Search Results for author:
Found 267 papers, 69 papers with code
Learning a discriminative hidden part model for human action recognition
In particular, our experimental results demonstrate that combining large-scale global features and local patch features performs significantly better than directly applying hCRF on local patches alone.
A Rate Distortion Approach for Semi-Supervised Conditional Random Fields
We propose a novel information theoretic approach for semi-supervised learning of conditional random fields.
Beyond Actions: Discriminative Models for Contextual Group Activities
We propose a discriminative model for recognizing group activities.
A Discriminative Latent Model of Image Region and Object Tag Correspondence
In particular, we model the mapping that translates image regions to annotations.
Kernel Latent SVM for Visual Recognition
Latent SVMs (LSVMs) are a class of powerful tools that have been successfully applied to many applications in computer vision.
Non-parametric Filtering for Geometric Detail Extraction and Material Representation
Geometric detail is a universal phenomenon in real world objects.
Invertibility and Robustness of Phaseless Reconstruction
This paper is concerned with the question of reconstructing a vector in a finite-dimensional real Hilbert space when only the magnitudes of the coefficients of the vector under a redundant linear map are known.
Stable Learning in Coding Space for Multi-Class Decoding and Its Extension for Multi-Class Hypothesis Transfer Learning
Many prevalent multi-class classification approaches can be unified and generalized by the output coding framework which usually consists of three phases: (1) coding, (2) learning binary classifiers, and (3) decoding.
Multiple Authors Detection: A Quantitative Analysis of Dream of the Red Chamber
Inspired by the authorship controversy of Dream of the Red Chamber and the application of machine learning in the study of literary stylometry, we develop a rigorous new method for the mathematical analysis of authorship by testing for a so-called chrono-divide in writing styles.
A new approach for physiological time series
We developed a new approach for the analysis of physiological time series.
Weakly Supervised Localization of Novel Objects Using Appearance Transfer
We propose a method for transferring the appearance models of the familiar objects to the unseen object.
rnn : Recurrent Library for Torch
The rnn package provides components for implementing a wide range of Recurrent Neural Networks.
Improving Human Action Recognition by Non-action Classification
In this paper we consider the task of recognizing human actions in realistic video where human actions are dominated by irrelevant factors.
Stochastic Patching Process
Due to constraints of partition strategy, existing models may cause unnecessary dissections in sparse regions when fitting data in dense regions.
Iterative Views Agreement: An Iterative Low-Rank based Structured Optimization Method to Multi-View Spectral Clustering
Multi-view spectral clustering, which aims at yielding an agreement or consensus data objects grouping across multi-views with their graph laplacian matrices, is a fundamental clustering problem.
PrivLogit: Efficient Privacy-preserving Logistic Regression by Tailoring Numerical Optimizers
Leveraging this new method, we propose two new secure protocols for conducting logistic regression in a privacy-preserving and distributed manner.
Robust Hashing for Multi-View Data: Jointly Learning Low-Rank Kernelized Similarity Consensus and Hash Functions
To learn robust hash functions, a latent low-rank kernel function is used to construct hash functions in order to accommodate linearly inseparable data.
Infinite Hidden Semi-Markov Modulated Interaction Point Process
The proposed approach can simultaneously model both the observations and arrival times of temporal events, and determine the number of latent states from data.
Personalized Video Recommendation Using Rich Contents from Videos
In the existing video recommender systems, the models make the recommendations based on the user-video interactions and single specific content features.
MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification
With the development of deep learning, supervised learning has frequently been adopted to classify remotely sensed images using convolutional networks (CNNs).
Effective Multi-Query Expansions: Collaborative Deep Networks for Robust Landmark Retrieval
Given a query photo issued by a user (q-user), the landmark retrieval is to return a set of photos with their landmarks similar to those of the query, while the existing studies on the landmark retrieval focus on exploiting geometries of landmarks for similarity matches between candidate photos and a query photo.
Structured Deep Hashing with Convolutional Neural Networks for Fast Person Re-identification
Given a pedestrian image as a query, the purpose of person re-identification is to identify the correct match from a large collection of gallery images depicting the same person captured by disjoint camera views.
Evolution-Preserving Dense Trajectory Descriptors
Recently Trajectory-pooled Deep-learning Descriptors were shown to achieve state-of-the-art human action recognition results on a number of datasets.
Label Refinement Network for Coarse-to-Fine Semantic Segmentation
We propose a novel network architecture called the label refinement network that predicts segmentation labels in a coarse-to-fine fashion at several resolutions.
The SUMMA Platform Prototype
We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Finding Modes by Probabilistic Hypergraphs Shifting
Unlike the existing techniques to seek graph modes by shifting vertices based on pair-wise edges (i. e, an edge with $2$ ends), our paradigm is based on shifting high-order edges (hyperedges) to deliver graph modes.
Call Attention to Rumors: Deep Attention Based Recurrent Neural Networks for Early Rumor Detection
The proposed model delves soft-attention into the recurrence to simultaneously pool out distinct features with particular focus and produce hidden representations that capture contextual variations of relevant posts over time.
Flexible and Creative Chinese Poetry Generation Using Neural Memory
It has been shown that Chinese poems can be successfully generated by sequence-to-sequence neural models, particularly with the attention mechanism.
Unsupervised Learning Layers for Video Analysis
This paper presents two unsupervised learning layers (UL layers) for label-free video analysis: one for fully connected layers, and the other for convolutional ones.
Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification
To this end, a novel objective function is proposed to jointly optimize similarity metric learning, local positive mining and robust deep embedding.
Gated Feedback Refinement Network for Dense Image Labeling
Effective integration of local and global contextual information is crucial for dense labeling problems.
What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
To address \emph{what} to match, our deep network emphasizes common local patterns by learning joint representations in a multiplicative way.
Beyond Low-Rank Representations: Orthogonal Clustering Basis Reconstruction with Optimized Graph Structure for Multi-view Spectral Clustering
Low-Rank Representation (LRR) is arguably one of the most powerful paradigms for Multi-view spectral clustering, which elegantly encodes the multi-view local graph/manifold structures into an intrinsic low-rank self-expressive data similarity embedded in high-dimensional space, to yield a better graph partition than their single-view counterparts.
Eigen Evolution Pooling for Human Action Recognition
We introduce Eigen Evolution Pooling, an efficient method to aggregate a sequence of feature vectors.
Multi-View Spectral Clustering via Structured Low-Rank Matrix Factorization
However, as we observed, such classical paradigm still suffers from (1) overlooking the flexible local manifold structure, caused by (2) enforcing the low-rank data correlation agreement among all views; worse still, (3) LRR is not intuitively flexible to capture the latent data clustering structures.
Where to Focus: Deep Attention-based Spatially Recurrent Bilinear Networks for Fine-Grained Visual Recognition
Given an image, two different Convolutional Neural Networks (CNNs) are constructed, where the outputs of two CNNs are correlated through bilinear pooling to simultaneously focus on discriminative regions and extract relevant features.
When Point Process Meets RNNs: Predicting Fine-Grained User Interests with Mutual Behavioral Infectivity
Inspired by point process in modeling temporal point process, in this paper we present a deep prediction method based on two recurrent neural networks (RNNs) to jointly model each user's continuous browsing history and asynchronous event sequences in the context of inter-user behavioral mutual infectivity.
Occlusion Aware Unsupervised Learning of Optical Flow
Especially on KITTI dataset where abundant unlabeled samples exist, our unsupervised method outperforms its counterpart trained with supervised learning.
Crossing Generative Adversarial Networks for Cross-View Person Re-identification
Given a pair of person images, the proposed model consists of the variational auto-encoder to encode the pair into respective latent variables, a proposed cross-view alignment to reduce the view disparity, and an adversarial layer to seek the joint distribution of latent representations.
Cross-Modal Person Re-Identification
Generative Adversarial Network
Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images
Specifically, we propose to randomly shuffle the pixels in the origin images and leverage the shuffled image as input to make CNN more concerned with the statistical properties.
Learning Semantic Segmentation with Diverse Supervision
Models based on deep convolutional neural networks (CNN) have significantly improved the performance of semantic segmentation.
LEGO: Learning Edge with Geometry all at Once by Watching Videos
In our framework, the predicted depths, normals and edges are forced to be consistent all the time.
BigDL: A Distributed Deep Learning Framework for Big Data
This paper presents BigDL (a distributed deep learning framework for Apache Spark), which has been used by a variety of users in the industry for building deep learning applications on production big data platforms.
Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval
In this paper, we propose a novel deep generative approach to cross-modal retrieval to learn hash functions in the absence of paired training samples through the cycle consistency loss.
Deep Co-attention based Comparators For Relative Representation Learning in Person Re-identification
Recent effective methods are developed in a pair-wise similarity learning system to detect a fixed set of features from distinct regions which are mapped to their vector embeddings for the distance measuring.
OMG - Emotion Challenge Solution
This short paper describes our solution to the 2018 IEEE World Congress on Computational Intelligence One-Minute Gradual-Emotional Behavior Challenge, whose goal was to estimate continuous arousal and valence values from short videos.
Video Summarization Using Fully Convolutional Sequence Networks
This paper addresses the problem of video summarization.
Video Summarization by Learning from Unpaired Data
Our model aims to learn a mapping function $F : V \rightarrow S$ such that the distribution of resultant summary videos from $F(V)$ is similar to the distribution of $S$ with the help of an adversarial objective.
Pulling Actions out of Context: Explicit Separation for Effective Combination
The ability to recognize human actions in video has many potential applications.
Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding
The four types of information, i. e. 2D flow, camera pose, segment mask and depth maps, are integrated into a differentiable holistic 3D motion parser (HMP), where per-pixel 3D motion for rigid background and moving objects are recovered.
Gated Feedback Refinement Network for Coarse-to-Fine Dense Semantic Image Labeling
In order to address this issue, we also propose Gated Feedback Refinement Network (G-FRNet) that addresses this limitation.
Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models
We present Manifold, a framework that utilizes visual analysis techniques to support interpretation, debugging, and comparison of machine learning models in a more transparent and interactive manner.
Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification
Video-based person re-identification (re-id) is a central application in surveillance systems with significant concern in security.
Unbiased LambdaMART: An Unbiased Pairwise Learning-to-Rank Algorithm
Although click data is widely used in search systems in practice, so far the inherent bias, most notably position bias, has prevented it from being used in training of a ranker for search, i. e., learning-to-rank.
Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo Videos
Then the whole scene is decomposed into moving foreground and static background by compar- ing the estimated optical flow and rigid flow derived from the depth and ego-motion.
Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding
Performance on the five tasks of depth estimation, optical flow estimation, odometry, moving object segmentation and scene flow estimation shows that our approach outperforms other SoTA methods.
Data-Driven Tight Frame for Cryo-EM Image Denoising and Conformational Classification
We introduce the use of data-driven tight frame (DDTF) algorithm for cryo-EM image denoising.
Computation Image and Video Processing
Perceptual Visual Interactive Learning
Supervised learning methods are widely used in machine learning.
Video-based Person Re-identification Using Spatial-Temporal Attention Networks
The goal is to identify a person from videos captured under different cameras.
Spelling Error Correction Using a Nested RNN Model and Pseudo Training Data
We propose a nested recurrent neural network (nested RNN) model for English spelling error correction and generate pseudo data based on phonetic similarity to train it.
Multi-view Laplacian Eigenmaps Based on Bag-of-Neighbors For RGBD Human Emotion Recognition
As RGB view and depth view lie in different spaces, a new distance metric bag of neighbors (BON) used in MvLE can get the similar distributions of the two views.
3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification
In this paper, we introduce a global video representation to video-based person re-identification (re-ID) that aggregates local 3D features across the entire video extent.
A Remote Sensing Image Dataset for Cloud Removal
Removing clouds is an indispensable pre-processing step in remote sensing image analysis.
GIF2Video: Color Dequantization and Temporal Interpolation of GIF images
In this paper, we propose GIF2Video, the first learning-based method for enhancing the visual quality of GIFs in the wild.
Deep Generative Learning via Variational Gradient Flow
We propose a general framework to learn deep generative models via \textbf{V}ariational \textbf{Gr}adient Fl\textbf{ow} (VGrow) on probability spaces.
Deep Discriminative Representation Learning with Attention Map for Scene Classification
However, most recent approaches to remote sensing scene classification are based on Convolutional Neural Networks (CNNs).
Wasserstein-Wasserstein Auto-Encoders
To address the challenges in learning deep generative models (e. g., the blurriness of variational auto-encoder and the instability of training generative adversarial networks, we propose a novel deep generative model, named Wasserstein-Wasserstein auto-encoders (WWAE).
Crowd Counting Using Scale-Aware Attention Networks
In this paper, we consider the problem of crowd counting in images.
Few-Shot Deep Adversarial Learning for Video-based Person Re-identification
Video-based person re-identification (re-ID) refers to matching people across camera views from arbitrary unaligned video footages.
Cross-Entropy Adversarial View Adaptation for Person Re-identification
The main contribution is to learn coupled asymmetric mappings regarding view characteristics which are adversarially trained to address the view discrepancy by optimising the cross-entropy view confusion objective.
When AWGN-based Denoiser Meets Real Noises
In this paper, we propose a novel approach to boost the performance of a real image denoiser which is trained only with synthetic pixel-independent noise data dominated by AWGN.
Ranked #2 on
Denoising
on Darmstadt Noise Dataset
Convolutional Temporal Attention Model for Video-based Person Re-identification
A common approach for person re-identification is to first extract image features for all frames in the video, then aggregate all the features to form a video-level feature.
Cross-Modal Self-Attention Network for Referring Image Segmentation
This module controls the information flow of features at different levels.
Ranked #14 on
Referring Video Object Segmentation
on Refer-YouTube-VOS
(using extra training data)
Knowledge Distillation for Human Action Anticipation
In this paper, we propose a novel knowledge distillation framework that uses an action recognition network to supervise the training of an action anticipation network, guiding the latter to attend to the relevant information needed for correctly anticipating the future actions.
Contextual Attention for Hand Detection in the Wild
We also conduct ablation studies on hand detection to show the effectiveness of the proposed contextual attention module.
Attentive Action and Context Factorization
This is a challenging task due to the subtlety of human actions in video and the co-occurrence of contextual elements.
Visualizing and Understanding the Semantics of Embedding Spaces via Algebraic Formulae
Embeddings are a fundamental component of many modern machine learning and natural language processing models.
Parallax: Visualizing and Understanding the Semantics of Embedding Spaces via Algebraic Formulae
Embeddings are a fundamental component of many modern machine learning and natural language processing models.
Efficient EM-Variational Inference for Hawkes Process
In classical Hawkes process, the baseline intensity and triggering kernel are assumed to be a constant and parametric function respectively, which limits the model flexibility.
UnOS: Unified Unsupervised Optical-Flow and Stereo-Depth Estimation by Watching Videos
In this paper, we propose UnOS, an unified system for unsupervised optical flow and stereo depth estimation using convolutional neural network (CNN) by taking advantages of their inherent geometrical consistency based on the rigid-scene assumption.
Optimal low rank tensor recovery
We investigate the sample size requirement for exact recovery of a high order tensor of low rank from a subset of its entries.
A Targeted Acceleration and Compression Framework for Low bit Neural Networks
In this paper, we propose a novel Targeted Acceleration and Compression (TAC) framework to improve the performance of 1 bit deep neural networks W e consider that the acceleration and compression effects of binarizing fully connected layer s are not sufficient to compensate for the accuracy loss caused by it In the proposed framework, t he convolutional and fully connected layer are separated and optimized i ndividually .
Learning Structured Twin-Incoherent Twin-Projective Latent Dictionary Pairs for Classification
In this setting, our TP-DPL integrates the twin-incoherence based latent flexible DPL and the joint embedding of codes as well as salient features by twin-projection into a unified model in an adaptive neighborhood-preserving manner.
Adaptive Structure-constrained Robust Latent Low-Rank Coding for Image Recovery
Specifically, AS-LRC performs the latent decomposition of given data into a low-rank reconstruction by a block-diagonal codes matrix, a group sparse locality-adaptive salient feature part and a sparse error part.
Multi-Task Deep Learning with Dynamic Programming for Embryo Early Development Stage Classification from Time-Lapse Videos
Accurate classification of embryo early development stages can provide embryologists valuable information for assessing the embryo quality, and hence is critical to the success of IVF.
A Convolutional Neural Network with Mapping Layers for Hyperspectral Image Classification
In this paper, we propose a convolutional neural network with mapping layers (MCNN) for hyperspectral image (HSI) classification.
Future Frame Prediction Using Convolutional VRNN for Anomaly Detection
Anomaly detection in videos aims at reporting anything that does not conform the normal behaviour or distribution.
Region Mutual Information Loss for Semantic Segmentation
In this paper, we develop a region mutual information (RMI) loss to model the dependencies among pixels more simply and efficiently.
Scalable Inference for Nonparametric Hawkes Process Using Pólya-Gamma Augmentation
In this paper, we consider the sigmoid Gaussian Hawkes process model: the baseline intensity and triggering kernel of Hawkes process are both modeled as the sigmoid transformation of random trajectories drawn from Gaussian processes (GP).
Kernelized Multiview Subspace Analysis by Self-weighted Learning
With the popularity of multimedia technology, information is always represented or transmitted from multiple views.
Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low Light Image Enhancement
Contrast enhancement and noise removal are coupled problems for low-light image enhancement.
Diversifying Inference Path Selection: Moving-Mobile-Network for Landmark Recognition
We intuitively find that M$^2$Net can essentially promote the diversity of the inference path (selected blocks subset) selection, so as to enhance the recognition accuracy.
Learning to Recommend via Meta Parameter Partition
The fixed part, capturing user invariant features, is shared by all users and is learned during offline meta learning stage.
Multilayer Collaborative Low-Rank Coding Network for Robust Deep Subspace Discovery
In this paper, we explore the deep multi-subspace recovery problem by designing a multilayer architecture for latent LRR.
Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition
But existing CNNs based frameworks still have several drawbacks: 1) the traditaional pooling operation may lose important feature information and is unlearnable; 2) the tradi-tional convolution operation optimizes slowly and the hierar-chical features from different layers are not fully utilized.
DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking
However, in practice it is rather common to have no un-paired images in real deraining task, in such cases how to remove the rain streaks in an unsupervised way will be a very challenging task due to lack of constraints between images and hence suffering from low-quality recovery results.
Compressed DenseNet for Lightweight Character Recognition
LDB is a convolutional block similarly as dense block, but it can reduce the computation cost and weight size to (1/L, 2/L), compared with original ones, where L is the number of layers in blocks.
Convolutional Dictionary Pair Learning Network for Image Representation Learning
To address this issue, we propose a novel generalized end-to-end representation learning architecture, dubbed Convolutional Dictionary Pair Learning Network (CDPL-Net) in this paper, which integrates the learning schemes of the CNN and dictionary pair learning into a unified framework.
Learning Hybrid Representation by Robust Dictionary Learning in Factorized Compressed Space
Specifically, J-RFDL performs the robust representation by DL in a factorized compressed space to eliminate the negative effects of noise and outliers on the results, which can also make the DL process efficient.
Unsupervised Learning of Camera Pose with Compositional Re-estimation
We consider the problem of unsupervised camera pose estimation.
Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition
To construct FDRN, we propose a new fast residual dense block (f-RDB) to retain the ability of local feature fusion and local residual learning of original RDB, which can reduce the computing efforts at the same time.
Semi-DerainGAN: A New Semi-supervised Single Image Deraining Network
Although supervised deep deraining networks have obtained impressive results on synthetic datasets, they still cannot obtain satisfactory results on real images due to weak generalization of rain removal capacity, i. e., the pre-trained models usually cannot handle new shapes and directions that may lead to over-derained/under-derained results.
Deep Learning-based Image Compression with Trellis Coded Quantization
Recently many works attempt to develop image compression models based on deep learning architectures, where the uniform scalar quantizer (SQ) is commonly applied to the feature maps between the encoder and decoder.
Dual Convolutional LSTM Network for Referring Image Segmentation
Given an input image and a referring expression in the form of a natural language sentence, the goal is to segment the object of interest in the image referred by the linguistic query.
Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning
We consider the problem of few-shot scene adaptive crowd counting.
RiskOracle: A Minute-level Citywide Traffic Accident Forecasting Framework
Real-time traffic accident forecasting is increasingly important for public safety and urban management (e. g., real-time safe route planning and emergency response deployment).
Convex Shape Representation with Binary Labels for Image Segmentation: Models and Fast Algorithms
We present a novel and effective binary representation for convex shapes.
LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression
BERT is a cutting-edge language representation model pre-trained by a large corpus, which achieves superior performances on various natural language understanding tasks.
SimpleMKKM: Simple Multiple Kernel K-means
We propose a simple yet effective multiple kernel clustering algorithm, termed simple multiple kernel k-means (SimpleMKKM).
Try This Instead: Personalized and Interpretable Substitute Recommendation
Then, by treating attributes as the bridge between users and items, we can thoroughly model the user-item preferences (i. e., personalization) and item-item relationships (i. e., substitution) for recommendation.
Approximation in shift-invariant spaces with deep ReLU neural networks
We also give lower bounds of the $L^p (1\le p \le \infty)$ approximation error for Sobolev spaces, which show that our construction of neural network is asymptotically optimal up to a logarithmic factor.
Ontology-based systematic classification and analysis of coronaviruses, hosts, and host-coronavirus interactions towards deep understanding of COVID-19
We hypothesized that ontology can be used as an integrative platform to classify and analyze HCI and disease outcomes.
Other Quantitative Biology
Deep Degradation Prior for Low-Quality Image Classification
Since the statistical properties are independent to image content, deep degradation prior can be learned on a training set of limited images without supervision of semantic labels and served in a form of "plugging-in" module of the existing classification networks to improve their performance on degraded images.
Utilizing machine learning to prevent water main breaks by understanding pipeline failure drivers
Data61 and Western Water worked collaboratively to apply engineering expertise and Machine Learning tools to find a cost-effective solution to the pipe failure problem in the region west of Melbourne, where on average 400 water main failures occur per year.
Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion
In this paper, we provide a substantial overview of the existing state-of-the-arts on the filed of multi-modal data analytics from shallow to deep spaces.
Automated Radiological Report Generation For Chest X-Rays With Weakly-Supervised End-to-End Deep Learning
The model provides automated recognition of given scans and generation of reports.
Unsupervised Vehicle Re-identification with Progressive Adaptation
For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as ``pseudo target samples''.
Unsupervised Vehicle Re-Identification
Vehicle Re-Identification
Recovering Accurate Labeling Information from Partially Valid Data for Effective Multi-Label Learning
Partial Multi-label Learning (PML) aims to induce the multi-label predictor from datasets with noisy supervision, where each training instance is associated with several candidate labels but only partially valid.
Recurrent Relational Memory Network for Unsupervised Image Captioning
Unsupervised image captioning with no annotations is an emerging challenge in computer vision, where the existing arts usually adopt GAN (Generative Adversarial Networks) models.
Cross-Modal Weighting Network for RGB-D Salient Object Detection
In this paper, we propose a novel Cross-Modal Weighting (CMW) strategy to encourage comprehensive interactions between RGB and depth channels for RGB-D SOD.
Ranked #9 on
RGB-D Salient Object Detection
on NJU2K
Few-shot Scene-adaptive Anomaly Detection
In this paper, we propose a novel few-shot scene-adaptive anomaly detection problem to address the limitations of previous approaches.
Adaptive Video Highlight Detection by Learning from User History
In this paper, we propose a simple yet effective framework that learns to adapt highlight detection to a user by exploiting the user's history in the form of highlights that the user has previously created.
Ontology-based annotation and analysis of COVID-19 phenotypes
The commonly occurring 17 phenotypes were classified into different groups based on the Human Phenotype Ontology (HPO).
Sentence Guided Temporal Modulation for Dynamic Video Thumbnail Generation
We consider the problem of sentence specified dynamic video thumbnail generation.
A Mathematical Introduction to Generative Adversarial Nets (GAN)
This paper attempts to provide an overview of GANs from a mathematical point of view.
Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior
Nonnegative matrix factorization is usually powerful for learning the "shallow" parts-based representation, but it clearly fails to discover deep hierarchical information within both the basis and representation spaces.
Where is the Model Looking At?--Concentrate and Explain the Network Attention
We generate attribute-based textual explanations for the network and ground the attributes on the image to show visual explanations.
High Quality Remote Sensing Image Super-Resolution Using Deep Memory Connected Network
Single image super-resolution is an effective way to enhance the spatial resolution of remote sensing image, which is crucial for many applications such as target detection and image classification.
Deep-HOSeq: Deep Higher Order Sequence Fusion for Multimodal Sentiment Analysis
In this research, we first propose a common network to discover both intra-modal and inter-modal dynamics by utilizing basic LSTMs and tensor based convolution networks.
SmartTriage: A system for personalized patient data capture, documentation generation, and decision support
Symptom checkers have emerged as an important tool for collecting symptoms and diagnosing patients, minimizing the involvement of clinical personnel.
AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting
In particular, we propose a new problem called unlabeled scene-adaptive crowd counting.
Long-Term Pipeline Failure Prediction Using Nonparametric Survival Analysis
We applied Machine Learning techniques to find a cost-effective solution to the pipe failure problem in these Australian cities, where on average 1500 of water main failures occur each year.
A Sequence-to-Sequence Approach to Dialogue State Tracking
This paper is concerned with dialogue state tracking (DST) in a task-oriented dialogue system.
Ranked #1 on
Multi-domain Dialogue State Tracking
on SGD
Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction
The main idea is to use CNNs to learn local appearances of vessels in image crops while using another point-cloud network to learn the global geometry of vessels in the entire image.
Joint Visual and Audio Learning for Video Highlight Detection
In video highlight detection, the goal is to identify the interesting moments within an unedited video.
BiGCN: A Bi-directional Low-Pass Filtering Graph Neural Network
Graph convolutional networks (GCNs) have achieved great success on graph-structured data.
On the capacity of deep generative networks for approximating distributions
Furthermore, it is shown that the approximation error in Wasserstein distance grows at most linearly on the ambient dimension and that the approximation order only depends on the intrinsic dimension of the target distribution.
VSEGAN: Visual Speech Enhancement Generative Adversarial Network
This paper proposes a novel frameworkthat involves visual information for speech enhancement, by in-corporating a Generative Adversarial Network (GAN).
Wasserstein Graph Neural Networks for Graphs with Missing Attributes
In this paper, we propose an innovative node representation learning framework, Wasserstein Graph Neural Network (WGNN), to mitigate the problem.
STUaNet: Understanding uncertainty in spatiotemporal collective human mobility
The high dynamics and heterogeneous interactions in the complicated urban systems have raised the issue of uncertainty quantification in spatiotemporal human mobility, to support critical decision-makings in risk-aware web applications such as urban event prediction where fluctuations are of significant interests.
Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network
In this paper, we propose a cross-modal self-attention (CMSA) module to utilize fine details of individual words and the input image or video, which effectively captures the long-range dependencies between linguistic and visual features.
Ranked #5 on
Referring Expression Segmentation
on J-HMDB
(Precision@0.9 metric)
DynACPD Embedding Algorithm for Prediction Tasks in Dynamic Networks
Classical network embeddings create a low dimensional representation of the learned relationships between features across nodes.
Quaternion Factorization Machines: A Lightweight Solution to Intricate Feature Interaction Modelling
As a well-established approach, factorization machine (FM) is capable of automatically learning high-order interactions among features to make predictions without the need for manual feature engineering.
Dual-side Sparse Tensor Core
We demonstrate the feasibility of our design with minimal changes to the existing production-scale inner-product-based Tensor Core.
An error analysis of generative adversarial networks for learning distributions
This paper studies how well generative adversarial networks (GANs) learn probability distributions from finite samples.
Learning Elastic Embeddings for Customizing On-Device Recommenders
The core idea is to compose elastic embeddings for each item, where an elastic embedding is the concatenation of a set of embedding blocks that are carefully chosen by an automated search function.
Generalized Linear Bandits with Local Differential Privacy
In this paper, we design LDP algorithms for stochastic generalized linear bandits to achieve the same regret bound as in non-privacy settings.
DECORE: Deep Compression with Reinforcement Learning
For a larger dataset like ImageNet with just 30 epochs of training, it can compress the ResNet-50 architecture by 44. 7% and reduce FLOPs by 42. 3%, with just a 0. 69% drop on Top-5 accuracy of the uncompressed model.
Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification
However, data augmentation for graph-based models remains a challenging problem, as graph data is more complex than traditional data, which consists of two features with different properties: graph topology and node attributes.
Deep Generative Learning via Schrödinger Bridge
At the sample level, we derive our Schr\"{o}dinger Bridge algorithm by plugging the drift term estimated by a deep score estimator and a deep density ratio estimator into the Euler-Maruyama method.
PVGNet: A Bottom-Up One-Stage 3D Object Detector With Integrated Multi-Level Features
Quantization-based methods are widely used in LiDAR points 3D object detection for its efficiency in extracting context information.
Test-Time Fast Adaptation for Dynamic Scene Deblurring via Meta-Auxiliary Learning
Therefore, we are able to exploit the internal information at test time via the auxiliary task to enhance the performance of deblurring.
Image Change Captioning by Learning From an Auxiliary Task
Inspired by the success of multi-task learning, we formulate a training scheme that uses an auxiliary task to improve the training of the change captioning network.
Visualizing Graph Neural Networks with CorGIE: Corresponding a Graph to Its Embedding
Graph neural networks (GNNs) are a class of powerful machine learning tools that model node relations for making predictions of nodes or links.
Bias-Tolerant Fair Classification
Therefore, we propose a Bias-TolerantFAirRegularizedLoss (B-FARL), which tries to regain the benefits using data affected by label bias and selection bias.
Data-Driven Constitutive Relation Reveals Scaling Law for Hydrodynamic Transport Coefficients
We further proposed a constitutive relation model based on scaling law and tested it on the calculation of Rayleigh scattering spectra.
Spatio-Temporal Self-Attention Network for Video Saliency Prediction
3D convolutional neural networks have achieved promising results for video tasks in computer vision, including video saliency prediction that is explored in this paper.
NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset
While diverse question answering (QA) datasets have been proposed and contributed significantly to the development of deep learning models for QA tasks, the existing datasets fall short in two aspects.
FedDrop: Trajectory-weighted Dropout for Efficient Federated Learning
Federated learning (FL) enables edge clients to train collaboratively while preserving individual's data privacy.
Graph Information Matters: Understanding Graph Filters from Interaction Probability
We show that the homophily degree of graphs significantly affects the prediction error of graph filters.
Unrestricted Adversarial Attacks on ImageNet Competition
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input.
Non-Asymptotic Error Bounds for Bidirectional GANs
Our results are also applicable to the Wasserstein bidirectional GAN if the target distribution is assumed to have a bounded support.
Self-supervised Spatiotemporal Representation Learning by Exploiting Video Continuity
Recent self-supervised video representation learning methods have found significant success by exploring essential properties of videos, e. g. speed, temporal order, etc.
Experimental quantum advantage with quantum coupon collector
The information transmitted by the proposed game also broke the classical limit.
Multi-Grained Spatio-Temporal Features Perceived Network for Event-Based Lip-Reading
To recognize words from the event data, we propose a novel Multi-grained Spatio-Temporal Features Perceived Network (MSTP) to perceive fine-grained spatio-temporal features from microsecond time-resolved event data.
Contrastive Learning for Unsupervised Video Highlight Detection
Our framework encodes a video into a vector representation by learning to pick video clips that help to distinguish it from other videos via a contrastive objective using dropout noise.
Exposure Normalization and Compensation for Multiple-Exposure Correction
However, the procedures of correcting underexposure and overexposure to normal exposures are much different from each other, leading to large discrepancies for the network in correcting multiple exposures, thus resulting in poor performance.
Dreaming To Prune Image Deraining Networks
It is based on our observation that deep degradation representations can be clustered by degradation characteristics (types of rain) while independent of image content.
MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning
The learning objective of these methods is often hand-engineered and is not directly tied to the objective (i. e. incrementally learning new classes) during testing.
Approximation bounds for norm constrained neural networks with applications to regression and GANs
This paper studies the approximation capacity of ReLU neural networks with norm constraint on the weights.
When Does A Spectral Graph Neural Network Fail in Node Classification?
Although graph filters provide theoretical foundations for model explanations, it is unclear when a spectral GNN will fail.
S-Rocket: Selective Random Convolution Kernels for Time Series Classification
A population-based optimization algorithm evolves the population in order to find a best state vector which minimizes the number of active kernels while maximizing the accuracy of the classifier.
ProgressiveMotionSeg: Mutually Reinforced Framework for Event-Based Motion Segmentation
Dynamic Vision Sensor (DVS) can asynchronously output the events reflecting apparent motion of objects with microsecond resolution, and shows great application potential in monitoring and other fields.
Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison
To this end, the Few-Shot Object Detection (FSOD) has been topical recently, as it mimics the humans' ability of learning to learn, and intelligently transfers the learned generic object knowledge from the common heavy-tailed, to the novel long-tailed object classes.
BigDL 2.0: Seamless Scaling of AI Pipelines from Laptops to Distributed Cluster
To address this challenge, we have open sourced BigDL 2. 0 at https://github. com/intel-analytics/BigDL/ under Apache 2. 0 license (combining the original BigDL and Analytics Zoo projects); using BigDL 2. 0, users can simply build conventional Python notebooks on their laptops (with possible AutoML support), which can then be transparently accelerated on a single node (with up-to 9. 6x speedup in our experiments), and seamlessly scaled out to a large cluster (across several hundreds servers in real-world use cases).
Thinking inside The Box: Learning Hypercube Representations for Group Recommendation
Such user and group preferences are commonly represented as points in the vector space (i. e., embeddings), where multiple user embeddings are compressed into one to facilitate ranking for group-item pairs.
Transformer-Empowered 6G Intelligent Networks: From Massive MIMO Processing to Semantic Communication
It is anticipated that 6G wireless networks will accelerate the convergence of the physical and cyber worlds and enable a paradigm-shift in the way we deploy and exploit communication networks.
On Private Online Convex Optimization: Optimal Algorithms in $\ell_p$-Geometry and High Dimensional Contextual Bandits
To address such a challenge as the online convex optimization with privacy protection, we propose a private variant of online Frank-Wolfe algorithm with recursive gradients for variance reduction to update and reveal the parameters upon each data.
DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection
Since GAD emphasizes the application and the rarity of anomalous samples, enriching the varieties of its datasets is fundamental work.
Improving Visual Speech Enhancement Network by Learning Audio-visual Affinity with Multi-head Attention
The proposed model alleviates these drawbacks by a) applying a model that fuses audio and visual features layer by layer in encoding phase, and that feeds fused audio-visual features to each corresponding decoder layer, and more importantly, b) introducing a 2-stage multi-head cross attention (MHCA) mechanism to infer audio-visual speech enhancement for balancing the fused audio-visual features and eliminating irrelevant features.
GLD-Net: Improving Monaural Speech Enhancement by Learning Global and Local Dependency Features with GLD Block
For monaural speech enhancement, contextual information is important for accurate speech estimation.
Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification
It is a challenging and practical problem since the query images often suffer from resolution degradation due to the different capturing conditions from real-world cameras.
SHREC'22 Track: Sketch-Based 3D Shape Retrieval in the Wild
We define two SBSR tasks and construct two benchmarks consisting of more than 46, 000 CAD models, 1, 700 realistic models, and 145, 000 sketches in total.
Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay
In this paper, we show through empirical results that adopting the data replay is surprisingly favorable.
De-biased Representation Learning for Fairness with Unreliable Labels
In other words, the fair pre-processing methods ignore the discrimination encoded in the labels either during the learning procedure or the evaluation stage.
PECCO: A Profit and Cost-oriented Computation Offloading Scheme in Edge-Cloud Environment with Improved Moth-flame Optimisation
With the fast growing quantity of data generated by smart devices and the exponential surge of processing demand in the Internet of Things (IoT) era, the resource-rich cloud centres have been utilised to tackle these challenges.
Trajectory Tracking Control of the Bionic Joint Actuated by Pneumatic Artificial Muscle Based on Robust Modeling
Then, a hybrid model is established based on the two models (the nonlinear model and the LTI model) and corresponding to it, a cascaded controller is developed, the outer loop of which is an H-infinite controller for the angular position tracking designed by loop-shaping design procedure (LSDP) and the inner loop is a nonlinear controller based on the feedback linearization theory for the PAM driving pressure control.
Instance Image Retrieval by Learning Purely From Within the Dataset
Although achieving promising results, this approach is restricted by two issues: 1) the domain gap between benchmark datasets and the dataset of a given retrieval task; 2) the required auxiliary dataset cannot be readily obtained.
Grasping Core Rules of Time Series through Pure Models
Time series underwent the transition from statistics to deep learning, as did many other machine learning fields.
Towards Learning in Grey Spatiotemporal Systems: A Prophet to Non-consecutive Spatiotemporal Dynamics
To infer region-wise proximity under flexible factor-wise combinations and enable dynamic neighborhood aggregations, we further disentangle compounded influences of exogenous factors on region-wise proximity and learn to aggregate them.
Switchable Online Knowledge Distillation
Instead of focusing on the accuracy gap at test phase by the existing arts, the core idea of SwitOKD is to adaptively calibrate the gap at training phase, namely distillation gap, via a switching strategy between two modes -- expert mode (pause the teacher while keep the student learning) and learning mode (restart the teacher).
Delving Globally into Texture and Structure for Image Inpainting
Our model is orthogonal to the fashionable arts, such as Convolutional Neural Networks (CNNs), Attention and Transformer model, from the perspective of texture and structure information for image inpainting.
Spatio-Temporal Contrastive Learning Enhanced GNNs for Session-based Recommendation
The idea is to supplement the GNN-based main supervised recommendation task with the temporal representation via an auxiliary cross-view contrastive learning mechanism.
Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022
In this work, we present the winning solution for ORBIT Few-Shot Video Object Recognition Challenge 2022.
Hierarchical Few-Shot Object Detection: Problem, Benchmark and Method
In this paper, we propose and solve a new problem called hierarchical few-shot object detection (Hi-FSOD), which aims to detect objects with hierarchical categories in the FSOD paradigm.
Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts
Most existing methods perform training on multiple source domains using a single model, and the same trained model is used on all unseen target domains.
Ranked #22 on
Domain Generalization
on DomainNet
FAQS: Communication-efficient Federate DNN Architecture and Quantization Co-Search for personalized Hardware-aware Preferences
Due to user privacy and regulatory restrictions, federate learning (FL) is proposed as a distributed learning framework for training deep neural networks (DNN) on decentralized data clients.
HQNAS: Auto CNN deployment framework for joint quantization and architecture search
Deep learning applications are being transferred from the cloud to edge with the rapid development of embedded computing systems.
