Search Results for author:
Found 137 papers, 41 papers with code
CLIO: Role-interactive Multi-event Head Attention Network for Document-level Event Extraction
Transforming the large amounts of unstructured text on the Internet into structured event knowledge is a critical, yet unsolved goal of NLP, especially when addressing document-level text.
Multimodal Sarcasm Target Identification in Tweets
Sarcasm is important to sentiment analysis on social media.
Towards Better Entity Linking with Multi-View Enhanced Distillation
Aiming at learning entity representations that can match divergent mentions, this paper proposes a Multi-View Enhanced Distillation (MVD) framework, which can effectively transfer knowledge of multiple fine-grained and mention-relevant parts within entities from cross-encoders to dual-encoders.
DeepGate2: Functionality-Aware Circuit Representation Learning
Circuit representation learning aims to obtain neural representations of circuit elements and has emerged as a promising research direction that can be applied to various EDA and logic reasoning tasks.
Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study
Our study investigates three key research questions: (1) the number of different prompt types that can jailbreak LLMs, (2) the effectiveness of jailbreak prompts in circumventing LLM constraints, and (3) the resilience of ChatGPT against these jailbreak prompts.
Automatic Code Summarization via ChatGPT: How Far Are We?
To support software developers in understanding and maintaining programs, various automatic code summarization techniques have been proposed to generate a concise natural language comment for a given code snippet.
Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter
However, as pre-trained language models (PLMs) continue to increase in size, the communication cost for transmitting parameters during synchronization has become a training speed bottleneck.
SFP: Spurious Feature-targeted Pruning for Out-of-Distribution Generalization
Based on the idea that in-distribution (ID) data with spurious features may have a lower experience risk, in this paper, we propose a novel Spurious Feature-targeted model Pruning framework, dubbed SFP, to automatically explore invariant substructures without referring to the above drawbacks.
SegGPT Meets Co-Saliency Scene
Co-salient object detection targets at detecting co-existed salient objects among a group of images.
AsConvSR: Fast and Lightweight Super-Resolution Network with Assembled Convolutions
In recent years, videos and images in 720p (HD), 1080p (FHD) and 4K (UHD) resolution have become more popular for display devices such as TVs, mobile phones and VR.
DETRs Beat YOLOs on Real-time Object Detection
In this paper, we first analyze the influence of NMS in modern real-time object detectors on inference speed, and establish an end-to-end speed benchmark.
PP-MobileSeg: Explore the Fast and Accurate Semantic Segmentation Model on Mobile Devices
To address this issue, we propose PP-MobileSeg, a semantic segmentation model that achieves state-of-the-art performance on mobile devices.
Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection
When extracting object knowledge from PVLMs, the former adaptively transforms object proposals and adopts object-aware mask attention to obtain precise and complete knowledge of objects.
Ranked #6 on
Open Vocabulary Object Detection
on MSCOCO
Angel-PTM: A Scalable and Economical Large-scale Pre-training System in Tencent
Recent years have witnessed the unprecedented achievements of large-scale pre-trained models, especially the Transformer models.
Video4MRI: An Empirical Study on Brain Magnetic Resonance Image Analytics with CNN-based Video Classification Frameworks
Due to the high similarity between MRI data and videos, we conduct extensive empirical studies on video recognition techniques for MRI classification to answer the questions: (1) can we directly use video recognition models for MRI classification, (2) which model is more appropriate for MRI, (3) are the common tricks like data augmentation in video recognition still useful for MRI classification?
XFL: A High Performace, Lightweighted Federated Learning Framework
This paper introduces XFL, an industrial-grade federated learning project.
Knowledge Enhancement for Contrastive Multi-Behavior Recommendation
In particular, we design the multi-behavior learning module to extract users' personalized behavior information for user-embedding enhancement, and utilize knowledge graph in the knowledge enhancement module to derive more robust knowledge-aware representations for items.
Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models
Preference-based reinforcement learning (PbRL) can enable robots to learn to perform tasks based on an individual's preferences without requiring a hand-crafted reward function.
SIRL: Similarity-based Implicit Representation Learning
This, in turn, is what enables the robot to disambiguate between what needs to go into the representation versus what is spurious, as well as what aspects of behavior can be compressed together versus not.
Efficient Stein Variational Inference for Reliable Distribution-lossless Network Pruning
Extensive experiments based on small Cifar-10 and large-scaled ImageNet demonstrate that our method can obtain sparser networks with great generalization performance while providing quantified reliability for the pruned model.
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
Specifically, InternVideo efficiently explores masked video modeling and video-language contrastive learning as the pretraining objectives, and selectively coordinates video representations of these two complementary frameworks in a learnable manner to boost various video applications.
Ranked #1 on
Open Set Action Recognition
on UCF101-MiTv2
InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges
In this report, we present our champion solutions to five tracks at Ego4D challenge.
Ranked #1 on
State Change Object Detection
on Ego4D
CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streaming
Recent years have witnessed the dramatic growth of Internet video traffic, where the video bitstreams are often compressed and delivered in low quality to fit the streamer's uplink bandwidth.
Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning
We prove that FedFoA is a model-agnostic training framework and can be easily compatible with state-of-the-art unsupervised FL methods.
PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector
With multi-scale training and testing, PP-YOLOE-R-l and PP-YOLOE-R-x further improve the detection precision to 80. 02 and 80. 73 mAP.
Ranked #2 on
Oriented Object Detection
on DOTA 1.0
MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction
In this work, we define the task of Medical-domain Chinese Spelling Correction and propose MCSCSet, a large scale specialist-annotated dataset that contains about 200k samples.
VideoPipe 2022 Challenge: Real-World Video Understanding for Urban Pipe Inspection
For this reason, we propose to advance research areas of video understanding, with a shift from traditional action recognition to industrial anomaly analysis.
RAIS: Robust and Accurate Interactive Segmentation via Continual Learning
Interactive image segmentation aims at segmenting a target region through a way of human-computer interaction.
EISeg: An Efficient Interactive Segmentation Tool based on PaddlePaddle
In recent years, the rapid development of deep learning has brought great advancements to image and video segmentation methods based on neural networks.
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation
Furthermore, RAP can be naturally combined with many existing black-box attack techniques, to further boost the transferability.
PP-StructureV2: A Stronger Document Analysis System
For Table Recognition model, we utilize PP-LCNet, CSP-PAN and SLAHead to optimize the backbone module, feature fusion module and decoding module, respectively, which improved the table structure accuracy by 6\% with comparable inference speed.
Ranked #3 on
Table Recognition
on PubTabNet
FAST: Improving Controllability for Text Generation with Feedback Aware Self-Training
Controllable text generation systems often leverage control codes to direct various properties of the output like style and length.
Periodic Graph Transformers for Crystal Material Property Prediction
Our Matformer is designed to be invariant to periodicity and can capture repeating patterns explicitly.
Ranked #1 on
Band Gap
on JARVIS-DFT
A Nonparametric Contextual Bandit with Arm-level Eligibility Control for Customer Service Routing
Routing contacts to eligible SMEs turns out to be a non-trivial problem because SMEs' domain eligibility is subject to training quality and can change over time.
DeepGen: Diverse Search Ad Generation and Real-Time Customization
In addition, our system creates a customized ad in real-time in response to the user's search query, therefore highlighting different aspects of the same product based on what the user is looking for.
Ultra-low Latency Adaptive Local Binary Spiking Neural Network with Accuracy Loss Estimator
Spiking neural network (SNN) is a brain-inspired model which has more spatio-temporal information processing capacity and computational energy efficiency.
Learning Hierarchical Protein Representations via Complete 3D Graph Networks
In this work, we propose to develop a novel hierarchical graph network, known as ProNet, to capture the relations.
An Ultra-low Power TinyML System for Real-time Visual Processing at Edge
Tiny machine learning (TinyML), executing AI workloads on resource and power strictly restricted systems, is an important and challenging topic.
Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models
Though image classification datasets could provide the backbone networks with rich visual features and discriminative ability, they are incapable of fully pre-training the target model (i. e., backbone+segmentation modules) in an end-to-end manner.
Assessing the Effects of Hyperparameters on Knowledge Graph Embedding Quality
We regressed the embedding quality on those hyperparameter configurations, using this model to generate Sobol sensitivity indices for each of the hyperparameters.
Tell Me the Evidence? Dual Visual-Linguistic Interaction for Answer Grounding
Answer grounding aims to reveal the visual evidence for visual question answering (VQA), which entails highlighting relevant positions in the image when answering questions about images.
ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs
To incorporate 3D information completely and efficiently, we propose a novel message passing scheme that operates within 1-hop neighborhood.
Multiple Domain Cyberspace Attack and Defense Game Based on Reward Randomization Reinforcement Learning
In order to improve the defense ability of defender, a game model based on reward randomization reinforcement learning is proposed.
KGRGRL: A User's Permission Reasoning Method Based on Knowledge Graph Reward Guidance Reinforcement Learning
Following that, we proposed a user's permissions reasoning method based on reinforcement learning.
Improved-Flow Warp Module for Remote Sensing Semantic Segmentation
Second, the offsets help with the low-resolution deep feature up-sampling process to improve the feature accordance, which boosts the accuracy of semantic segmentation.
PP-Matting: High-Accuracy Natural Image Matting
Also, we propose a semantic context branch (SCB) that adopts a semantic segmentation subtask.
Ranked #2 on
Image Matting
on Distinctions-646
PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model
Real-world applications have high demands for semantic segmentation methods.
Ranked #4 on
Real-Time Semantic Segmentation
on Cityscapes val
Rotated Object Detection via Scale-invariant Mahalanobis Distance in Aerial Images
The eight-parameter (coordinates of box vectors) methods in rotated object detection usually use ln-norm losses (L1 loss, L2 loss, and smooth L1 loss) as loss functions.
Ultra-low Latency Spiking Neural Networks with Spatio-Temporal Compression and Synaptic Convolutional Block
We evaluate the proposed method for event streams classification tasks on neuromorphic N-MNIST, CIFAR10-DVS, DVS128 gesture datasets.
The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining
Existing machine unlearning techniques focus on centralized training, where access to all holders' training data is a must for the server to conduct the unlearning process.
A practical framework for multi-domain speech recognition and an instance sampling method to neural language modeling
Automatic speech recognition (ASR) systems used on smart phones or vehicles are usually required to process speech queries from very different domains.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
The Volcspeech system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge
For Track 1, we propose several approaches to empower the clustering-based speaker diarization system to handle overlapped speech.
Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization
In this paper, we present a system design which offers efficient protection of individual model updates throughout the learning procedure, allowing clients to only provide obscured model updates while a cloud server can still perform the aggregation.
Distributional Reinforcement Learning via Sinkhorn Iterations
Distributional reinforcement learning~(RL) is a class of state-of-the-art algorithms that estimate the entire distribution of the total return rather than only its expectation.
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.
FamilySeer: Towards Optimized Tensor Codes by Exploiting Computation Subgraph Similarity
Currently, the DL compilers partition the input DL models into several subgraphs and leverage the auto-tuning to find the optimal tensor codes of these subgraphs.
EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate
Then it diversifies the experts and continues to train the MoE with a novel Dense-to-Sparse gate (DTS-Gate).
PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset
This work is the first to construct a large-scale video portrait dataset that contains 291 videos from 23 conference scenes with 14K fine-labeled frames and extensions to multi-camera teleconferencing.
Direct Training via Backpropagation for Ultra-low Latency Spiking Neural Networks with Multi-threshold
In our proposed training method, we proposed three approximated derivative for spike activity to solve the problem of the non-differentiable issue which cause difficulties for direct training SNNs based on BP.
Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization
Anderson mixing has been heuristically applied to reinforcement learning (RL) algorithms for accelerating convergence and improving the sampling efficiency of deep RL.
Locally Adaptive Structure and Texture Similarity for Image Quality Assessment
The latest advances in full-reference image quality assessment (IQA) involve unifying structure and texture similarity based on deep representations.
Resource-constrained Federated Edge Learning with Heterogeneous Data: Formulation and Analysis
Similarly, due to the heterogeneity of the connected remote devices, FEEL faces the challenge of heterogeneous data and non-IID (Independent and Identically Distributed) data.
Dyn-Backdoor: Backdoor Attack on Dynamic Link Prediction
Backdoor attacks induce the DLP methods to make wrong prediction by the malicious training data, i. e., generating a subgraph sequence as the trigger and embedding it to the training data.
Interpreting Distributional Reinforcement Learning: A Regularization Perspective
Distributional reinforcement learning~(RL) is a class of state-of-the-art algorithms that estimate the whole distribution of the total return rather than only its expectation.
Gaussian Differential Privacy Transformation: from identification to application
Gaussian differential privacy (GDP) is a single-parameter family of privacy notions that provides coherent guarantees to avoid the exposure of individuals from machine learning models.
Towards Understanding Distributional Reinforcement Learning: Regularization, Optimization, Acceleration and Sinkhorn Algorithm
Distributional reinforcement learning~(RL) is a class of state-of-the-art algorithms that estimate the whole distribution of the total return rather than only its expectation.
Exploring the Robustness of Distributional Reinforcement Learning against Noisy State Observations
In real scenarios, state observations that an agent observes may contain measurement errors or adversarial noises, misleading the agent to take suboptimal actions or even collapse while training.
Distributional Reinforcement Learning
reinforcement-learning
+1
BioCopy: A Plug-And-Play Span Copy Mechanism in Seq2Seq Models
Copy mechanisms explicitly obtain unchanged tokens from the source (input) sequence to generate the target (output) sequence under the neural seq2seq framework.
How Does Knowledge Graph Embedding Extrapolate to Unseen Data: A Semantic Evidence View
However, most existing KGE works focus on the design of delicate triple modeling function, which mainly tells us how to measure the plausibility of observed triples, but offers limited explanation of why the methods can extrapolate to unseen data, and what are the important factors to help KGE extrapolate.
Ranked #10 on
Link Prediction
on FB15k-237
EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow
In addition, with the proposed method, we develop an efficient interactive segmentation tool for practical data annotation tasks.
Ranked #2 on
Interactive Segmentation
on PASCAL VOC
(NoC@85 metric)
Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observations
In real scenarios, state observations that an agent observes may contain measurement errors or adversarial noises, misleading the agent to take suboptimal actions or even collapse while training.
BoA-PTA, A Bayesian Optimization Accelerated Error-Free SPICE Solver
One of the greatest challenges in IC design is the repeated executions of computationally expensive SPICE simulations, particularly when highly complex chip testing/verification is involved.
Swap-Free Fat-Water Separation in Dixon MRI using Conditional Generative Adversarial Networks
Using data from the UK Biobank Dixon MRI, our model is able to predict highly accurate fat and water channels that are free from artifacts.
EGC2: Enhanced Graph Classification with Easy Graph Compression
To achieve lower-complexity defense applied to graph classification models, EGC2 utilizes a centrality-based edge-importance index to compress the graphs, filtering out trivial structures and adversarial perturbations in the input graphs, thus improving the model's robustness.
Markov Decision Process modeled with Bandits for Sequential Decision Making in Linear-flow
For marketing, we sometimes need to recommend content for multiple pages in sequence.
A Map of Bandits for E-commerce
The rich body of Bandit literature not only offers a diverse toolbox of algorithms, but also makes it hard for a practitioner to find the right solution to solve the problem at hand.
Mask-Embedded Discriminator With Region-Based Semantic Regularization for Semi-Supervised Class-Conditional Image Synthesis
Semi-supervised generative learning (SSGL) makes use of unlabeled data to achieve a trade-off between the data collection/annotation effort and generation performance, when adequate labeled data are not available.
Optical Mouse: 3D Mouse Pose From Single-View Video
We present a method to infer the 3D pose of mice, including the limbs and feet, from monocular videos.
FineAction: A Fine-Grained Video Dataset for Temporal Action Localization
Temporal action localization (TAL) is an important and challenging problem in video understanding.
Machine Learning Regression based Single Event Transient Modeling Method for Circuit-Level Simulation
A multilayer feedfordward neural network is used to build the SET pulse current model by learning the data from TCAD simulation.
DIG: A Turnkey Library for Diving into Graph Deep Learning Research
Although there exist several libraries for deep learning on graphs, they are aiming at implementing basic operations for graph deep learning.
Sent2Matrix: Folding Character Sequences in Serpentine Manifolds for Two-Dimensional Sentence
We study text representation methods using deep models.
The ADENUIM Telescope- A new beam telescope for the DESY II Test Beam Facility
The coincident signal of all scintillators is used as trigger and then used as a trigger and distributed to the entire system, including all the telescope planes and any devices under test from test beam users.
Instrumentation and Detectors Instrumentation and Methods for Astrophysics High Energy Physics - Experiment
Spherical Message Passing for 3D Graph Networks
Based on such observations, we propose the spherical message passing (SMP) as a novel and powerful scheme for 3D molecular learning.
PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation
The toolkit aims to help both developers and researchers in the whole process of designing segmentation models, training models, optimizing performance and inference speed, and deploying models.
A Multi-Stage Attentive Transfer Learning Framework for Improving COVID-19 Diagnosis
The method is then integrated to the last stage of the proposed transfer learning framework to reuse the complex patterns learned from the same CT images.
CleftNet: Augmented Deep Learning for Synaptic Cleft Detection from Brain Electron Microscopy
The effectiveness of our methods is evaluated on both online and offline tasks.
Social Media, Content Moderation, and Technology
This means that platforms under different revenue models can have different incentives to improve their content moderation technology.
Semi-Supervised Single-Stage Controllable GANs for Conditional Fine-Grained Image Generation
To ensure disentanglement among the variables, we maximize mutual information between the class-independent variable and synthesized images, map real images to the latent space of a generator to perform consistency regularization of cross-class attributes, and incorporate class semantic-based regularization into a discriminator's feature space.
Poisoning Semi-supervised Federated Learning via Unlabeled Data: Attacks and Defenses
Extensive case studies have shown that our attacks are effective on different datasets and common semi-supervised learning methods.
Towards Communication-efficient and Attack-Resistant Federated Edge Learning for Industrial Internet of Things
Second, we propose an asynchronous local differential privacy mechanism, which improves communication efficiency and mitigates gradient leakage attacks by adding well-designed noise to the gradients of edge nodes.
A Systematic Literature Review on Federated Learning: From A Model Quality Perspective
In this process, the server uses an incentive mechanism to encourage clients to contribute high-quality and large-volume data to improve the global model.
Topology-Aware Graph Pooling Networks
In addition, graph topology is incorporated in global voting to compute the importance score of each node globally in the entire graph.
Large-Scale Analysis of Iliopsoas Muscle Volumes in the UK Biobank
We also found that iliopsoas volume was significantly related to height, BMI and age, and that there was an acceleration in muscle volume decrease in men with age.
Scalable and Communication-efficient Decentralized Federated Edge Learning with Multi-blockchain Framework
This framework can achieve scalable and flexible decentralized FEL by individually manage local model updates or model sharing records for performance isolation.
Cryptography and Security
PR-NN: RNN-based Detection for Coded Partial-Response Channels
In this paper, we investigate the use of recurrent neural network (RNN)-based detection of magnetic recording channels with inter-symbol interference (ISI).
Machine Learning Explanations to Prevent Overtrust in Fake News Detection
Combating fake news and misinformation propagation is a challenging task in the post-truth era.
Federated Learning in the Sky: Aerial-Ground Air Quality Sensing Framework with UAV Swarms
To this end, this paper proposes a new federated learning-based aerial-ground air quality sensing framework for fine-grained 3D air quality monitoring and forecasting.
Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approach
Third, to adapt the proposed framework to the timeliness of industrial anomaly detection, we propose a gradient compression mechanism based on Top-\textit{k} selection to improve communication efficiency.
Deep Learning of High-Order Interactions for Protein Interface Prediction
However, these methods do not incorporate the important sequential information from amino acid chains and the high-order pairwise interactions.
Protein Interface Prediction
Vocal Bursts Intensity Prediction
Image Processing and Quality Control for Abdominal Magnetic Resonance Imaging in the UK Biobank
An end-to-end image analysis pipeline is presented for the abdominal MRI protocol used in the UK Biobank on the first 38, 971 participants.
Variable Selection via Thompson Sampling
Thompson sampling is a heuristic algorithm for the multi-armed bandit problem which has a long tradition in machine learning.
BIG-bench Machine Learning
Interpretable Machine Learning
+3
Assessing the Impact of COVID-19 on the Objective and Analysis of Oncology Clinical Trials -- Application of the Estimand Framework
We identify key intercurrent events that may occur due to COVID-19 in oncology clinical trials with a focus on time-to-event endpoints and discuss considerations pertaining to the other estimand attributes introduced in the ICH E9 addendum.
Federated Learning for 6G Communications: Challenges, Methods, and Future Directions
As the 5G communication networks are being widely deployed worldwide, both industry and academia have started to move beyond 5G and explore 6G communications.
Regularizing Discriminative Capability of CGANs for Semi-Supervised Generative Learning
Semi-supervised generative learning aims to learn the underlying class-conditional distribution of partially labeled data.
Exemplar-based Generative Facial Editing
Image synthesis has witnessed substantial progress due to the increasing power of generative model.
Networks with pixels embedding: a method to improve noise resistance in images classification
In the task of image classification, usually, the network is sensitive to noises.
An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties
Realizing general inverse design could greatly accelerate the discovery of new materials with user-defined properties.
Activation functions are not needed: the ratio net
We compare the effectiveness and efficiency of the ratio net and that of the RBF and the MLP with various kinds of activation functions in the classification task on the mnist database of handwritten digits and the Internet Movie Database (IMDb) which is a binary sentiment analysis dataset.
A Secure Federated Learning Framework for 5G Networks
In this article, we propose a blockchain-based secure FL framework to create smart contracts and prevent malicious or unreliable participants from involving in FL.
Privacy-preserving Traffic Flow Prediction: A Federated Learning Approach
Through extensive case studies on a real-world dataset, it is shown that FedGRU's prediction accuracy is 90. 96% higher than the advanced deep learning models, which confirm that FedGRU can achieve accurate and timely traffic prediction without compromising the privacy and security of raw data.
The Deep Learning Compiler: A Comprehensive Survey
In this paper, we perform a comprehensive survey of existing DL compilers by dissecting the commonly adopted design in details, with emphasis on the DL oriented multi-level IRs, and frontend/backend optimizations.
MulGAN: Facial Attribute Editing by Exemplar
These methods encode attribute-related information in images into the predefined region of the latent feature space by employing a pair of images with opposite attributes as input to train model, the face attribute transfer between the input image and the exemplar can be achieved by exchanging their attribute-related latent feature region.
THUEE system description for NIST 2019 SRE CTS Challenge
This paper describes the systems submitted by the department of electronic engineering, institute of microelectronics of Tsinghua university and TsingMicro Co. Ltd. (THUEE) to the NIST 2019 speaker recognition evaluation CTS challenge.
PPGAN: Privacy-preserving Generative Adversarial Network
To address this issue, we propose a Privacy-preserving Generative Adversarial Network (PPGAN) model, in which we achieve differential privacy in GANs by adding well-designed noise to the gradient during the model learning procedure.
Employing Deep Part-Object Relationships for Salient Object Detection
In the second step, we feed the primary capsules into two identical streams, within each of which low-level capsules (parts) will be assigned to their familiar high-level capsules (object) via a locally connected routing.
Building Change Detection for Remote Sensing Images Using a Dual Task Constrained Deep Siamese Convolutional Network Model
In recent years, building change detection methods have made great progress by introducing deep learning, but they still suffer from the problem of the extracted features not being discriminative enough, resulting in incomplete regions and irregular boundaries.
Building change detection for remote sensing images
Change Detection
+3
Open DNN Box by Power Side-Channel Attack
However, recent studies indicate that they are also vulnerable to adversarial attacks.
Global Pixel Transformers for Virtual Staining of Microscopy Images
It is also shown that our proposed global pixel transformer layer is useful to improve the fluorescence image prediction results.
MV-C3D: A Spatial Correlated Multi-View 3D Convolutional Neural Networks
Experimental results on ModelNet10 and ModelNet40 datasets show that our MV-C3D technique can achieve outstanding performance with multi-view images which are captured from partial angles with less range.
Normalization Gradients are Least-squares Residuals
Batch Normalization (BN) and its variants have seen widespread adoption in the deep learning community because they improve the training of deep neural networks.
Estimation of Inter-Sentiment Correlations Employing Deep Neural Network Models
By contrast, in objective news bodies and titles, it is easy to regard text as caused love (gd).
DSNet: Deep and Shallow Feature Learning for Efficient Visual Tracking
In recent years, Discriminative Correlation Filter (DCF) based tracking methods have achieved great success in visual tracking.
An Efficient Bandit Algorithm for Realtime Multivariate Optimization
We further apply our algorithm to optimize a message that promotes adoption of an Amazon service.
A Multi-sentiment-resource Enhanced Attention Network for Sentiment Classification
Deep learning approaches for sentiment classification do not fully exploit sentiment linguistic knowledge.
Ranked #4 on
Sentiment Analysis
on MR
Multi-glance Reading Model for Text Understanding
Based on the multi-glance mechanism, we design two types of recurrent neural network models for repeated reading: Glance Cell Model (GCM) and Glance Gate Model (GGM).
Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network
Human generates responses relying on semantic and functional dependencies, including coreference relation, among dialogue elements and their context.
Ranked #6 on
Conversational Response Selection
on RRS
Multi-Modal Coreference Resolution with the Correlation between Space Structures
In this paper, we bring a extrinsic correlation between the space structures of each modalities in coreference resolution.
Comparison of Multiple Features and Modeling Methods for Text-dependent Speaker Verification
Additionally, we also find that even though bottleneck features perform well for text-independent speaker verification, they do not outperform MFCCs on the most challenging Imposter-Correct trials on RedDots.
Teaching Compositionality to CNNs
Convolutional neural networks (CNNs) have shown great success in computer vision, approaching human-level performance when trained for specific tasks via application-specific loss functions.
Sparse Representation based Multi-sensor Image Fusion: A Review
As a result of several successful applications in computer vision and image processing, sparse representation (SR) has attracted significant attention in multi-sensor image fusion.
A backward pass through a CNN using a generative model of its activations
Neural networks have shown to be a practical way of building a very complex mapping between a pre-specified input space and output space.
Hierarchical compositional feature learning
We introduce the hierarchical compositional network (HCN), a directed generative model able to discover and disentangle, without supervision, the building blocks of a set of binary images.
Formula of Volume of Revolution with Integration by Parts and Extension
A calculation formula of volume of revolution with integration by parts of definite integral is derived based on monotone function, and extended to a general case that curved trapezoids is determined by continuous, piecewise strictly monotone and differential function.
