Search Results for author:
Found 524 papers, 160 papers with code
Modeling 4D fMRI Data via Spatio-Temporal Convolutional Neural Networks (ST-CNN)
Simultaneous modeling of the spatio-temporal variation patterns of brain functional network from 4D fMRI data has been an important yet challenging problem for the field of cognitive neuroscience and medical image analysis.
Boosting up Scene Text Detectors with Guided CNN
Deep CNNs have achieved great success in text detection.
Knowledge Base Relation Detection via Multi-View Matching
Relation detection is a core component for Knowledge Base Question Answering (KBQA).
Adversarial Learning for Chinese NER from Crowd Annotations
To quickly obtain new labeled data, we can choose crowdsourcing as an alternative way at lower cost in a short time.
Chinese Named Entity Recognition
named-entity-recognition
+2
SEE: Syntax-aware Entity Embedding for Neural Relation Extraction
First, we encode the context of entities on a dependency tree as sentence-level entity embedding based on tree-GRU.
AdaComp : Adaptive Residual Gradient Compression for Data-Parallel Distributed Training
Highly distributed training of Deep Neural Networks (DNNs) on future compute platforms (offering 100 of TeraOps/s of computational capacity) is expected to be severely communication constrained.
DeepSkeleton: Skeleton Map for 3D Human Pose Regression
For the first time, we show that training regression network from skeleton map alone is capable of meeting the performance of state-of-theart 3D human pose estimation works.
GaDei: On Scale-up Training As A Service For Deep Learning
By evaluating the NLC workloads, we show that only the conservative hyper-parameter setup (e. g., small mini-batch size and small learning rate) can guarantee acceptable model accuracy for a wide range of customers.
Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization
Learning to remember long sequences remains a challenging task for recurrent neural networks.
Embedding Visual Hierarchy with Deep Networks for Large-Scale Visual Recognition
Our LMM model can provide an end-to-end approach for jointly learning: (a) the deep networks to extract more discriminative deep features for image and object class representation; (b) the tree classifier for recognizing large numbers of object classes hierarchically; and (c) the visual hierarchy adaptation for achieving more accurate indexing of large numbers of object classes hierarchically.
Deep Mixture of Diverse Experts for Large-Scale Visual Recognition
In this paper, a deep mixture of diverse experts algorithm is developed for seamlessly combining a set of base deep CNNs (convolutional neural networks) with diverse outputs (task spaces), e. g., such base deep CNNs are trained to recognize different subsets of tens of thousands of atomic object classes.
Application of Multi-channel 3D-cube Successive Convolution Network for Convective Storm Nowcasting
This paper describes the first attempt to nowcast storm initiation, growth, and advection simultaneously under a deep learning framework using multi-source meteorological data.
Low-rank Label Propagation for Semi-supervised Learning with 100 Millions Samples
The success of semi-supervised learning crucially relies on the scalability to a huge amount of unlabelled data that are needed to capture the underlying manifold structure for better classification.
Learning Compact Appearance Representation for Video-based Person Re-Identification
This paper presents a novel approach for video-based person re-identification using multiple Convolutional Neural Networks (CNNs).
PIGMIL: Positive Instance Detection via Graph Updating for Multiple Instance Learning
To the end, we propose a positive instance detection via graph updating for multiple instance learning, called PIGMIL, to detect TPI accurately.
Integrating Topic Models and Latent Factors for Recommendation
In this work, we consider the problem of hotel recommendation for travel planning services by integrating the location information and the user's preference for recommendation.
End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
This paper proposes dynamic chunk reader (DCR), an end-to-end neural reading comprehension (RC) model that is able to extract and rank a set of answer candidates from a given document to answer questions.
Ranked #49 on
Question Answering
on SQuAD1.1 dev
Deep Kinematic Pose Regression
In this work, we propose to directly embed a kinematic object model into the deep neutral network learning for general articulated object pose estimation.
Ranked #307 on
3D Human Pose Estimation
on Human3.6M
Empirical Study on Deep Learning Models for Question Answering
In this paper we explore deep learning models with memory component or attention mechanism for question answering task.
Structured Memory for Neural Turing Machines
Neural Turing Machines (NTM) contain memory component that simulates "working memory" in the brain to store and retrieve information to ease simple algorithms learning.
Network-based Isoform Quantification with RNA-Seq Data for Cancer Transcriptome Analysis
Based on our observation that the abundances of the neighboring isoforms by domain-domain interactions in the network are positively correlated, Net-RSTQ models the expression of the neighboring transcripts as Dirichlet priors on the likelihood of the observed read alignments against the transcripts in one gene.
Recognizing Extended Spatiotemporal Expressions by Actively Trained Average Perceptron Ensembles
We collected and annotated data set by querying commercial web searches API with such spatiotemporal expressions as were missed by state-of-the- art parsers.
Exploring Metaphorical Senses and Word Representations for Identifying Metonyms
A metonym is a word with a figurative meaning, similar to a metaphor.
Conditional Restricted Boltzmann Machines for Cold Start Recommendations
Restricted Boltzman Machines (RBMs) have been successfully used in recommender systems.
Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation
Prior relevant studies recommend treatments either use supervised learning (e. g. matching the indicator signal which denotes doctor prescriptions), or reinforcement learning (e. g. maximizing evaluation signal which indicates cumulative reward from survival rates).
Non-locally Enhanced Encoder-Decoder Network for Single Image De-raining
Single image rain streaks removal has recently witnessed substantial progress due to the development of deep convolutional neural networks.
Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos
Secondly, TSD significantly reduces the computations to run video action recognition with compressed frames on the cloud, while maintaining high recognition accuracies.
Solving Pictorial Jigsaw Puzzle by Stigmergy-inspired Internet-based Human Collective Intelligence
And through feedback, each player is provided with personalized feedback information based on the current COG and the player's exploration result, in order to accelerate his/her puzzle-solving process.
Dynamic Graph Modules for Modeling Object-Object Interactions in Activity Recognition
Video action recognition, a critical problem in video understanding, has been gaining increasing attention.
NADPEx: An on-policy temporally consistent exploration method for deep reinforcement learning
Reinforcement learning agents need exploratory behaviors to escape from local optima.
Label-Free Distant Supervision for Relation Extraction via Knowledge Graph Embedding
This paper proposes a label-free distant supervision method, which makes no use of the relation labels under this inadequate assumption, but only uses the prior knowledge derived from the KG to supervise the learning of the classifier directly and softly.
Learning to Decompose Compound Questions with Reinforcement Learning
Our model consists of two parts: (i) a novel learning-to-decompose agent that learns a policy to decompose a compound question into simple questions and (ii) three independent simple-question answerers that classify the corresponding relations for each simple question.
Deep Boosting of Diverse Experts
In this paper, a deep boosting algorithm is developed to learn more discriminative ensemble classifier by seamlessly combining a set of base deep CNNs (base experts) with diverse capabilities, e. g., these base deep CNNs are sequentially trained to recognize a set of object classes in an easy-to-hard way according to their learning complexities.
Edge-Semantic Learning Strategy for Layout Estimation in Indoor Environment
More specifically, we present an encoder-decoder network with shared encoder and two separate decoders, which are composed of multiple deconvolution (transposed convolution) layers, to jointly learn the edge maps and semantic labels of a room image.
MSR: Multi-Scale Shape Regression for Scene Text Detection
State-of-the-art scene text detection techniques predict quadrilateral boxes that are prone to localization errors while dealing with straight or curved text lines of different orientations and lengths in scenes.
Weakly Supervised Semantic Segmentation for Social Images
Image semantic segmentation is the task of partitioning image into several regions based on semantic concepts.
Binarized Mode Seeking for Scalable Visual Pattern Discovery
Second, we further extend bMS to a more general form, namely contrastive binary mean shift (cbMS), which maximizes the contrastive density in binary space, for finding informative patterns that are both frequent and discriminative for the dataset.
Multiple Granularity Descriptors for Fine-Grained Categorization
Fine-grained categorization, which aims to distinguish subordinate-level categories such as bird species or dog breeds, is an extremely challenging task.
A Spatio-Temporal Appearance Representation for Viceo-Based Pedestrian Re-Identification
Pedestrian re-identification is a difficult problem due to the large variations in a person's appearance caused by different poses and viewpoints, illumination changes, and occlusions.
VrR-VG: Refocusing Visually-Relevant Relationships
Relationships encode the interactions among individual instances, and play a critical role in deep visual scene understanding.
Hierarchical Photo-Scene Encoder for Album Storytelling
In this paper, we propose a novel model with a hierarchical photo-scene encoder and a reconstructor for the task of album storytelling.
Ranked #5 on
Image-guided Story Ending Generation
on VIST-E
Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks
Here, the challenge is to learn accurate "few-shot" models for classes existing at the tail of the class distribution, for which little data is available.
Interaction Embeddings for Prediction and Explanation in Knowledge Graphs
Knowledge graph embedding aims to learn distributed representations for entities and relations, and is proven to be effective in many applications.
Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning
We also evaluate the efficiency of rule learning and quality of rules from IterE compared with AMIE+, showing that IterE is capable of generating high quality rules more efficiently.
Distributed Deep Learning Strategies For Automatic Speech Recognition
We show that we can train the LSTM model using ADPSGD in 14 hours with 16 NVIDIA P100 GPUs to reach a 7. 6% WER on the Hub5- 2000 Switchboard (SWB) test set and a 13. 1% WER on the CallHome (CH) test set.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Everyone is a Cartoonist: Selfie Cartoonization with Attentive Adversarial Networks
Selfie and cartoon are two popular artistic forms that are widely presented in our daily life.
Anti-Confusing: Region-Aware Network for Human Pose Estimation
In this work, we propose a novel framework named Region-Aware Network (RANet), which learns the ability of anti-confusing in case of heavy occlusion, nearby person and symmetric appearance, for human pose estimation.
Accelerated Target Updates for Q-learning
This paper studies accelerations in Q-learning algorithms.
Machine Learning Based Routing Congestion Prediction in FPGA High-Level Synthesis
Early and accurate congestion estimation is of great benefit to guide the optimization in HLS and improve the efficiency of implementation.
Predictive Ensemble Learning with Application to Scene Text Detection
Taking scene text detection as the application, where no suitable ensemble learning strategy exists, PEL can significantly improve the performance, compared to either individual state-of-the-art models, or the fusion of multiple models by non-maximum suppression.
Correlative Multi-Label Multi-Instance Image Annotation
The cross-level label coherence en-codes the consistency between the labels at the image leveland the labels at the region level.
Reconstruct and Represent Video Contents for Captioning via Reinforcement Learning
Unlike previous video captioning work mainly exploiting the cues of video contents to make a language description, we propose a reconstruction network (RecNet) in a novel encoder-decoder-reconstructor architecture, which leverages both forward (video to sentence) and backward (sentence to video) flows for video captioning.
Large-Scale Mixed-Bandwidth Deep Neural Network Acoustic Modeling for Automatic Speech Recognition
In automatic speech recognition (ASR), wideband (WB) and narrowband (NB) speech signals with different sampling rates typically use separate acoustic models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition
On commonly used public SWB-300 and SWB-2000 ASR datasets, ADPSGD can converge with a batch size 3X as large as the one used in SSGD, thus enable training at a much larger scale.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Multi-Granular Text Encoding for Self-Explaining Categorization
Self-explaining text categorization requires a classifier to make a prediction along with supporting evidence.
Hard-Aware Fashion Attribute Classification
For "hard" attributes with insufficient training data, Deact brings more stable synthetic samples for training and further improve the performance.
Road Context-aware Intrusion Detection System for Autonomous Cars
With such ongoing road context, RAIDS validates corresponding frames observed on the in-vehicle network.
Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning
However, the human annotation is expensive, while human-crafted patterns suffer from semantic drift and distant supervision samples are usually noisy.
Fake Colorized Image Detection
Based on our observations, i. e., potential traces in the hue, saturation, dark and bright channels, we propose two simple yet effective detection methods for fake colorized images: Histogram based Fake Colorized Image Detection (FCID-HIST) and Feature Encoding based Fake Colorized Image Detection (FCID-FE).
Multimedia
Relationship-Aware Spatial Perception Fusion for Realistic Scene Layout Generation
In our framework, a spatial constraint module is designed to fit reasonable scaling and spatial layout of object pairs with considering relationship between them.
Learning Actions from Human Demonstration Video for Robotic Manipulation
However, the general video captioning methods focus more on the understanding of the full frame, lacking of consideration on the specific object of interests in robotic manipulations.
AI Matrix: A Deep Learning Benchmark for Alibaba Data Centers
Alibaba has China's largest e-commerce platform.
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.
Learning Robust Representations with Graph Denoising Policy Network
Graph representation learning, aiming to learn low-dimensional representations which capture the geometric dependencies between nodes in the original graph, has gained increasing popularity in a variety of graph analysis tasks, including node classification and link prediction.
Hybrid Zero Dynamics Inspired Feedback Control Policy Design for 3D Bipedal Locomotion using Reinforcement Learning
This paper presents a novel model-free reinforcement learning (RL) framework to design feedback control policies for 3D bipedal walking.
Constrained Non-Affine Alignment of Embeddings
Embeddings are already essential tools for large language models and image analysis, and their use is being extended to many other research domains.
History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms
In this paper, we propose a novel scheme, which eliminates backtracking line search but still exploits the information along optimization path by adapting the batch size via history stochastic gradients.
A Decentralized Parallel Algorithm for Training Generative Adversarial Nets
Despite recent progress on decentralized algorithms for training deep neural networks, it remains unclear whether it is possible to train GANs in a decentralized manner.
A Machine Learning Nowcasting Method based on Real-time Reanalysis Data
Despite marked progress over the past several decades, convective storm nowcasting remains a challenge because most nowcasting systems are based on linear extrapolation of radar reflectivity without much consideration for other meteorological fields.
Long-distance distribution of atom-photon entanglement at telecom wavelength
Here we report on the generation and observation of entanglement between a Rb-87 atom and a photon at telecom wavelength over 20 km optical fiber.
Quantum Physics
Relation Adversarial Network for Low Resource Knowledge Graph Completion
Specifically, the framework takes advantage of a relation discriminator to distinguish between samples from different relations, and help learn relation-invariant features more transferable from source relations to target relations.
SubCharacter Chinese-English Neural Machine Translation with Wubi encoding
However, when the translation task involves Chinese, semantic granularity remains at the word and character level, so there is still need more fine-grained translation model of Chinese.
Language Model-Driven Unsupervised Neural Machine Translation
We present the detailed mathematical construction of our method.
Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks
Reducing the numerical precision of data and computation is extremely effective in accelerating deep learning training workloads.
Convolutional Neural Network for Convective Storm Nowcasting Using 3D Doppler Weather Radar Data
On the first layer of CNN, a cross-channel 3D convolution was proposed to fuse 3D raw data.
Furnishing Your Room by What You See: An End-to-End Furniture Set Retrieval Framework with Rich Annotated Benchmark Dataset
However, few works focus on the understanding of furniture within the scenes and a large-scale dataset is also lacked to advance the field.
SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection
In this paper, we present a two-stage coarse-to-fine searching strategy named Structural-to-Modular NAS (SM-NAS) for searching a GPU-friendly design of both an efficient combination of modules and better modular-level architecture for object detection.
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.
Learning Efficient Video Representation with Video Shuffle Networks
To this end, we propose the video shuffle, a parameter-free plug-in component that efficiently reallocates the inputs of 2D convolution so that its receptive field can be extended to the temporal dimension.
Improving Neural Relation Extraction with Positive and Unlabeled Learning
We present a novel approach to improve the performance of distant supervision relation extraction with Positive and Unlabeled (PU) Learning.
Attentive Representation Learning with Adversarial Training for Short Text Clustering
Relying on this, the representation learning and clustering for short texts are seamlessly integrated into a unified model.
Zooming into Face Forensics: A Pixel-level Analysis
The stunning progress in face manipulation methods has made it possible to synthesize realistic fake face images, which poses potential threats to our society.
Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets
Then we propose an adaptive variant of OSG named Optimistic Adagrad (OAdagrad) and reveal an \emph{improved} adaptive complexity $O\left(\epsilon^{-\frac{2}{1-\alpha}}\right)$, where $\alpha$ characterizes the growth rate of the cumulative stochastic gradient and $0\leq \alpha\leq 1/2$.
Vision and Language: from Visual Perception to Content Creation
The real-world deployment or services of vision and language are elaborated as well.
A Two-step Calibration Method for Unfocused Light Field Camera Based on Projection Model Analysis
The proposed method is able to reuse traditional camera calibration methods for the direction parameter set.
How Does BN Increase Collapsed Neural Network Filters?
This phenomenon is caused by the normalization effect of BN, which induces a non-trainable region in the parameter space and reduces the network capacity as a result.
Knowledge-Aware Deep Dual Networks for Text-Based Mortality Prediction
To address the above issues, we propose novel Knowledge-aware Deep Dual Networks (K-DDN) for the text-based mortality prediction task.
A Novel Hybrid Sequential Model for Review-based Rating Prediction
Nowadays, the online interactions between users and items become diverse, and may include textual reviews as well as numerical ratings.
Learning Long- and Short-Term User Literal-Preference with Multimodal Hierarchical Transformer Network for Personalized Image Caption
Personalized image caption, a natural extension of the standard image caption task, requires to generate brief image descriptions tailored for users’ writing style and traits, and is more practical to meet users’ real demands.
Improving Efficiency in Large-Scale Decentralized Distributed Training
Decentralized Parallel SGD (D-PSGD) and its asynchronous variant Asynchronous Parallel SGD (AD-PSGD) is a family of distributed learning algorithms that have been demonstrated to perform well for large-scale deep learning tasks.
Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling
Despite the wide applications of Adam in reinforcement learning (RL), the theoretical convergence of Adam-type RL algorithms has not been established.
Syndrome-aware Herb Recommendation with Multi-Graph Convolution Network
Given a set of symptoms to treat, we aim to generate an overall syndrome representation by effectively fusing the embeddings of all the symptoms in the set, to mimic how a doctor induces the syndromes.
Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition
The past decade has witnessed great progress in Automatic Speech Recognition (ASR) due to advances in deep learning.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment
Specifically, the fractional dilated kernel is adaptively constructed according to the image aspect ratios, where the interpolation of nearest two integers dilated kernels is used to cope with the misalignment of fractional sampling.
Learning from a Lightweight Teacher for Efficient Knowledge Distillation
Knowledge Distillation (KD) is an effective framework for compressing deep learning models, realized by a student-teacher paradigm requiring small student networks to mimic the soft target generated by well-trained teachers.
Map Generation from Large Scale Incomplete and Inaccurate Data Labels
Accurately and globally mapping human infrastructure is an important and challenging task with applications in routing, regulation compliance monitoring, and natural disaster response management etc..
FP-Stereo: Hardware-Efficient Stereo Vision for Embedded Applications
To reduce the design effort and achieve the right balance, we propose FP-Stereo for building high-performance stereo matching pipelines on FPGAs automatically.
Multi-future Merchant Transaction Prediction
We use experiments on real-world merchant transaction data to demonstrate the effectiveness of our proposed model.
Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descent
In this paper, we first characterize the convergence rate for Q-AMSGrad, which is the Q-learning algorithm with AMSGrad update (a commonly adopted alternative of Adam for theoretical analysis).
Automatic Image Labelling at Pixel Level
A Guided Filter Network (GFN) is first developed to learn the segmentation knowledge from a source domain, and such GFN then transfers such segmentation knowledge to generate coarse object masks in the target domain.
Research Progress of Convolutional Neural Network and its Application in Object Detection
With the improvement of computer performance and the increase of data volume, the object detection based on convolutional neural network (CNN) has become the main algorithm for object detection.
Momentum Q-learning with Finite-Sample Convergence Guarantee
For the infinite state-action space case, we establish the convergence guarantee for MomentumQ with linear function approximations and Markovian sampling.
Multi-stream RNN for Merchant Transaction Prediction
New challenges have surfaced in monitoring and guaranteeing the integrity of payment processing systems.
GeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planes
The task of room layout estimation is to locate the wall-floor, wall-ceiling, and wall-wall boundaries.
A(DP)$^2$SGD: Asynchronous Decentralized Parallel Stochastic Gradient Descent with Differential Privacy
A popular distributed learning strategy is federated learning, where there is a central server storing the global model and a set of local computing nodes updating the model parameters with their corresponding data.
Products-10K: A Large-scale Product Recognition Dataset
With the rapid development of electronic commerce, the way of shopping has experienced a revolutionary evolution.
Learn by Observation: Imitation Learning for Drone Patrolling from Videos of A Human Navigator
Extensive experiments are conducted to demonstrate the accuracy of the proposed imitating learning process as well as the reliability of the holistic system for autonomous drone navigation.
Decision Tree Based Hardware Power Monitoring for Run Time Dynamic Power Management in FPGA
A flexible architecture of the hardware power monitoring is proposed, which can be instrumented in any RTL design for runtime power estimation, dispensing with the need for extra power measurement devices.
An Ensemble Learning Approach for In-situ Monitoring of FPGA Dynamic Power
As field-programmable gate arrays become prevalent in critical application domains, their power consumption is of high concern.
Towards Efficient and Scalable Acceleration of Online Decision Tree Learning on FPGA
We further present a high-performance, hardware-efficient and scalable online decision tree learning system on a field-programmable gate array (FPGA) with system-level optimization techniques.
HARD-Net: Hardness-AwaRe Discrimination Network for 3D Early Activity Prediction
In this paper, we propose a novel Hardness-AwaRe Discrimination Network (HARD-Net) to specifically investigate the relationships between the similar activity pairs that are hard to be discriminated.
Ranked #4 on
Skeleton Based Action Recognition
on UAV-Human
DualDE: Dually Distilling Knowledge Graph Embedding for Faster and Cheaper Reasoning
In DualDE, we propose a soft label evaluation mechanism to adaptively assign different soft label and hard label weights to different triples, and a two-stage distillation approach to improve the student's acceptance of the teacher.
Towards a Flexible Embedding Learning Framework
Our proposed framework utilizes a set of entity-relation-matrices as the input, which quantifies the affinities among different entities in the database.
Kernel Based Progressive Distillation for Adder Neural Networks
A convolutional neural network (CNN) with the same architecture is simultaneously initialized and trained as a teacher network, features and weights of ANN and CNN will be transformed to a new space to eliminate the accuracy drop.
Finite-Time Analysis for Double Q-learning
Although Q-learning is one of the most successful algorithms for finding the best action-value function (and thus the optimal policy) in reinforcement learning, its implementation often suffers from large overestimation of Q-function values incurred by random sampling.
Double Q-learning: New Analysis and Sharper Finite-time Bound
Double Q-learning (Hasselt 2010) has gained significant success in practice due to its effectiveness in overcoming the overestimation issue of Q-learning.
Why Does Decentralized Training Outperform Synchronous Training In The Large Batch Setting?
We conduct extensive studies over 12 state-of-the-art DL models/tasks and demonstrate that DPSGD consistently outperforms SSGD in the large batch setting; and DPSGD converges in cases where SSGD diverges for large learning rates.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
RRL: A Scalable Classifier for Interpretable Rule-Based Representation Learning
Rule-based models, e. g., decision trees, are widely used in scenarios demanding high model interpretability for their transparent inner structures and good model expressivity.
How Can Self-Attention Networks Recognize Dyck-n Languages?
For $\mathcal{D}_2$, we find that SA$^-$ completely breaks down on long sequences whereas the accuracy of SA$^+$ is 58. 82$\%$.
G-DARTS-A: Groups of Channel Parallel Sampling with Attention
Differentiable Architecture Search (DARTS) provides a baseline for searching effective network architectures based gradient, but it is accompanied by huge computational overhead in searching and training network architecture.
Learn to Navigate Maplessly with Varied LiDAR Configurations: A Support Point-Based Approach
Deep reinforcement learning (DRL) demonstrates great potential in mapless navigation domain.
Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction
Current supervised relational triple extraction approaches require huge amounts of labeled data and thus suffer from poor performance in few-shot settings.
Merchant Category Identification Using Credit Card Transactions
In this work, we approach this problem from a multi-modal learning perspective, where we use not only the merchant time series data but also the information of merchant-merchant relationship (i. e., affinity) to verify the self-reported business type (i. e., merchant category) of a given merchant.
Online Decision Based Visual Tracking via Reinforcement Learning
A deep visual tracker is typically based on either object detection or template matching while each of them is only suitable for a particular group of scenes.
Adam$^+$: A Stochastic Method with Adaptive Variance Reduction
As a result, Adam$^+$ requires few parameter tuning, as Adam, but it enjoys a provable convergence guarantee.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Saikosaponins with similar structures but different mechanisms lead to combined hepatotoxicity
Previous studies have revealed that saikosaponins are the major types of components that contribute to the hepatotoxicity of Radix Bupleuri.
Latency Minimization for Multiuser Computation Offloading in Fog-Radio Access Networks
This paper considers computation offloading in fog-radio access networks (F-RAN), where multiple user equipments (UEs) offload their computation tasks to the F-RAN through a number of fog nodes.
Sex Differences in Severity and Mortality Among Patients With COVID-19: Evidence from Pooled Literature Analysis and Insights from Integrated Bioinformatic Analysis
Objective: To conduct a meta-analysis of current studies that examined sex differences in severity and mortality in patients with COVID-19, and identify potential mechanisms underpinning these differences.
Diversity in immunogenomics: the value and the challenge
With the advent of high-throughput sequencing technologies, the fields of immunogenomics and adaptive immune receptor repertoire research are facing both opportunities and challenges.
Circles are like Ellipses, or Ellipses are like Circles? Measuring the Degree of Asymmetry of Static and Contextual Embeddings and the Implications to Representation Learning
Human judgments of word similarity have been a popular method of evaluating the quality of word embedding.
Hard-ODT: Hardware-Friendly Online Decision Tree Learning Algorithm and System
Following this, we present Hard-ODT, a high-performance, hardware-efficient and scalable online decision tree learning system on a field-programmable gate array (FPGA) with system-level optimization techniques.
SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II
In this paper, we will share the key insights and optimizations on efficient imitation learning and reinforcement learning for StarCraft II full game.
Anomalous Hall and Nernst Effects in FeRh
Antiferromagnets with tunable phase transitions are promising for future spintronics applications.
Materials Science
Take More Positives: An Empirical Study of Contrastive Learing in Unsupervised Person Re-Identification
By studying two unsupervised person re-ID methods in a cross-method way, we point out a hard negative problem is handled implicitly by their designs of data augmentations and PK sampler respectively.
AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence
With a comprehensive comparison on the performance, power consumption, hardware resource consumption and network generalization capability, we conclude the AdderNet is able to surpass all the other competitors including the classical CNN, novel memristor-network, XNOR-Net and the shift-kernel based network, indicating its great potential in future high performance and energy-efficient artificial intelligence applications.
MUSE: Multi-Scale Temporal Features Evolution for Knowledge Tracing
The proposed model is capable to capture the dynamic changes in users knowledge states at different temporal-ranges, and provides an efficient and powerful way to combine local and global features to make predictions.
Speech Emotion Recognition with Multiscale Area Attention and Data Augmentation
In this paper, we apply multiscale area attention in a deep convolutional neural network to attend emotional characteristics with varied granularities and therefore the classifier can benefit from an ensemble of attentions with different scales.
Boost AI Power: Data Augmentation Strategies with unlabelled Data and Conformal Prediction, a Case in Alternative Herbal Medicine Discrimination with Electronic Nose
Furthermore, this study provides a systematic analysis of different augmentation strategies.
Optically synchronized fiber links with spectrally pure integrated lasers
In this paper we report a record low 3x10^-4 rad^2 residual phase error variance for synchronization based on independent, spectrally pure, ultra-high mutual coherence, photonic integrated lasers.
Optics Applied Physics
Massive Self-Assembly in Grid Environments
Self-assembly plays an essential role in many natural processes, involving the formation and evolution of living or non-living structures, and shows potential applications in many emerging domains.
Multiagent Systems Distributed, Parallel, and Cluster Computing Robotics
Graph-Based Tri-Attention Network for Answer Ranking in CQA
However, they encounter two main limitations: (1) Correlations between answers in the same question are often overlooked.
IPAPRec: A promising tool for learning high-performance mapless navigation skills with deep reinforcement learning
This paper studies how to improve the generalization performance and learning speed of the navigation agents trained with deep reinforcement learning (DRL).
Social Link Inference via Multi-View Matching Network from Spatio-Temporal Trajectories
In this paper, we investigate the problem of social link inference in a target Location-aware Social Network (LSN), which aims at predicting the unobserved links between users within the network.
Zero-shot Adversarial Quantization
To address the above issues, we propose a zero-shot adversarial quantization (ZAQ) framework, facilitating effective discrepancy estimation and knowledge transfer from a full-precision model to its quantized model.
Ranked #2 on
Data Free Quantization
on CIFAR-100
(CIFAR-100 W5A5 Top-1 Accuracy metric)
Fast Beam Training and Alignment for IRS-Assisted Millimeter Wave/Terahertz Systems
Intelligent reflecting surface (IRS) has emerged as a competitive solution to address blockage issues in millimeter wave (mmWave) and Terahertz (THz) communications due to its capability of reshaping wireless transmission environments.
Pneumonia after bacterial or viral infection preceded or followed by radiation exposure -- a reanalysis of older radiobiological data and implications for low dose radiotherapy for COVID-19 pneumonia
For 7 studies that evaluated post-inoculation radiation exposure (more relevant to LDRT for COVID-19 pneumonia) the results are heterogeneous, with 2 studies showing a significant increase (p<0. 001) and another showing a significant decrease (p<0. 001) in mortality associated with radiation exposure.
Source-Free Domain Adaptation for Semantic Segmentation
To cope with this issue, we propose a source-free domain adaptation framework for semantic segmentation, namely SFDA, in which only a well-trained source model and an unlabeled target domain dataset are available for adaptation.
Exploiting Relationship for Complex-scene Image Generation
Our method tends to synthesize plausible layouts and objects, respecting the interplay of multiple objects in an image.
Jittering Effects Analysis and Beam Training Design for UAV Millimeter Wave Communications
In beam training design, with the relationship between attitude angles and AoA/AoD, we propose to generate a rough estimate of AoA and AoD from UAV navigation information.
Hybrid Interference Mitigation Using Analog Prewhitening
This paper proposes a novel scheme for mitigating strong interferences, which is applicable to various wireless scenarios, including full-duplex wireless communications and uncoordinated heterogenous networks.
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
Large-scale distributed training of Deep Neural Networks (DNNs) on state-of-the-art platforms is expected to be severely communication constrained.
Billion-scale Pre-trained E-commerce Product Knowledge Graph Model
As a backbone for online shopping platforms, we built a billion-scale e-commerce product knowledge graph for various item knowledge services such as item recommendation.
Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation
For student morphism, weight inheritance strategy is adopted, allowing the student to flexibly update its architecture while fully utilize the predecessor's weights, which considerably accelerates the search; To facilitate dynamic distillation, an elastic teacher pool is trained via integrated progressive shrinking strategy, from which teacher detectors can be sampled without additional cost in subsequent searches.
Focus on Local: Detecting Lane Marker from Bottom Up via Key Point
Mainstream lane marker detection methods are implemented by predicting the overall structure and deriving parametric curves through post-processing.
Ranked #2 on
Lane Detection
on TuSimple
Model Aided Deep Learning Based MIMO OFDM Receiver With Nonlinear Power Amplifiers
Multi-input multi-output orthogonal frequency division multiplexing (MIMO OFDM) is a key technology for mobile communication systems.
Joint Channel Estimation and Mixed-ADCs Allocation for Massive MIMO via Deep Learning
Instead of randomly assigning the mixed-ADCs, we then design a novel antenna selection network for mixed-ADCs allocation to further improve the channel estimation accuracy.
On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation
In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness.
Summarizing Chinese Medical Answer with Graph Convolution Networks and Question-focused Dual Attention
It is desirable to generate answer summaries for online search engines, particularly summaries that can reveal direct answers to questions.
SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving
Experiments show that SODA10M can serve as a promising pre-training dataset for different self-supervised learning methods, which gives superior performance when fine-tuning with different downstream tasks (i. e., detection, semantic/instance segmentation) in autonomous driving domain.
Learning a Facial Expression Embedding Disentangled From Identity
The facial expression analysis requires a compact and identity-ignored expression representation.
LPSNet: A Lightweight Solution for Fast Panoptic Segmentation
Panoptic segmentation is a challenging task aiming to simultaneously segment objects (things) at instance level and background contents (stuff) at semantic level.
Discrimination-Aware Mechanism for Fine-Grained Representation Learning
Therefore, there is a need for a training mechanism that enforces the discriminativeness of all the elements in the feature to capture more the subtle visual cues.
Prior Aided Streaming Network for Multi-task Affective Recognitionat the 2nd ABAW2 Competition
Automatic affective recognition has been an important research topic in human computer interaction (HCI) area.
Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data
Reinforcement learning (RL)-based auto-pruning has been further proposed to automate the DNN pruning process to avoid expensive hand-crafted work.
Greedy Network Enlarging
Recent studies on deep convolutional neural networks present a simple paradigm of architecture design, i. e., models with more MACs typically achieve better accuracy, such as EfficientNet and RegNet.
Performance assessment and tuning of PID control using TLBO: the single-loop case and PI/P cascade case
Minimum output variance (MOV) is used as a benchmark for CPA of PID, but it is difficult to be found due to the associated non-convex optimization problem.
Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video
In this paper, we introduce a novel task, referred to as Weakly-Supervised Spatio-Temporal Anomaly Detection (WSSTAD) in surveillance video.
Binary Complex Neural Network Acceleration on FPGA
Deep complex networks (DCN), in contrast, can learn from complex data, but have high computational costs; therefore, they cannot satisfy the instant decision-making requirements of many deployable systems dealing with short observations or short signal bursts.
G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation
In this paper, we investigate the knowledge distillation (KD) strategy for object detection and propose an effective framework applicable to both homogeneous and heterogeneous student-teacher pairs.
ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones
To this concern, this work proposes a real-time augmented reality virtual shoe try-on system for smartphones, namely ARShoe.
4-bit Quantization of LSTM-based Speech Recognition Models
We investigate the impact of aggressive low-precision representations of weights and activations in two families of large LSTM-based architectures for Automatic Speech Recognition (ASR): hybrid Deep Bidirectional LSTM - Hidden Markov Models (DBLSTM-HMMs) and Recurrent Neural Network - Transducers (RNN-Ts).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
How Does Adversarial Fine-Tuning Benefit BERT?
Adversarial training (AT) is one of the most reliable methods for defending against adversarial attacks in machine learning.
Deep Person Generation: A Survey from the Perspective of Face, Pose and Cloth Synthesis
Deep person generation has attracted extensive research attention due to its wide applications in virtual agents, video conferencing, online shopping and art/movie production.
On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation
In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness.
Online Multi-horizon Transaction Metric Estimation with Multi-modal Learning in Payment Networks
In this work, we study the problem of multivariate time series prediction for estimating transaction metrics associated with entities in the payment transaction database.
MC$^2$-SF: Slow-Fast Learning for Mobile-Cloud Collaborative Recommendation
With the hardware development of mobile devices, it is possible to build the recommendation models on the mobile side to utilize the fine-grained features and the real-time feedbacks.
Video Temporal Relationship Mining for Data-Efficient Person Re-identification
This paper is a technical report to our submission to the ICCV 2021 VIPriors Re-identification Challenge.
C3-SemiSeg: Contrastive Semi-Supervised Segmentation via Cross-Set Learning and Dynamic Class-Balancing
The semi-supervised semantic segmentation methods utilize the unlabeled data to increase the feature discriminative ability to alleviate the burden of the annotated data.
Exploring Geometry-Aware Contrast and Clustering Harmonization for Self-Supervised 3D Object Detection
Here we present a novel self-supervised 3D Object detection framework that seamlessly integrates the geometry-aware contrast and clustering harmonization to lift the unsupervised 3D representation learning, named GCC-3D.
Embedding Compression with Hashing for Efficient Representation Learning in Graph
When applying such type of networks on graph without node feature, one can extract simple graph-based node features (e. g., number of degrees) or learn the input node representation (i. e., embeddings) when training the network.
Sensoring and Application of Multimodal Data for the Detection of Freezing of Gait in Parkinson's Disease
The accurate and reliable detection or prediction of freezing of gaits (FOG) is important for fall prevention in Parkinson's Disease (PD) and studying the physiological transitions during the occurrence of FOG.
TSK Fuzzy System Towards Few Labeled Incomplete Multi-View Data Classification
The proposed method has the following distinctive characteristics: 1) it can deal with the incomplete and few labeled multi-view data simultaneously; 2) it integrates the missing view imputation and model learning as a single process, which is more efficient than the traditional two-step strategy; 3) attributed to the interpretable fuzzy inference rules, this method is more interpretable.
Asynchronous Decentralized Distributed Training of Acoustic Models
Specifically, we study three variants of asynchronous decentralized parallel SGD (ADPSGD), namely, fixed and randomized communication patterns on a ring as well as a delay-by-one scheme.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Directional Self-supervised Learning for Heavy Image Augmentations
Specifically, we adapt heavy augmentation policies after the views lightly augmented by standard augmentations, to generate harder view (HV).
ViDA-MAN: Visual Dialog with Digital Humans
We demonstrate ViDA-MAN, a digital-human agent for multi-modal interaction, which offers realtime audio-visual responses to instant speech inquiries.
Consensus Graph Learning for Multi-view Clustering
Furthermore, we unify the spectral embedding and low rank tensor learning into a unified optimization framework to determine the spectral embedding matrices and tensor representation jointly.
CAN ALTQ LEARN FASTER: EXPERIMENTS AND THEORY
Differently from the popular Deep Q-Network (DQN) learning, Alternating Q-learning (AltQ) does not fully fit a target Q-function at each iteration, and is generally known to be unstable and inefficient.
Optimizing for In-memory Deep Learning with Emerging Memory Technology
In-memory deep learning has already demonstrated orders of magnitude higher performance density and energy efficiency.
Using Reconfigurable Intelligent Surfaces for UE Positioning in mmWave MIMO Systems
We develop a RIS-aided positioning framework to locate a UE in environments where the LOS path may or may not be available.
Multi-Domain Transformer-Based Counterfactual Augmentation for Earnings Call Analysis
Earnings call (EC), as a periodic teleconference of a publicly-traded company, has been extensively studied as an essential market indicator because of its high analytical value in corporate fundamentals.
Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent
We conduct extensive studies over 18 state-of-the-art DL models/tasks and demonstrate that DPSGD often converges in cases where SSGD diverges for large learning rates in the large batch setting.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization
In this paper, we propose a novel framework built upon the transformer, termed LCTR (Local Continuity TRansformer), which targets at enhancing the local perception capability of global features among long-range feature dependencies.
Error-bounded Approximate Time Series Joins Using Compact Dictionary Representations of Time Series
The matrix profile is an effective data mining tool that provides similarity join functionality for time series data.
Data-Free Knowledge Transfer: A Survey
In this paper, we provide a comprehensive survey on data-free knowledge transfer from the perspectives of knowledge distillation and unsupervised domain adaptation, to help readers have a better understanding of the current research status and ideas.
Responsive Listening Head Generation: A Benchmark Dataset and Baseline
Automatically synthesizing listening behavior that actively responds to a talking head, is critical to applications such as digital human, virtual agents and social robots.
New volatility evolution model after extreme events
Empirical study of the evolutionary behaviors of volatility after endogenous and exogenous events further demonstrates the descriptive power of our new model.
Learning-From-Disagreement: A Model Comparison and Visual Analytics Framework
With these metrics, one can easily identify meta-features with the most complementary behaviors in two classifiers, and use them to better ensemble the classifiers.
