Search Results for author:
Found 357 papers, 130 papers with code
Locally Aligned Feature Transforms across Views
In this paper, we propose a new approach for matching images observed in different camera views with complex cross-view transforms and apply it to person reidentification.
Exploiting Structure in Weighted Model Counting Approaches to Probabilistic Inference
Previous studies have demonstrated that encoding a Bayesian network into a SAT formula and then performing weighted model counting using a backtracking search algorithm can be an effective method for exact inference.
A Novel Face Recognition Method using Nearest Line Projection
Instead of projecting an image to its nearest image, we try to project it to its nearest line spanned by two different face images.
Real-time Decolorization using Dominant Colors
Decolorization is the process to convert a color image or video to its grayscale version, and it has received great attention in recent years.
DeepReID: Deep Filter Pairing Neural Network for Person Re-Identification
In this paper, we propose a novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter.
Macroblock Classification Method for Video Applications Involving Motions
We demonstrate that this low-computation-complexity method can efficiently catch the characteristics of the frame.
Improved Image Deblurring based on Salient-region Segmentation
Image deblurring techniques play important roles in many image processing applications.
Analytic connectivity of $k$-uniform hypergraphs
In this paper, we study the analytic connectivity of a $k$-uniform hypergraph $H$, denoted by $\alpha(H)$.
Combinatorics 05C65 (Primary), 05C40, 05B05, 26D15 (Secondary)
Bearing fault diagnosis based on spectrum images of vibration signals
Bearing fault diagnosis has been a challenge in the monitoring activities of rotating machinery, and it's receiving more and more attention.
Turing learning: a metric-free approach to inferring behavior and its application to swarms
We present two case studies with swarms of simulated robots and prove that the underlying behaviors cannot be inferred by a metric-based system identification method.
Towards an "In-the-Wild" Emotion Dataset Using a Game-based Framework
To evaluate the dataset, we compared the performance of two deep learning models trained on both GaMo and CIFE.
Recycle deep features for better object detection
Aiming at improving the performance of existing detection algorithms developed for different applications, we propose a region regression-based multi-stage class-agnostic detection pipeline, whereby the existing algorithms are employed for providing the initial detection proposals.
Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering
While question answering (QA) with neural network, i. e. neural QA, has achieved promising results in recent years, lacking of large scale real-word QA dataset is still a challenge for developing and evaluating neural QA system.
CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016
This paper presents the method that underlies our submission to the untrimmed video classification task of ActivityNet Challenge 2016.
A Recursive Framework for Expression Recognition: From Web Images to Deep Models to Game Dataset
In order to increase the expression recognition accuracy, we also fine-tune the CNN model and thus obtain a better CNN facial expression recognition model.
Facial Expression Recognition
Facial Expression Recognition (FER)
Tuning parameter calibration for $\ell_1$-regularized logistic regression
Feature selection is a standard approach to understanding and modeling high-dimensional classification data, but the corresponding statistical methods hinge on tuning parameters that are difficult to calibrate.
Learning and Fusing Multimodal Features from and for Multi-task Facial Computing
We have found that features trained for one task can be used for other related tasks.
Chinese Poetry Generation with Planning based Neural Network
Chinese poetry generation is a very challenging task in natural language processing.
Recurrent Neural Network Language Model Adaptation Derived Document Vector
In many natural language processing (NLP) tasks, a document is commonly modeled as a bag of words using the term frequency-inverse document frequency (TF-IDF) vector.
Exploring Differential Topic Models for Comparative Summarization of Scientific Papers
This paper investigates differential topic models (dTM) for summarizing the differences among document groups.
Abstractive News Summarization based on Event Semantic Link Network
This paper studies the abstractive multi-document summarization for event-oriented news texts through event information extraction and abstract representation.
Fast color transfer from multiple images
Our algorithm is not restricted to one-to-one image color transfer and can make use of more than one target images to transfer the color in different regions in the source image.
EAC-Net: A Region-based Deep Enhancing and Cropping Approach for Facial Action Unit Detection
For the enhancing layers, we designed an attention map based on facial landmark features and applied it to a pretrained neural network to conduct enhanced learning (The E-Net).
Prostate Cancer Diagnosis using Deep Learning with 3D Multiparametric MRI
A novel deep learning architecture (XmasNet) based on convolutional neural networks was developed for the classification of prostate cancer lesions, using the 3D multiparametric MRI data provided by the PROSTATEx challenge.
Derivation of Document Vectors from Adaptation of LSTM Language Model
In many natural language processing (NLP) tasks, a document is commonly modeled as a bag of words using the term frequency-inverse document frequency (TF-IDF) vector.
Action Unit Detection with Region Adaptation, Multi-labeling Learning and Optimal Temporal Fusing
Action Unit (AU) detection becomes essential for facial analysis.
Person Re-Identification by Deep Joint Learning of Multi-Loss Classification
Existing person re-identification (re-id) methods rely mostly on either localised or global feature representation alone.
Ranked #103 on
Person Re-Identification
on Market-1501
WebVision Challenge: Visual Learning and Understanding With Web Data
The 2017 WebVision challenge consists of two tracks, the image classification task on WebVision test set, and the transfer learning task on PASCAL VOC 2012 dataset.
R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
In this paper, we propose a novel method called Rotational Region CNN (R2CNN) for detecting arbitrary-oriented texts in natural scene images.
SAR Target Recognition Using the Multi-aspect-aware Bidirectional LSTM Recurrent Neural Networks
However, there is a limitation in current deep learning based ATR solution that each learning process only handle one SAR image, namely learning the static scattering information, while missing the space-varying information.
WebVision Database: Visual Learning and Understanding from Web Data
Our new WebVision database and relevant studies in this work would benefit the advance of learning state-of-the-art visual models with minimum supervision based on web data.
DeepUNet: A Deep Fully Convolutional Network for Pixel-level Sea-Land Segmentation
Semantic segmentation is a fundamental research in remote sensing image processing.
Hierarchical Gated Recurrent Neural Tensor Network for Answer Triggering
In this paper, we focus on the problem of answer triggering ad-dressed by Yang et al. (2015), which is a critical component for a real-world question answering system.
Attribute Recognition by Joint Recurrent Learning of Context and Correlation
Recognising semantic pedestrian attributes in surveillance images is a challenging task for computer vision, particularly when the imaging quality is poor with complex background clutter and uncontrolled viewing conditions, and the number of labelled training data is small.
Streaming Small-Footprint Keyword Spotting using Sequence-to-Sequence Models
We develop streaming keyword spotting systems using a recurrent neural network transducer (RNN-T) model: an all-neural, end-to-end trained, sequence-to-sequence model which jointly learns acoustic and language model components.
Distributed Representation for Traditional Chinese Medicine Herb via Deep Learning Models
Traditional Chinese Medicine (TCM) has accumulated a big amount of precious resource in the long history of development.
Deep Residual Text Detection Network for Scene Text
Scene text detection is a challenging problem in computer vision.
Training Simplification and Model Simplification for Deep Learning: A Minimal Effort Back Propagation Method
Based on the sparsified gradients, we further simplify the model by eliminating the rows or columns that are seldom updated, which will reduce the computational cost both in the training and decoding, and potentially accelerate decoding in real-world applications.
Appearance-and-Relation Networks for Video Classification
Specifically, SMART blocks decouple the spatiotemporal learning module into an appearance branch for spatial modeling and a relation branch for temporal modeling.
Ranked #51 on
Action Recognition
on UCF101
Generalizing GANs: A Turing Perspective
In this paper we examine how these algorithms relate to the Turing test, and derive what - from a Turing perspective - can be considered their defining features.
Exploration on Generating Traditional Chinese Medicine Prescription from Symptoms with an End-to-End method
Traditional Chinese Medicine (TCM) is an influential form of medical treatment in China and surrounding areas.
Improving Word Vector with Prior Knowledge in Semantic Dictionary
Using low dimensional vector space to represent words has been very effective in many NLP tasks.
Harmonious Attention Network for Person Re-Identification
Existing person re-identification (re-id) methods either assume the availability of well-aligned person bounding box images as model input or rely on constrained attention selection mechanisms to calibrate misaligned images.
Ranked #13 on
Person Re-Identification
on CUHK03 detected
Automatic Translating between Ancient Chinese and Contemporary Chinese with Limited Aligned Corpora
In this paper, we propose to build an end-to-end neural model to automatically translate between ancient and contemporary Chinese.
Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation
The existing sequence-to-sequence model tends to memorize the words and the patterns in the training dataset instead of learning the meaning of the words.
SeqFace: Make full use of sequence information for face recognition
Deep convolutional neural networks (CNNs) have greatly improved the Face Recognition (FR) performance in recent years.
Ranked #1 on
Face Verification
on YouTube Faces DB
Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification
Most existing person re-identification (re-id) methods require supervised model learning from a separate large set of pairwise labelled training data for every single camera pair.
Ranked #22 on
Unsupervised Domain Adaptation
on Market to Duke
Adapting Blockchain Technology for Scientific Computing
Blockchain stores information into a chain of blocks, whose integrity is usually guaranteed by Proof of Work (PoW).
Cryptography and Security Distributed, Parallel, and Cluster Computing
Generative Model for Heterogeneous Inference
However, the learning and inference of BN model are NP-hard thus the number of stochastic variables in BN is highly constrained.
TreeSegNet: Adaptive Tree CNNs for Subdecimeter Aerial Image Segmentation
For the task of subdecimeter aerial imagery segmentation, fine-grained semantic segmentation results are usually difficult to obtain because of complex remote sensing content and optical conditions.
Adversarial adaptive 1-D convolutional neural networks for bearing fault diagnosis under varying working condition
The layers between the source and target feature extractor are partially untied during the training stage to take both training efficiency and domain adaptation into consideration.
Automatic Academic Paper Rating Based on Modularized Hierarchical Convolutional Neural Network
As more and more academic papers are being submitted to conferences and journals, evaluating all these papers by professionals is time-consuming and can cause inequality due to the personal factors of the reviewers.
Stochastic Gradient Descent with Hyperbolic-Tangent Decay on Classification
Learning rate scheduler has been a critical issue in the deep neural network training.
SGM: Sequence Generation Model for Multi-label Classification
Further analysis of experimental results demonstrates that the proposed methods not only capture the correlations between labels, but also select the most informative words automatically when predicting different labels.
A Unified Approximation Framework for Compressing and Accelerating Deep Neural Networks
To address this issue, various approximation techniques have been investigated, which seek for a light weighted network with little performance degradation in exchange of smaller model size or faster inference.
NMT-based Cross-lingual Document Embeddings
This paper further adds a distance constraint to the training objective function of NV so that the two embeddings of a parallel document are required to be as close as possible.
Cross-Lingual Document Classification
Document Classification
+5
Primal Meaning Recommendation via On-line Encyclopedia
We define the primal meaning of an expression to be a frequently used sense of that expression from which its other frequent senses can be deduced.
Sememe Prediction: Learning Semantic Knowledge from Unstructured Textual Wiki Descriptions
In the experiments, we take a real-world sememe knowledge base HowNet and the corresponding descriptions of the words in Baidu Wiki for training and evaluation.
Learning Universal Sentence Representations with Mean-Max Attention Autoencoder
In the encoding we propose a mean-max strategy that applies both mean and max pooling operations over the hidden vectors to capture diverse information of the input.
Stochastic Answer Networks for SQuAD 2.0
This paper presents an extension of the Stochastic Answer Network (SAN), one of the state-of-the-art machine reading comprehension models, to be able to judge whether a question is unanswerable or not.
Improving Neural Abstractive Document Summarization with Explicit Information Selection Modeling
Information selection is the most important component in document summarization task.
Ranked #32 on
Abstractive Text Summarization
on CNN / Daily Mail
Improving Neural Abstractive Document Summarization with Structural Regularization
Recent neural sequence-to-sequence models have shown significant progress on short text summarization.
Ranked #43 on
Abstractive Text Summarization
on CNN / Daily Mail
Knowing Where to Look? Analysis on Attention of Visual Question Answering System
Attention mechanisms have been widely used in Visual Question Answering (VQA) solutions due to their capacity to model deep cross-domain interactions.
The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation
With recent breakthroughs in artificial neural networks, deep generative models have become one of the leading techniques for computational creativity.
Learning to discover and localize visual objects with open vocabulary
To alleviate the cost of obtaining accurate bounding boxes for training today's state-of-the-art object detection models, recent weakly supervised detection work has proposed techniques to learn from image-level labels.
Improved Expressivity Through Dendritic Neural Networks
In this study, we model such local nonlinearity of dendritic trees with our dendritic neural network (DENN) structure and apply this structure to typical machine learning tasks.
Applied Federated Learning: Improving Google Keyboard Query Suggestions
Federated learning is a distributed form of machine learning where both the training data and model training are decentralized.
DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systems
Furthermore, DeepBillboard is sufficiently robust and resilient for generating physical-world adversarial billboard tests for real-world driving under various weather conditions.
AADS: Augmented Autonomous Driving Simulation using Data-driven Algorithms
Our augmented approach combines the flexibility in a virtual environment (e. g., vehicle movements) with the richness of the real world to allow effective simulation of anywhere on earth.
ORSIm Detector: A Novel Object Detection Framework in Optical Remote Sensing Imagery Using Spatial-Frequency Channel Features
To this end, we propose a novel object detection framework, called optical remote sensing imagery detector (ORSIm detector), integrating diverse channel features extraction, feature learning, fast image pyramid matching, and boosting strategy.
Semi-Supervised Self-Taught Deep Learning for Finger Bones Segmentation
Segmentation stands at the forefront of many high-level vision tasks.
Multi-Interest Network with Dynamic Routing for Recommendation at Tmall
Industrial recommender systems usually consist of the matching stage and the ranking stage, in order to handle the billion-scale of users and items.
Ranked #1 on
Information Retrieval
on Amazon
High-Resolution Network for Photorealistic Style Transfer
Photorealistic style transfer aims to transfer the style of one image to another, but preserves the original structure and detail outline of the content image, which makes the content image still look like a real shot after the style transfer.
Spatial-Spectral Feature Extraction via Deep ConvLSTM Neural Networks for Hyperspectral Image Classification
Particularly, long short-term memory (LSTM), as a special deep learning structure, has shown great ability in modeling long-term dependencies in the time dimension of video or the spectral dimension of HSIs.
Behavior Sequence Transformer for E-commerce Recommendation in Alibaba
Deep learning based methods have been widely used in industrial recommendation systems (RSs).
Ranked #9 on
Recommendation Systems
on MovieLens 1M
Multiple Policy Value Monte Carlo Tree Search
Many of the strongest game playing programs use a combination of Monte Carlo tree search (MCTS) and deep neural networks (DNN), where the DNNs are used as policy or value evaluators.
Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model
In this paper, we propose to generate comments with a graph-to-sequence model that models the input news as a topic interaction graph.
Monotonic Infinite Lookback Attention for Simultaneous Machine Translation
Simultaneous machine translation begins to translate each source sentence before the source speaker is finished speaking, with applications to live and streaming scenarios.
Coherent Comments Generation for Chinese Articles with a Graph-to-Sequence Model
In this paper, we propose to generate comments with a graph-to-sequence model that models the input news as a topic interaction graph.
Deformable Tube Network for Action Detection in Videos
To perform action detection, we design a 3D convolution network with skip connections for tube classification and regression.
Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
Learning to localize and name object instances is a fundamental problem in vision, but state-of-the-art approaches rely on expensive bounding box supervision.
Two-Pass End-to-End Speech Recognition
However, this model still lags behind a large state-of-the-art conventional model in quality [2].
Toward better boundary preserved supervoxel segmentation for 3D point clouds
In this paper, we present a simple but effective supervoxel segmentation method for point clouds, which formalizes supervoxel segmentation as a subset selection problem.
HSI-BERT: Hyperspectral Image Classification Using the Bidirectional Encoder Representation From Transformers
Moreover, several attentions are learned by different heads, and each head of the MHSA layer encodes the semantic context-aware representation to obtain discriminative features.
Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View
Graph Neural Networks (GNNs) have achieved promising performance on a wide range of graph-based tasks.
Ranked #52 on
Node Classification
on Cora
Recursive Graphical Neural Networks for Text Classification
Graph is a natural structure to describe the complicated relation between tokens.
Neural Operator Search
We address this limitation by additionally exploiting feature self-calibration operations, resulting in a heterogeneous search space.
A Three-dimensional Convolutional-Recurrent Network for Convective Storm Nowcasting
Very short-term convective storm forecasting, termed nowcasting, has long been an important issue and has attracted substantial interest.
Multi-level Gated Recurrent Neural Network for Dialog Act Classification
In this paper we focus on the problem of dialog act (DA) labelling.
Dynamic Upsampling of Smoke through Dictionary-based Learning
We propose a novel dictionary-based neural network which learns both a fast evaluation of sparse patch encoding and a dictionary of corresponding coarse and fine patches from a sequence of example simulations computed with any numerical solver.
Graphics
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP).
Ranked #1 on
Sentiment Analysis
on SST-2 Binary classification
AutoRemover: Automatic Object Removal for Autonomous Driving Videos
To deal with shadows, we build up an autonomous driving shadow dataset and design a deep neural network to detect shadows automatically.
High Temporal Resolution Rainfall Runoff Modelling Using Long-Short-Term-Memory (LSTM) Networks
Accurate and efficient models for rainfall runoff (RR) simulations are crucial for flood risk management.
A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i. e., word error rate (WER), and latency, i. e., the time the hypothesis is finalized after the user stops speaking.
Investigation of Singing Voice Separation for Singing Voice Detection in Polyphonic Music
Singing voice detection (SVD), to recognize vocal parts in the song, is an essential task in music information retrieval (MIR).
kDecay: Just adding k-decay items on Learning-Rate Schedule to improve Neural Networks
On the ImageNet, accuracy is improved by 1. 25\%.
Jointly Modeling Aspect and Sentiment with Dynamic Heterogeneous Graph Neural Networks
Target-Based Sentiment Analysis aims to detect the opinion aspects (aspect extraction) and the sentiment polarities (sentiment detection) towards them.
Query-Variant Advertisement Text Generation with Association Knowledge
In this paper, we propose the query-variant advertisement text generation task that aims to generate candidate advertisement texts for different web search queries with various needs based on queries and item keywords.
Improving Accent Conversion with Reference Encoder and End-To-End Text-To-Speech
Accent conversion (AC) transforms a non-native speaker's accent into a native accent while maintaining the speaker's voice timbre.
Leveraging Graph to Improve Abstractive Multi-Document Summarization
Graphs that capture relations between textual units have great benefits for detecting salient information from multiple documents and generating overall coherent summaries.
BiERU: Bidirectional Emotional Recurrent Unit for Conversational Sentiment Analysis
Sentiment analysis in conversations has gained increasing attention in recent years for the growing amount of applications it can serve, e. g., sentiment analysis, recommender systems, and human-robot interaction.
Ranked #39 on
Emotion Recognition in Conversation
on IEMOCAP
Channel Attention based Iterative Residual Learning for Depth Map Super-Resolution
Second, we propose a new framework for real-world DSR, which consists of four modules : 1) An iterative residual learning module with deep supervision to learn effective high-frequency components of depth maps in a coarse-to-fine manner; 2) A channel attention strategy to enhance channels with abundant high-frequency components; 3) A multi-stage fusion module to effectively re-exploit the results in the coarse-to-fine process; and 4) A depth refinement module to improve the depth map by TGV regularization and input loss.
Modeling the Stock Relation with Graph Network for Overnight Stock Movement Prediction
Further analysis shows that the introduction of the graph enables our model to predict the movement of stocks that are not directly associated with news as well as the whole market, which is not available in most previous methods.
PerMO: Perceiving More at Once from a Single Image for Autonomous Driving
We present a novel approach to detect, segment, and reconstruct complete textured 3D models of vehicles from a single image for autonomous driving.
Vehicle Detection of Multi-source Remote Sensing Data Using Active Fine-tuning Network
In addition, the generalization ability of Ms-AFt in dense remote sensing scenes is further verified on stereo aerial imagery of a large camping site.
DVI: Depth Guided Video Inpainting for Autonomous Driving
To get clear street-view and photo-realistic simulation in autonomous driving, we present an automatic video inpainting algorithm that can remove traffic agents from videos and synthesize missing regions with the guidance of depth/point cloud.
Ranked #1 on
Image Inpainting
on ApolloScape
TEAM: We Need More Powerful Adversarial Examples for DNNs
In this paper, we propose a novel method (TEAM, Taylor Expansion-Based Adversarial Methods) to generate more powerful adversarial examples than previous methods.
Structure-Aware Network for Lane Marker Extraction with Dynamic Vision Sensor
We then propose a structure-aware network for lane marker extraction in DVS images.
Exploring the Impacts from Datasets to Monocular Depth Estimation (MDE) Models with MineNavi
Current computer vision tasks based on deep learning require a huge amount of data with annotations for model training or testing, especially in some dense estimation tasks, such as optical flow segmentation and depth estimation.
Transformer based Multilingual document Embedding model
One of the current state-of-the-art multilingual document embedding model LASER is based on the bidirectional LSTM neural machine translation model.
Physically-Constrained Transfer Learning through Shared Abundance Space for Hyperspectral Image Classification
Transfer learning-based methods address this problem by pre-training in the source domain and fine-tuning on the target domain.
General Classification
Hyperspectral Image Classification
+1
Parallel Rescoring with Transformer for Streaming On-Device Speech Recognition
The 2nd-pass model plays a key role in the quality improvement of the end-to-end model to surpass the conventional model.
Adversarial Privacy Preserving Graph Embedding against Inference Attack
In this paper, we propose Adversarial Privacy Graph Embedding (APGE), a graph adversarial training framework that integrates the disentangling and purging mechanisms to remove users' private information from learned node representations.
Temporal optical neurons for serial deep learning
This concept represents a novel one-dimensional realization of artificial neural networks, enabling an efficient application of optical deep learning methods to the analysis and processing of serial data signals, while offering a new overall perspective for the temporal signal processing.
VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognition
We introduce VoiceFilter-Lite, a single-channel source separation model that runs on the device to preserve only the speech signals from a target user, as part of a streaming speech recognition system.
Hidden Markov Models for Pipeline Damage Detection Using Piezoelectric Transducers
However, the negative pressure waves or guided stress waves may not be easily detected with environmental interference, e. g., the oil and gas pipelines in offshore environment.
SMOT: Single-Shot Multi Object Tracking
We combine this scheme with SSD detectors by proposing a novel tracking anchor assignment module.
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
However, we found that in the outdoor point cloud, the improvement obtained in this way is quite limited.
Ranked #2 on
3D Semantic Segmentation
on ScribbleKITTI
Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks
We present a novel method for multi-view depth estimation from a single video, which is a critical task in various applications, such as perception, reconstruction and robot navigation.
Decoupled Self Attention for Accurate One Stage Object Detection
When DSA module and object confidence task are applied in RetinaNet together, the detection performances based on ResNet50 and ResNet101 can be increased by 1. 0% AP and 1. 4% AP respectively.
CodeVIO: Visual-Inertial Odometry with Learned Optimizable Dense Depth
In this work, we present a lightweight, tightly-coupled deep depth network and visual-inertial odometry (VIO) system, which can provide accurate state estimates and dense depth maps of the immediate surroundings.
Learning Robust Representation for Clustering through Locality Preserving Variational Discriminative Network
Recent deep learning based methods focus on learning clustering oriented representations.
Gradient Descent Averaging and Primal-dual Averaging for Strongly Convex Optimization
In order to remove this factor, we first develop gradient descent averaging (GDA), which is a general projection-based dual averaging algorithm in the strongly convex setting.
UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning
Existed pre-training methods either focus on single-modal tasks or multi-modal tasks, and cannot effectively adapt to each other.
Ranked #3 on
Image Captioning
on MS COCO
Detection Booster Training: A detection booster training method for improving the accuracy of classifiers.
In this paper, we probe this direction by deriving a relationship between the estimation of unknown parameters of the probability density function (pdf) of input data and classification accuracy.
Rethinking Graph Neural Networks for Graph Coloring
To characterize the power of GNNs for the graph coloring problem, we first formalize the discrimination power of GNNs as the capability to assign nodes different colors.
A Simple Feature Augmentation for Domain Generalization
The topical domain generalization (DG) problem asks trained models to perform well on an unseen target domain with different data statistics from the source training domains.
Day-ahead electricity price prediction applying hybrid models of LSTM-based deep learning methods and feature selection algorithms under consideration of market coupling
In the context of trade liberalisation and market harmonisation in the European markets, accurate price forecasting becomes difficult for electricity market participants to obtain because electricity forecasting requires the consideration of features from ever-growing coupling markets.
Correlated interaction effects in three-dimensional semi-Dirac semimetal
The physical essences of the quantum critical points are determined by analyzing the susceptibility exponents for all of the source terms in particle-hole and particle-particle channels.
Strongly Correlated Electrons Materials Science
Phase Diagram of Triangular Lattice Quantum Ising Model under External Field
Quantum Ising model on a triangular lattice hosts a finite temperature Berezinskii-Kosterlitz-Thouless (BKT) phase with emergent U(1) symmetry, and it will transit into an up-up-down (UUD) phase with $C_3$ symmetry breaking upon an infinitesimal external field along the longitudinal direction, but the overall phase diagram spanned by the axes of external field and temperature remains opaque due to the lack of systematic invesitgations with controlled methodologies.
Strongly Correlated Electrons Statistical Mechanics
LEAD: LiDAR Extender for Autonomous Driving
In this paper, we propose LEAD, i. e., LiDAR Extender for Autonomous Driving, to extend the MEMS LiDAR by coupled image w. r. t both FoV and range.
Significant Inverse Magnetocaloric Effect induced by Quantum Criticality
Strong fluctuations in the low-$T$ quantum critical regime can give rise to a large thermal entropy change and thus significant cooling effect when approaching the QCP.
Strongly Correlated Electrons
Do Transformer Modifications Transfer Across Implementations and Applications?
The research community has proposed copious modifications to the Transformer architecture since it was introduced over three years ago, relatively few of which have seen widespread adoption.
A Universal Urbach Rule for Disordered Organic Semiconductors
A simple model is presented that explains absorption line-shapes of disordered systems, and we also provide a strategy to determine the excitonic disorder energy.
Optics Disordered Systems and Neural Networks
Modelling brain based on canonical ensemble with functional MRI: A thermodynamic exploration on neural system
(3) The detection of neural disease was demonstrated to be benefit from thermodynamic model, implying the immense potential of thermodynamics in auxiliary diagnosis.
Path-specific Underwater Acoustic Channel Tracking and its Application in Passive Time Reversal Mirror
With the path-specific parameters obtained by the proposed channel tracking, the proposed PTRM can not only match the time dispersion as conventional PTRM, but also the doubly-spread channel, since the path-specific delay and Doppler scaler factor can help to match the channel in both time and frequency domain.
Dynamic Underwater Acoustic Channel Tracking for Correlated Rapidly Time-varying Channels
A model based on the underwater acoustic channel's correlation can be used as the state-space model in the Kalman filter to improve the underwater acoustic channel tracking compared that without a model.
Learning Word-Level Confidence For Subword End-to-End ASR
We study the problem of word-level confidence estimation in subword-based end-to-end (E2E) models for automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Transferable Semantic Augmentation for Domain Adaptation
To remedy this, we propose a Transferable Semantic Augmentation (TSA) approach to enhance the classifier adaptation ability through implicitly generating source features towards target semantics.
Dynamic Domain Adaptation for Efficient Inference
Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy.
Adaptive Surface Normal Constraint for Depth Estimation
We present a novel method for single image depth estimation using surface normal constraints.
Morpho-evolution with learning using a controller archive as an inheritance mechanism
This causes a potential mismatch between the structure of an inherited controller and the new body.
Discover the Hidden Attack Path in Multi-domain Cyberspace Based on Reinforcement Learning
To achieve these results, we pose discovering attack paths as a Reinforcement Learning (RL) problem and train an agent to discover multi-domain cyberspace attack paths.
ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion
We tackle the problem of object completion from point clouds and propose a novel point cloud completion network employing an Asymmetrical Siamese Feature Matching strategy, termed as ASFM-Net.
Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning
To capture these properties effectively and efficiently, we propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN), called RE-GCN, which learns the evolutional representations of entities and relations at each timestamp by modeling the KG sequence recurrently.
Multi-scale PIIFD for Registration of Multi-source Remote Sensing Images
This paper aims at providing multi-source remote sensing images registered in geometric space for image fusion.
MUSE: Multi-faceted Attention for Signed Network Embedding
Signed network embedding is an approach to learn low-dimensional representations of nodes in signed networks with both positive and negative links, which facilitates downstream tasks such as link prediction with general data mining frameworks.
BASS: Boosting Abstractive Summarization with Unified Semantic Graph
Abstractive summarization for long-document or multi-document remains challenging for the Seq2Seq architecture, as Seq2Seq is not good at analyzing long-distance relations in text.
DiaKG: an Annotated Diabetes Dataset for Medical Knowledge Graph Construction
In order to accelerate the research for domain-specific knowledge graphs in the medical domain, we introduce DiaKG, a high-quality Chinese dataset for Diabetes knowledge graph, which contains 22, 050 entities and 6, 890 relations in total.
Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs
Specifically, at the clue searching stage, CluSTeR learns a beam search policy via reinforcement learning (RL) to induce multiple clues from historical facts.
Generative Adversarial Networks: A Survey Towards Private and Secure Applications
Generative Adversarial Networks (GAN) have promoted a variety of applications in computer vision, natural language processing, etc.
MST: Masked Self-Supervised Transformer for Visual Representation
More importantly, the masked tokens together with the remaining tokens are further recovered by a global image decoder, which preserves the spatial information of the image and is more friendly to the downstream dense prediction tasks.
Toward Less Hidden Cost of Code Completion with Acceptance and Ranking Models
We integrate this ranking scheme with two frequency models and a GPT-2 styled language model, along with the acceptance model to yield 27. 80% and 37. 64% increase in TOP1 and TOP5 accuracy, respectively.
Semi-TCL: Semi-Supervised Track Contrastive Representation Learning
We design a new instance-to-track matching objective to learn appearance embedding that compares a candidate detection to the embedding of the tracks persisted in the tracker.
Video 3D Sampling for Self-supervised Representation Learning
As a result, we can leverage the spatial information (the size of objects), temporal information (the direction and magnitude of motions) as our learning target.
Residual Attention Based Network for Automatic Classification of Phonation Modes
Phonation mode is an essential characteristic of singing style as well as an important expression of performance.
A Data-driven Explainable Case-based Reasoning Approach for Financial Risk Detection
The rapid development of artificial intelligence methods contributes to their wide applications for forecasting various financial risks in recent years.
UoB\_UK at SemEval 2021 Task 2: Zero-Shot and Few-Shot Learning for Multi-lingual and Cross-lingual Word Sense Disambiguation.
This paper describes our submission to SemEval 2021 Task 2.
Wavelet-Based Network For High Dynamic Range Imaging
The frequency-guided upsampling module reconstructs details from multiple frequency-specific components with rich details.
Semantic Concentration for Domain Adaptation
To tackle this issue, we propose Semantic Concentration for Domain Adaptation (SCDA), which encourages the model to concentrate on the most principal features via the pair-wise adversarial alignment of prediction distributions.
Multi defect detection and analysis of electron microscopy images with deep learning
Electron microscopy is widely used to explore defects in crystal structures, but human detecting of defects is often time-consuming, error-prone, and unreliable, and is not scalable to large numbers of images or real-time analysis.
ASAT: Adaptively Scaled Adversarial Training in Time Series
Besides the security concerns of potential adversarial examples, adversarial training can also improve the generalization ability of neural networks, train robust neural networks, and provide interpretability for neural networks.
Long-term, Short-term and Sudden Event: Trading Volume Movement Prediction with Graph-based Multi-view Modeling
Trading volume movement prediction is the key in a variety of financial applications.
LUAI Challenge 2021 on Learning to Understand Aerial Images
This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV 2021, which focuses on object detection and semantic segmentation in aerial images.
Musical Tempo Estimation Using a Multi-scale Network
Recently, some single-step systems without onset detection have shown their effectiveness in automatic musical tempo estimation.
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception
In this paper, we benchmark our model on these three tasks.
Tied & Reduced RNN-T Decoder
Previous works on the Recurrent Neural Network-Transducer (RNN-T) models have shown that, under some conditions, it is possible to simplify its prediction network with little or no loss in recognition accuracy (arXiv:2003. 07705 [eess. AS], [2], arXiv:2012. 06749 [cs. CL]).
CENN: Conservative energy method based on neural networks with subdomains for solving variational problems involving heterogeneous and complex geometries
The advantage of the proposed method is higher efficiency, more accurate, and less hyperparameters than the strong form PINN with subdomains.
A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection
Specifically, an anchor-free object-adaptation label assignment (OLA) strategy is presented to define the positive candidates based on two-dimensional (2-D) oriented Gaussian heatmaps, which reflect the shape and direction features of arbitrary-oriented objects.
Ranked #31 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
Referring Self-supervised Learning on 3D Point Cloud
In this paper, we study a new problem named Referring Self-supervised Learning (RSL) on 3D scene understanding: Given the 3D synthetic models with labels and the unlabeled 3D real scene scans, our goal is to distinguish the identical semantic objects on an unseen scene according to the referring synthetic 3D models.
MC-LCR: Multi-modal contrastive classification by locally correlated representations for effective face forgery detection
Moreover, we make a key observation that subtle forgery artifacts can be further exposed in the patch-wise phase and amplitude spectrum and exhibit different clues.
Learning UI Navigation through Demonstrations composed of Macro Actions
The action space is restricted to the UI elements plus a few global actions.
Deep Learning for UAV-based Object Detection and Tracking: A Survey
Owing to effective and flexible data acquisition, unmanned aerial vehicle (UAV) has recently become a hotspot across the fields of computer vision (CV) and remote sensing (RS).
SgSum: Transforming Multi-document Summarization into Sub-graph Selection
Comparing with traditional methods, our method has two main advantages: (1) the relations between sentences are captured by modeling both the graph structure of the whole document set and the candidate sub-graphs; (2) directly outputs an integrate summary in the form of sub-graph which is more informative and coherent.
FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows
However, current methods can not effectively map image features to a tractable base distribution and ignore the relationship between local and global features which are important to identify anomalies.
Ranked #20 on
Anomaly Detection
on MVTec AD
Unsupervised Anomaly Detection
Weakly Supervised Defect Detection
Exploiting Both Domain-specific and Invariant Knowledge via a Win-win Transformer for Unsupervised Domain Adaptation
Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain.
Variational Autoencoder with CCA for Audio-Visual Cross-Modal Retrieval
On the one hand, audio encoder and visual encoder separately encode audio data and visual data into two different latent spaces.
Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting
RDIM and region fitting do not require extra running time and these three steps can be well integrated into other attacks.
Transfer learning of phase transitions in percolation and directed percolation
With the DANN, only a small fraction of input configurations (2d images) needs to be labeled, which is automatically chosen, in order to capture the critical point.
An Intelligent Self-driving Truck System For Highway Transportation
Recently, there have been many advances in autonomous driving society, attracting a lot of attention from academia and industry.
PPDL: Predicate Probability Distribution Based Loss for Unbiased Scene Graph Generation
However, the application value of SG on downstream tasks is severely limited by the predicate classification bias, which is caused by long-tailed data and presented as semantic bias of predicted relation predicates.
Large-Scale Video Panoptic Segmentation in the Wild: A Benchmark
In contrast, our large-scale VIdeo Panoptic Segmentation in the Wild (VIPSeg) dataset provides 3, 536 videos and 84, 750 frames with pixel-level panoptic annotations, covering a wide range of real-world scenarios and categories.
Generative adversarial network for super-resolution imaging through a fiber
A multimode fiber represents the ultimate limit in miniaturization of imaging endoscopes.
Evolutionary Action Selection for Gradient-based Policy Learning
Evolutionary Algorithms (EAs) and Deep Reinforcement Learning (DRL) have recently been integrated to take the advantage of the both methods for better exploration and exploitation. The evolutionary part in these hybrid methods maintains a population of policy networks. However, existing methods focus on optimizing the parameters of policy network, which is usually high-dimensional and tricky for EA. In this paper, we shift the target of evolution from high-dimensional parameter space to low-dimensional action space. We propose Evolutionary Action Selection-Twin Delayed Deep Deterministic Policy Gradient (EAS-TD3), a novel hybrid method of EA and DRL. In EAS, we focus on optimizing the action chosen by the policy network and attempt to obtain high-quality actions to promote policy learning through an evolutionary algorithm.
DDU-Net: Dual-Decoder-U-Net for Road Extraction Using High-Resolution Remote Sensing Images
Extracting roads from high-resolution remote sensing images (HRSIs) is vital in a wide variety of applications, such as autonomous driving, path planning, and road navigation.
A Joint Morphological Profiles and Patch Tensor Change Detection for Hyperspectral Imagery
Multi-temporal hyperspectral images can be used to detect changed information, which has gradually attracted researchers' attention.
TONet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music
In this paper, we propose TONet, a plug-and-play model that improves both tone and octave perceptions by leveraging a novel input representation and a novel network architecture.
DEEPCHORUS: A Hybrid Model of Multi-scale Convolution and Self-attention for Chorus Detection
Chorus detection is a challenging problem in musical signal processing as the chorus often repeats more than once in popular songs, usually with rich instruments and complex rhythm forms.
Improving Non-native Word-level Pronunciation Scoring with Phone-level Mixup Data Augmentation and Multi-source Information
Moreover, we utilize multi-source information (e. g., MFCC and deep features) to further improve the scoring system performance.
Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
A common practice is to select the highly confident predictions as the pseudo ground-truth, but it leads to a problem that most pixels may be left unused due to their unreliability.
A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds
Recent works on 3D single object tracking treat the task as a target-specific 3D detection task, where an off-the-shelf 3D detector is commonly employed for the tracking.
Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods
In this survey, we provide a systematic overview of the research progress on the faithfulness problem of NLG, including problem analysis, evaluation metrics and optimization methods.
Efficient universal shuffle attack for visual object tracking
Recently, adversarial attacks have been applied in visual object tracking to deceive deep trackers by injecting imperceptible perturbations into video frames.
UniVIP: A Unified Framework for Self-Supervised Visual Pre-training
Furthermore, our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2. 5% with the same pre-training epochs in linear probing, and surpass current self-supervised object detection methods on COCO dataset, demonstrating its universality and potential.
Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning
Furthermore, these models are all trained offline, which cannot well adapt to the changes of evolutional patterns from then on.
UNIMO-2: End-to-End Unified Vision-Language Grounded Learning
In particular, we propose to conduct grounded learning on both images and texts via a sharing grounded space, which helps bridge unaligned images and texts, and align the visual and textual semantic spaces on different types of corpora.
Towards 3D Scene Understanding by Referring Synthetic Models
Promising performance has been achieved for visual perception on the point cloud.
Open-Vocabulary DETR with Conditional Matching
To this end, we propose a novel open-vocabulary detector based on DETR -- hence the name OV-DETR -- which, once trained, can detect any object given its class name or an exemplar image.
Ranked #21 on
Open Vocabulary Object Detection
on MSCOCO
SepViT: Separable Vision Transformer
Vision Transformers have witnessed prevailing success in a series of vision tasks.
