flow estimator that can backpropagate the alignment errors between an input view and a synthetic rendering from another input view, which is projected to the target view through the 3D shape to be inferred.
Decorrelated Adversarial Learning for Age-Invariant Face Recognition
To reduce such a discrepancy, in this paper we propose a novel algorithm to remove age-related components from features mixed with both identity and age information.
Ranked #3 on
Age-Invariant Face Recognition
on CACDVS
Exploring Representativeness and Informativeness for Active Learning
Then can we find a way to fuse the two active sampling criteria without any assumption on data?
Shared Predictive Cross-Modal Deep Quantization
In this paper, we propose a deep quantization approach, which is among the early attempts of leveraging deep neural networks into quantization-based cross-modal similarity search.
MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation
Extensive experiments on challenging datasets demonstrate the effectiveness of the proposed method, especially in the case of object missing.
Deep Spectral Clustering using Dual Autoencoder Network
In this paper, we propose a joint learning framework for discriminative embedding and spectral clustering.
FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
On the basis of the FaceShapeGene, a novel part-wise face image editing system is developed, which contains a shape-remix network and a conditional label-to-face transformer.
DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs
To address this issue, we propose a novel deep unsupervised hashing model, dubbed DistillHash, which can learn a distilled data set consisted of data pairs, which have confidence similarity signals.
Spatio-temporal Video Re-localization by Warp LSTM
The need for efficiently finding the video content a user wants is increasing because of the erupting of user-generated videos on the Web.
Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables
Due to the sequential dependencies among words in a caption, we formulate the generation of adversarial noises for targeted partial captions as a structured output learning problem with latent variables.
Image Deformation Meta-Networks for One-Shot Learning
Humans can robustly learn novel visual concepts even when images undergo various deformations and lose certain information.
Electronic structure and $H$-$T$ phase diagram of Eu(Fe$_{1-x}$Rh$_x$)$_2$As$_2$
The iron-based superconductors represent a promising platform for high-temperature superconductivity, but the interactions underpinning their pairing present a puzzle.
Superconductivity Strongly Correlated Electrons
An Encoding Strategy Based Word-Character LSTM for Chinese NER
A recently proposed lattice model has demonstrated that words in character sequence can provide rich word boundary information for character-based Chinese NER model.
High-Level Semantic Feature Detection: A New Perspective for Pedestrian Detection
Like edges, corners, blobs and other feature detectors, the proposed detector scans for feature points all over the image, for which the convolution is naturally suited.
Understanding Distributional Ambiguity via Non-robust Chance Constraint
Without the boundedness constraint, the CCO problem is shown to perform uniformly better than the DRO problem, irrespective of the radius of the ambiguity set, the choice of the divergence measure, or the tail heaviness of the center distribution.
Reconstruct and Represent Video Contents for Captioning via Reinforcement Learning
Unlike previous video captioning work mainly exploiting the cues of video contents to make a language description, we propose a reconstruction network (RecNet) in a novel encoder-decoder-reconstructor architecture, which leverages both forward (video to sentence) and backward (sentence to video) flows for video captioning.
Global injectivity of differentiable maps via W-condition in R^2
In this paper, we study the intrinsic relation between the global injectivity of differentiable local homeomorphisms $F$ and the rate that tends to zero of $Spec(F)$ in $\mathbb{R}^2$, where $Spec(F)$ denotes the set of all (complex) eigenvalues of $DF(x)$, for all $x\in \mathbb{R}^2$.
Functional Analysis Operator Algebras 14R15, 14E07, 14E09
A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing
In this paper, a non-convex non-smooth optimization framework is proposed to achieve diverse smoothing natures where even contradictive smoothing behaviors can be achieved.
Central Similarity Quantization for Efficient Image and Video Retrieval
In this work, we propose a new \emph{global} similarity metric, termed as \emph{central similarity}, with which the hash codes of similar data pairs are encouraged to approach a common center and those for dissimilar pairs to converge to different centers, to improve hash learning efficiency and retrieval accuracy.
Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion
To address these issues, in this work we propose a novel deep learning framework, named Cascaded Context Pyramid Network (CCPNet), to jointly infer the occupancy and semantic labels of a volumetric 3D scene from a single depth image.
Ranked #5 on
3D Semantic Scene Completion
on NYUv2
(using extra training data)
Multi-Frame Content Integration with a Spatio-Temporal Attention Mechanism for Person Video Motion Transfer
Specifically, we transfer the motion of one person in a target video to another person in a source video, while preserving the appearance of the source person.
Multimodal Emotion Recognition Using Deep Canonical Correlation Analysis
We evaluate the performance of DCCA on five multimodal datasets: the SEED, SEED-IV, SEED-V, DEAP, and DREAMER datasets.
Occlusion Robust Face Recognition Based on Mask Learning with PairwiseDifferential Siamese Network
Deep Convolutional Neural Networks (CNNs) have been pushing the frontier of the face recognition research in the past years.
From Text to Sound: A Preliminary Study on Retrieving Sound Effects to Radio Stories
In this paper, we address the problem of automatically adding sound effects to radio stories with a retrieval-based model.
Controllable Video Captioning with POS Sequence Guidance Based on Gated Fusion Network
In this paper, we propose to guide the video caption generation with Part-of-Speech (POS) information, based on a gated fusion of multiple representations of input videos.
DV3+HED+: A DCNNs-based Framework to Monitor Temporary Works and ESAs in Railway Construction Project Using VHR Satellite Images
Current VHR(Very High Resolution) satellite images enable the detailed monitoring of the earth and can capture the ongoing works of railway construction.
Multi-lingual Wikipedia Summarization and Title Generation On Low Resource Corpus
MultiLing 2019 Headline Generation Task on Wikipedia Corpus raised a critical and practical problem: multilingual task on low resource corpus.
ICDM 2019 Knowledge Graph Contest: Team UWA
We present an overview of our triple extraction system for the ICDM 2019 Knowledge Graph Contest.
Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning
Most existing text reading benchmarks make it difficult to evaluate the performance of more advanced deep learning models in large vocabularies due to the limited amount of training data.
In Conclusion Not Repetition: Comprehensive Abstractive Summarization With Diversified Attention Based On Determinantal Point Processes
Various Seq2Seq learning models designed for machine translation were applied for abstractive summarization task recently.
Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Prediction
To this end, we propose a novel Skeleton-joint Co-attention Recurrent Neural Networks (SC-RNN) to capture the spatial coherence among joints, and the temporal evolution among skeletons simultaneously on a skeleton-joint co-attention feature map in spatiotemporal space.
Accelerating Federated Learning via Momentum Gradient Descent
The proposed momentum federated learning (MFL) uses momentum gradient descent (MGD) in the local update step of FL system.
Deep Multiphase Level Set for Scene Parsing
The proposed method consists of three modules, i. e., recurrent FCNs, adaptive multiphase level set, and deeply supervised learning.
Context-Gated Convolution
As such, being aware of the global context, the modulated convolution kernel of our proposed CGC can better extract representative local patterns and compose discriminative features.
Ranked #61 on
Image Classification
on ObjectNet
(using extra training data)
Vatex Video Captioning Challenge 2020: Multi-View Features and Hybrid Reward Strategies for Video Captioning
This report describes our solution for the VATEX Captioning Challenge 2020, which requires generating descriptions for the videos in both English and Chinese languages.
Diversifying Topic-Coherent Response Generation for Natural Multi-turn Conversations
In this paper, we propose the Topic-coherent Hierarchical Recurrent Encoder-Decoder model (THRED) to diversify the generated responses without deviating the contextual topics for multi-turn conversations.
Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
Although there has been a progress in matching the marginal distributions between two domains, the classifier favors the source domain features and makes incorrect predictions on the target domain due to category-agnostic feature alignment.
Ranked #24 on
Image-to-Image Translation
on SYNTHIA-to-Cityscapes
Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos
Temporal sentence grounding in videos aims to detect and localize one target video segment, which semantically corresponds to a given sentence.
Redcoat: A Collaborative Annotation Tool for Hierarchical Entity Typing
We introduce Redcoat, a web-based annotation tool that supports collaborative hierarchical entity typing.
Word-level Lexical Normalisation using Context-Dependent Embeddings
In this paper we introduce a word-level GRU-based LN model and investigate the effectiveness of recent embedding techniques on word-level LN.
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
By incorporating DIoU and CIoU losses into state-of-the-art object detection algorithms, e. g., YOLO v3, SSD and Faster RCNN, we achieve notable performance gains in terms of not only IoU metric but also GIoU metric.
Empirical Autopsy of Deep Video Captioning Frameworks
We perform extensive experiments by varying the constituent components of the video captioning framework, and quantify the performance gains that are possible by mere component selection.
Multi-Task Driven Feature Models for Thermal Infrared Tracking
These two feature models are learned using a multi-task matching framework and are jointly optimized on the TIR tracking task.
PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds
We propose a novel end-to-end deep scene flow model, called PointPWC-Net, on 3D point clouds in a coarse-to-fine fashion.
Learning Multi-level Weight-centric Features for Few-shot Learning
Few-shot learning is currently enjoying a considerable resurgence of interest, aided by the recent advance of deep learning.
Cross-Modal Learning with Adversarial Samples
Extensive experiments on two cross-modal benchmark datasets show that the adversarial examples produced by our CMLA are efficient in fooling a target deep cross-modal hashing network.
Fast Stochastic Ordinal Embedding with Variance Reduction and Adaptive Step Size
Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years.
Potential Passenger Flow Prediction: A Novel Study for Urban Transportation Development
In this paper, this specific problem is termed as potential passenger flow (PPF) prediction, which is a novel and important study connected with urban computing and intelligent transportation systems.
Graph Inference Learning for Semi-supervised Classification
In this work, we address semi-supervised classification of graph data, where the categories of those unlabeled nodes are inferred from labeled nodes as well as graph structures.
Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization
In this paper, we bridge this gap by providing a sharp analysis of epoch-wise stochastic gradient descent ascent method (referred to as Epoch-GDA) for solving strongly convex strongly concave (SCSC) min-max problems, without imposing any additional assumption about smoothness or the function's structure.
Adversarial Perturbations Prevail in the Y-Channel of the YCbCr Color Space
Our results show that our approach achieves the best balance between defence against adversarial attacks such as FGSM, PGD and DDN and maintaining the original accuracies of VGG-16, ResNet50 and DenseNet121 on clean images.
An Improved DOA Estimation Method for a Mixture of Circular and Non-Circular Signals Based on Sparse Arrays
Sparse arrays have attracted a lot of interests recently for their capability of providing more degrees of freedom than traditional uniform linear arrays.
Towards Photo-Realistic Virtual Try-On by Adaptively Generating$\leftrightarrow$Preserving Image Content
First, a semantic layout generation module utilizes semantic segmentation of the reference image to progressively predict the desired semantic layout after try-on.
Ranked #4 on
Virtual Try-on
on VITON
(IS metric)
E2EET: From Pipeline to End-to-end Entity Typing via Transformer-Based Embeddings
They are therefore sensitive to window size selection and are unable to incorporate the context of the entire document.
MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning
We propose to incorporate neural architecture search (NAS) into general-purpose multi-task learning (GP-MTL).
Progressive Multi-Stage Learning for Discriminative Tracking
Visual tracking is typically solved as a discriminative learning problem that usually requires high-quality samples for online model adaptation.
Deblurring by Realistic Blurring
To address this problem, we propose a new method which combines two GAN models, i. e., a learning-to-Blur GAN (BGAN) and learning-to-DeBlur GAN (DBGAN), in order to learn a better model for image deblurring by primarily learning how to blur images.
Ranked #17 on
Deblurring
on HIDE (trained on GOPRO)
Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation
Furthermore, we propose a simple and effective method to mine the keyphrases of interest in the news article and build a first large-scale keyphrase-aware news headline corpus, which contains over 180K aligned triples of $<$news article, headline, keyphrase$>$.
Knowledge-guided Deep Reinforcement Learning for Interactive Recommendation
Interactive recommendation aims to learn from dynamic interactions between items and users to achieve responsiveness and accuracy.
Quantized Adam with Error Feedback
In this paper, we present a distributed variant of adaptive stochastic gradient method for training deep neural networks in the parameter-server model.
Energy Efficient User Clustering, Hybrid Precoding and Power Optimization in Terahertz MIMO-NOMA Systems
Considering the power consumption and implementation complexity, the hybrid precoding scheme based on the sub-connection structure is adopted.
Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks
In this paper, we study distributed algorithms for large-scale AUC maximization with a deep neural network as a predictive model.
Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation
In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and Non-Maximum Suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency.
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results
This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+.
Hierarchical Regression Network for Spectral Reconstruction from RGB Images
Hyperspectral reconstruction from RGB images denotes a reverse process of hyperspectral imaging by discovering an inverse response function.
Ranked #10 on
Spectral Reconstruction
on ARAD-1K
CPOT: Channel Pruning via Optimal Transport
Recent advances in deep neural networks (DNNs) lead to tremendously growing network parameters, making the deployments of DNNs on platforms with limited resources extremely difficult.
TCDesc: Learning Topology Consistent Descriptors
Then we define topology distance between descriptors as the difference of their topology vectors.
DFraud3- Multi-Component Fraud Detection freeof Cold-start
In this research, instead of focusing only on one component, detecting either fraud reviews or fraud users (fraudsters), vector representations are learnt for each component, enabling multi-component classification.
ScoreGAN: A Fraud Review Detector based on Multi Task Learning of Regulated GAN with Data Augmentation
However, the lack of trusted labeled data has limited the performance of the current solutions in detecting fraud reviews.
Real-time Universal Style Transfer on High-resolution Images via Zero-channel Pruning
Extracting effective deep features to represent content and style information is the key to universal style transfer.
