Search Results for author:
Found 135 papers, 64 papers with code
A Timestep aware Sentence Embedding and Acme Coverage for Brief but Informative Title Generation
The title generation task that summarizes article content in recapitulatory words relies heavily on utilizing the corresponding key context.
MagCache: Fast Video Generation with Magnitude-Aware Cache
Existing acceleration techniques for video diffusion models often rely on uniform heuristics or time-embedding variants to skip timesteps and reuse cached features.
MiniCPM4: Ultra-Efficient LLMs on End Devices
Specifically, in terms of model architecture, we propose InfLLM v2, a trainable sparse attention mechanism that accelerates both prefilling and decoding phases for long-context processing.
CLIP-aware Domain-Adaptive Super-Resolution
This work introduces CLIP-aware Domain-Adaptive Super-Resolution (CDASR), a novel framework that addresses the critical challenge of domain generalization in single image super-resolution.
Differentiable NMS via Sinkhorn Matching for End-to-End Fabric Defect Detection
Addressing these limitations, we propose a differentiable NMS framework for fabric defect detection that achieves superior localization precision through end-to-end optimization.
ReaderLM-v2: Small Language Model for HTML to Markdown and JSON
We present ReaderLM-v2, a compact 1. 5 billion parameter language model designed for efficient web content extraction.
UD-Mamba: A pixel-level uncertainty-driven Mamba model for medical image segmentation
Recent advancements have highlighted the Mamba framework, a state-space model known for its efficiency in capturing long-range dependencies with linear computational complexity.
EFKAN: A KAN-Integrated Neural Operator For Efficient Magnetotelluric Forward Modeling
Neural operators (NOs) have been effectively used for rapid MT forward modeling, demonstrating their promising performance in solving the MT forward modeling-related partial differential equations (PDEs).
CausalSR: Structural Causal Model-Driven Super-Resolution with Counterfactual Inference
We propose a novel counterfactual learning strategy that leverages semantic guidance to reason about hypothetical degradation scenarios, leading to theoretically-grounded representations that capture invariant features across different degradation conditions.
LayerAnimate: Layer-specific Control for Animation
In this paper, we introduce LayerAnimate, a novel architectural approach that enhances fine-grained control over individual animation layers within a video diffusion model, allowing users to independently manipulate foreground and background elements in distinct layers.
Mamba-Reg: Vision Mamba Also Needs Registers
Qualitative observations suggest, compared to vanilla Vision Mamba, MambaReg's feature maps appear cleaner and more focused on semantically meaningful regions.
Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency
In this work, we introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual representations.
Single-image reflection removal via self-supervised diffusion models
Reflections often degrade the visual quality of images captured through transparent surfaces, and reflection removal methods suffers from the shortage of paired real-world samples. This paper proposes a hybrid approach that combines cycle-consistency with denoising diffusion probabilistic models (DDPM) to effectively remove reflections from single images without requiring paired training data.
HEP-NAS: Towards Efficient Few-shot Neural Architecture Search via Hierarchical Edge Partitioning
One-shot methods have significantly advanced the field of neural architecture search (NAS) by adopting weight-sharing strategy to reduce search costs.
Towards Flexible 3D Perception: Object-Centric Occupancy Completion Augments 3D Object Detection
Recognizing that foreground objects only occupy a small portion of the scene, we introduce object-centric occupancy as a supplement to object bboxes.
CovidLLM: A Robust Large Language Model with Missing Value Adaptation and Multi-Objective Learning Strategy for Predicting Disease Severity and Clinical Outcomes in COVID-19 Patients
We started by selecting serological indicators that significantly correlate with clinical outcomes and disease severity to serve as input data for the model.
M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation
In this paper, we show that this scale-wise autoregressive framework can be effectively decoupled into \textit{intra-scale modeling}, which captures local spatial dependencies within each scale, and \textit{inter-scale modeling}, which models cross-scale relationships progressively from coarse-to-fine scales.
An Overview on IRS-Enabled Sensing and Communications for 6G: Architectures, Fundamental Limits, and Joint Beamforming Designs
Next, we consider a single IRS to facilitate integrated sensing and communication (ISAC), in which the transmit signals at the BS are used for achieving both S&C functionalities, aided by the IRS through reflective beamforming.
Semi-supervised Chinese Poem-to-Painting Generation via Cycle-consistent Adversarial Networks
In this work, we propose a semi-supervised approach using cycle-consistent adversarial networks to leverage the limited paired data and large unpaired corpus of poems and paintings.
Causal Image Modeling for Efficient Visual Understanding
In this work, we present a comprehensive analysis of causal image modeling and introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual representations.
jina-embeddings-v3: Multilingual Embeddings With Task LoRA
We introduce jina-embeddings-v3, a novel text embedding model with 570 million parameters, achieves state-of-the-art performance on multilingual data and long-context retrieval tasks, supporting context lengths of up to 8192 tokens.
Unsupervised Stereo Matching Network For VHR Remote Sensing Images Based On Error Prediction
In contrast, unsupervised learning methods can leverage the increasing availability of very-high-resolution (VHR) remote sensing images, offering considerable potential in the realm of stereo matching.
Rethinking the Key Factors for the Generalization of Remote Sensing Stereo Matching Networks
Stereo matching, a critical step of 3D reconstruction, has fully shifted towards deep learning due to its strong feature representation of remote sensing images.
Respiratory Subtraction for Pulmonary Microwave Ablation Evaluation
The experimental results confirm the effectiveness of the respiratory subtraction method and the proposed quantitative evaluation metric in assessing lung tumor treatment.
Intermittent Semi-working Mask: A New Masking Paradigm for LLMs
In this way, ISM is able to maintain the high quality of prefix LLM and low generation latency of causal LLM, simultaneously.
YuLan: An Open-source Large Language Model
This paper presents the development of YuLan, a series of open-source LLMs with $12$ billion parameters.
SSNVC: Single Stream Neural Video Compression with Implicit Temporal Information
Recently, Neural Video Compression (NVC) techniques have achieved remarkable performance, even surpassing the best traditional lossy video codec.
Autoregressive Pretraining with Mamba in Vision
The vision community has started to build with the recently developed state space model, Mamba, as the new backbone for a range of tasks.
Large-Scale Contextual Market Equilibrium Computation through Deep Learning
Motivated by this, our paper investigates the computation of market equilibrium in scenarios with a large-scale buyer population, where buyers and goods are represented by their contexts.
SCALM: Towards Semantic Caching for Automated Chat Services with Large Language Models
In this work, we for the first time conducted an analysis on real-world human-to-LLM interaction data, identifying key challenges in existing caching solutions for LLM-based chat services.
Mamba-R: Vision Mamba ALSO Needs Registers
Similar to Vision Transformers, this paper identifies artifacts also present within the feature maps of Vision Mamba.
Feature-based Federated Transfer Learning: Communication Efficiency, Robustness and Privacy
In this paper, we propose feature-based federated transfer learning as a novel approach to improve communication efficiency by reducing the uplink payload by multiple orders of magnitude compared to that of existing approaches in federated learning and federated transfer learning.
Expensive Multi-Objective Bayesian Optimization Based on Diffusion Models
In this paper, we propose a novel Composite Diffusion Model based Pareto Set Learning algorithm, namely CDM-PSL, for expensive MOBO.
Towards Accurate and Efficient Sorting of Retired Lithium-ion Batteries: A Data Driven Based Electrode Aging Assessment Approach
Next, a rapid estimation algorithm is proposed to identify the three electrode aging parameters (EAPs) which best reconstruct the 15 OCV feature points over the entire usable capacity range.
V3D: Video Diffusion Models are Effective 3D Generators
To fully unleash the potential of video diffusion to perceive the 3D world, we further introduce geometrical consistency prior and extend the video diffusion model to a multi-view consistent 3D generator.
VisRec: A Semi-Supervised Approach to Radio Interferometric Data Reconstruction
This hybrid approach allows VisRec to effectively leverage both labeled and unlabeled data.
An Integrated Data Processing Framework for Pretraining Foundation Models
The ability of the foundation models heavily relies on large-scale, diverse, and high-quality pretraining data.
Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings
We introduce a novel suite of state-of-the-art bilingual text embedding models that are designed to support English and another target language.
Low-Dose CT Reconstruction Using Dataset-free Learning
Although supervised-deep-learning-based reconstruction methods have demonstrated superior performance compared to conventional model-driven reconstruction algorithms, they require collecting massive pairs of low-dose and norm-dose CT images for neural network training, which limits their practical application in LDCT imaging.
Seismic Traveltime Tomography with Label-free Learning
To avoid generating and/or collecting labeled samples, we propose a novel method by integrating deep learning and dictionary learning to enhance the VMs with low resolution by using the traditional tomography-least square method (LSQR).
City Scene Super-Resolution via Geometric Error Minimization
Super-resolution techniques are crucial in improving image granularity, particularly in complex urban scenes, where preserving geometric structures is vital for data-informed cultural heritage applications.
Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications
The advancements in speed and efficiency of DCNv4, combined with its robust performance across diverse vision tasks, show its potential as a foundational building block for future vision models.
LightHouse: A Survey of AGI Hallucination
With the development of artificial intelligence, large-scale models have become increasingly intelligent.
ClassWise-SAM-Adapter: Parameter Efficient Fine-tuning Adapts Segment Anything to SAR Domain for Semantic Segmentation
Compared to conventional state-of-the-art semantic segmentation algorithms by extensive experiments, CWSAM showcases enhanced performance with fewer computing resources, highlighting the potential of leveraging foundational models like SAM for specific downstream tasks in the SAR domain.
PolarRec: Improving Radio Interferometric Data Reconstruction Using Polar Coordinates
Unfortunately existing reconstruction methods often miss some components of visibility in frequency domain so blurred object edges and persistent artifacts remain in the images.
QGFace: Quality-Guided Joint Training For Mixed-Quality Face Recognition
We propose a novel quality-guided joint training approach for mixed-quality face recognition, which could simultaneously learn the images of different qualities with a single encoder.
MM-TTS: Multi-modal Prompt based Style Transfer for Expressive Text-to-Speech Synthesis
The challenges of modeling such a multi-modal style controllable TTS mainly lie in two aspects:1)aligning the multi-modal information into a unified style space to enable the input of arbitrary modality as the style prompt in a single system, and 2)efficiently transferring the unified style representation into the given text content, thereby empowering the ability to generate prompt style-related voice.
Scientific Preparation for CSST: Classification of Galaxy and Nebula/Star Cluster Based on Deep Learning
Real-time identification of galaxy and nebula/star cluster (abbreviated as NSC) images is of great value during CSST survey.
SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference
Specifically, we replace the traditional self-attention block of CLIP vision encoder's last layer by our CSA module and reuse its pretrained projection matrices of query, key, and value, leading to a training-free adaptation approach for CLIP's zero-shot semantic segmentation.
GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting
3D editing plays a crucial role in many areas such as gaming and virtual reality.
Robust Network Slicing: Multi-Agent Policies, Adversarial Attacks, and Defensive Strategies
We evaluate the performance of the proposed policy ensemble algorithm by applying on the network slicing agents and the jammer agent in simulations to show its effectiveness.
Maximum Knowledge Orthogonality Reconstruction with Gradients in Federated Learning
MKOR only requires the server to send secretly modified parameters to clients and can efficiently and inconspicuously reconstruct the input images from clients' gradient updates.
Learning to Prompt Your Domain for Vision-Language Models
Prompt learning has recently become a very efficient transfer learning paradigm for Contrastive Language Image Pretraining (CLIP) models.
Text-to-3D using Gaussian Splatting
Specifically, our method adopts a progressive optimization strategy, which includes a geometry optimization stage and an appearance refinement stage.
mixed attention auto encoder for multi-class industrial anomaly detection
Most existing methods for unsupervised industrial anomaly detection train a separate model for each object category.
Baichuan 2: Open Large-scale Language Models
Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing the need for extensive feature engineering.
PolarRec: Radio Interferometric Data Reconstruction with Polar Coordinate Representation
This representation matches the way in which radio telescopes observe a celestial area as the Earth rotates.
Wireless Edge Content Broadcast via Integrated Terrestrial and Non-terrestrial Networks
In this paper, we introduce a novel approach to optimize wireless edge content placement using NTN, positioning NTN as a complement to TN for achieving optimal content broadcasting.
FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels
Consequently, we develop a suite of components to complement the virtual voxel concept, including a virtual voxel encoder, a virtual voxel mixer, and a virtual voxel assignment strategy.
Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusion
Radar is ubiquitous in autonomous driving systems due to its low cost and good adaptability to bad weather.
SAR-NeRF: Neural Radiance Fields for Synthetic Aperture Radar Multi-View Representation
SAR images are highly sensitive to observation configurations, and they exhibit significant variations across different viewing angles, making it challenging to represent and learn their anisotropic features.
Frame Fusion with Vehicle Motion Prediction for 3D Object Detection
To ''forward'' frames, we use vehicle motion models to estimate the future pose of the bounding boxes.
Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection
Drawing inspiration from this, we propose a high-performance offline detector in a track-centric perspective instead of the conventional object-centric perspective.
CoReFace: Sample-Guided Contrastive Regularization for Deep Face Recognition
To alleviate the above problem, we propose a novel approach namely Contrastive Regularization for Face recognition (CoReFace) to apply image-level regularization in feature representation learning.
Action Pick-up in Dynamic Action Space Reinforcement Learning
Then, we design two different AP methods: frequency-based global method and state clustering-based local method, based on the prior optimal policy.
Butterfly: Multiple Reference Frames Feature Propagation Mechanism for Neural Video Compression
Using more reference frames can significantly improve the compression efficiency in neural video compression.
Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification
In contrast, generative methods bring more image diversity in the augmented images but may not preserve semantic consistency, thus incorrectly changing the essential semantics of the original image.
Super Sparse 3D Object Detection
To enable efficient long-range detection, we first propose a fully sparse object detector termed FSD.
Mixed Neural Voxels for Fast Multi-view Video Synthesis
In this paper, we present a novel method named MixVoxels to better represent the dynamic scenes with fast training speed and competitive rendering qualities.
Towards A Unified Conformer Structure: from ASR to ASV Task
Transformer has achieved extraordinary performance in Natural Language Processing and Computer Vision tasks thanks to its powerful self-attention mechanism, and its variant Conformer has become a state-of-the-art architecture in the field of Automatic Speech Recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
DART: Articulated Hand Model with Diverse Accessories and Rich Textures
Unity GUI is also provided to generate synthetic hand data with user-defined settings, e. g., pose, camera, background, lighting, textures, and accessories.
Learning to Decompose Visual Features with Latent Textual Prompts
Recent advances in pre-training vision-language models like CLIP have shown great potential in learning transferable visual representations.
Communication-Efficient and Privacy-Preserving Feature-based Federated Transfer Learning
In order to improve the communication efficiency, we in this paper propose the feature-based federated transfer learning as an innovative approach to reduce the uplink payload by more than five orders of magnitude compared to that of existing approaches.
DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization
DUET is deployed on a powerful cloud server that only requires the low cost of forwarding propagation and low time delay of data transmission between the device and the cloud.
Personalizing Intervened Network for Long-tailed Sequential User Behavior Modeling
In this paper, we propose a novel approach that significantly improves the recommendation performance of the tail users while achieving at least comparable performance for the head users over the base model.
Fully Sparse 3D Object Detection
To enable efficient long-range LiDAR-based object detection, we build a fully sparse 3D object detector (FSD).
SHREC'22 Track: Sketch-Based 3D Shape Retrieval in the Wild
We define two SBSR tasks and construct two benchmarks consisting of more than 46, 000 CAD models, 1, 700 realistic models, and 145, 000 sketches in total.
Device-Cloud Collaborative Recommendation via Meta Controller
To overcome this issue, we propose a meta controller to dynamically manage the collaboration between the on-device recommender and the cloud-based recommender, and introduce a novel efficient sample construction from the causal perspective to solve the dataset absence issue of meta controller.
Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognition
According to the characteristic of SRSs, we present 22 diverse transformations and thoroughly evaluate them using 7 recent promising adversarial attacks (4 white-box and 3 black-box) on speaker recognition.
Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation
Contrastive learning has achieved impressive success in generation tasks to militate the "exposure bias" problem and discriminatively exploit the different quality of references.
CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation
Recent advances in self-supervised contrastive learning yield good image-level representation, which favors classification tasks but usually neglects pixel-level detailed information, leading to unsatisfactory transfer performance to dense prediction tasks such as semantic segmentation.
DePS: An improved deep learning model for de novo peptide sequencing
De novo peptide sequencing from mass spectrometry data is an important method for protein identification.
TECM: Transfer Learning-based Evidential C-Means Clustering
As a representative evidential clustering algorithm, evidential c-means (ECM) provides a deeper insight into the data by allowing an object to belong not only to a single class, but also to any subset of a collection of classes, which generalizes the hard, fuzzy, possibilistic, and rough partitions.
Tracing Text Provenance via Context-Aware Lexical Substitution
Tracing text provenance can help claim the ownership of text content or identify the malicious users who distribute misleading content like machine-generated fake news.
Embracing Single Stride 3D Object Detector with Sparse Transformer
In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases.
Ranked #3 on
3D Object Detection
on waymo cyclist
Enhanced Fast Boolean Matching based on Sensitivity Signatures Pruning
In this paper, we introduce Boolean sensitivity into Boolean matching and design several sensitivity-related signatures to enhance fast Boolean matching.
Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI
However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed.
Self-supervised denoising for massive noisy images
We propose an effective deep learning model for signal reconstruction, which requires no signal prior, no noise model calibration, and no clean samples.
Self-Supervised Learning by Estimating Twin Class Distributions
To solve this problem, we propose to maximize the mutual information between the input and the class predictions.
Ranked #1 on
Image Classification
on Oxford-IIIT Pet Dataset
Fine-Grained Image Classification
Representation Learning
+5
Boost Neural Networks by Checkpoints
In the experiments, it yields up to 5. 02% higher accuracy over single EfficientNet-B0 on the imbalanced datasets.
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.
YOLOX: Exceeding YOLO Series in 2021
In this report, we present some experienced improvements to YOLO series, forming a new high-performance detector -- YOLOX.
Ranked #1 on
Real-Time Object Detection
on Argoverse-HD (Detection-Only, Val)
(using extra training data)
Adversarial Reinforcement Learning in Dynamic Channel Access and Power Control
Deep reinforcement learning (DRL) has recently been used to perform efficient resource allocation in wireless communications.
Device-Cloud Collaborative Learning for Recommendation
With the rapid development of storage and computing power on mobile devices, it becomes critical and popular to deploy models on devices to save onerous communication latencies and to capture real-time features.
LiDAR R-CNN: An Efficient and Universal 3D Object Detector
LiDAR-based 3D detection in point cloud is essential in the perception system of autonomous driving.
RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection
The most notable difference with previous works is that our method is purely based on the range view representation.
RangeDet: In Defense of Range View for LiDAR-Based 3D Object Detection
We first analyze the existing range-view-based methods and find two issues overlooked by previous works: 1) the scale variation between nearby and far away objects; 2) the inconsistency between the 2D range image coordinates used in feature extraction and the 3D Cartesian coordinates used in output.
Understanding the Behaviour of Contrastive Loss
We will show that the contrastive loss is a hardness-aware loss function, and the temperature {\tau} controls the strength of penalties on hard negative samples.
Exploiting Behavioral Consistence for Universal User Representation
In this work, we focus on developing universal user representation model.
Unsupervised Representation Learning by Invariance Propagation
In this paper, we propose Invariance Propagation to focus on learning representations invariant to category-level variations, which are provided by different instances from the same category.
Unsupervised Representation Learning by InvariancePropagation
In this paper, we propose Invariance Propagation to focus on learning representations invariant to category-level variations, which are provided by different instances from the same category.
Decision-making at Unsignalized Intersection for Autonomous Vehicles: Left-turn Maneuver with Deep Reinforcement Learning
Decision-making module enables autonomous vehicles to reach appropriate maneuvers in the complex urban environments, especially the intersection situations.
Convolutional neural network based deep-learning architecture for intraprostatic tumour contouring on PSMA PET images in patients with primary prostate cancer
Accurate delineation of the intraprostatic gross tumour volume (GTV) is a prerequisite for treatment approaches in patients with primary prostate cancer (PCa).
Adversarial jamming attacks and defense strategies via adaptive deep reinforcement learning
As the applications of deep reinforcement learning (DRL) in wireless communications grow, sensitivity of DRL based wireless communication strategies against adversarial attacks has started to draw increasing attention.
Zero-shot Text Classification via Reinforced Self-training
In this situation, transferring from seen classes to unseen classes is extremely hard.
Cooling-Aware Resource Allocation and Load Management for Mobile Edge Computing Systems
Driven by explosive computation demands of Internet of Things (IoT), mobile edge computing (MEC) provides a promising technique to enhance the computation capability for mobile users.
SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check
This paper proposes to incorporate phonological and visual similarity knowledge into language models for CSC via a specialized graph convolutional network (SpellGCN).
An end-to-end CNN framework for polarimetric vision tasks based on polarization-parameter-constructing network
Pixel-wise operations between polarimetric images are important for processing polarization information.
COVID-19 Docking Server: A meta server for docking small molecules, peptides and antibodies against potential targets of COVID-19
Motivation: The coronavirus disease 2019 (COVID-19) caused by a new type of coronavirus has been emerging from China and led to thousands of death globally since December 2019.
A Discriminative Learned CNN Embedding for Remote Sensing Image Scene Classification
Concretely, for remote sensing image scene classification, we would like to map images from the same scene to feature vectors that are close, and map images from different scenes to feature vectors that are widely separated.
Kingsoft's Neural Machine Translation System for WMT19
This paper describes the Kingsoft AI Lab{'}s submission to the WMT2019 news translation shared task.
AirFace: Lightweight and Efficient Model for Face Recognition
With the development of convolutional neural network, significant progress has been made in computer vision tasks.
Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hopping
Experiments on two Mandarin ASR datasets show the replacement of RNNs by the self-attention networks yields a 8. 4%-10. 2% relative character error rate (CER) reduction.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Multi-scale Convolutional Neural Networks for Inverse Problems
We propose a novel neural network architecture highlighting fast convergence as a generic solution addressing image(s)-to-image(s) inverse problems of different domains.
Computational Physics Materials Science
Dual Ask-Answer Network for Machine Reading Comprehension
The task of question answering or question generation aims to infer an answer or a question when given the counterpart based on context.
Cascaded Mutual Modulation for Visual Reasoning
Our code is available at https://github. com/FlamingHorizon/CMM-VR.
Semi-Supervised Disfluency Detection
While the disfluency detection has achieved notable success in the past years, it still severely suffers from the data scarcity.
Unsupervised Neural Machine Translation with Weight Sharing
Unsupervised neural machine translation (NMT) is a recently proposed approach for machine translation which aims to train the model without using any labeled data.
Ranked #6 on
Machine Translation
on WMT2016 German-English
Precise Temporal Action Localization by Evolving Temporal Proposals
The performances of existing action localization approaches remain unsatisfactory in precisely determining the beginning and the end of an action.
A Subpixel Registration Algorithm for Low PSNR Images
This paper presents a fast algorithm for obtaining high-accuracy subpixel translation of low PSNR images.
Additive Margin Softmax for Face Verification
In this work, we introduce a novel additive angular margin for the Softmax loss, which is intuitively appealing and more interpretable than the existing works.
Ranked #2 on
Face Identification
on Trillion Pairs Dataset
Towards Compact and Fast Neural Machine Translation Using a Combined Method
Neural Machine Translation (NMT) lays intensive burden on computation and memory cost.
Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme
Joint extraction of entities and relations is an important task in information extraction.
Ranked #3 on
Relation Extraction
on NYT-single
NormFace: L2 Hypersphere Embedding for Face Verification
We show that both strategies, and small variants, consistently improve performance by between 0. 2% to 0. 4% on the LFW dataset based on two models.
On Consistency of Graph-based Semi-supervised Learning
We prove the consistency of graph-based learning in the case that the estimated scores are enforced to be equal to the observed responses for the labeled data.
Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
During training, both the dynamic discriminator and the static BLEU objective are employed to evaluate the generated sentences and feedback the evaluations to guide the learning of the generator.
DALiuGE: A Graph Execution Framework for Harnessing the Astronomical Data Deluge
The Data Activated Liu Graph Engine - DALiuGE - is an execution framework for processing large astronomical datasets at a scale required by the Square Kilometre Array Phase 1 (SKA1).
Distributed, Parallel, and Cluster Computing Instrumentation and Detectors
Regularizing Face Verification Nets For Pain Intensity Regression
In this way, the expression intensity regression task can benefit from the rich feature representations trained on a huge amount of data for face verification.
MAT: A Multimodal Attentive Translator for Image Captioning
In this way, the sequential representation of an image can be naturally translated to a sequence of words, as the target sequence of the RNN model.
A Character-Aware Encoder for Neural Machine Translation
This article proposes a novel character-aware neural machine translation (NMT) model that views the input sequences as sequences of characters rather than words.
DeepPicker: a Deep Learning Approach for Fully Automated Particle Picking in Cryo-EM
Particle picking is a time-consuming step in single-particle analysis and often requires significant interventions from users, which has become a bottleneck for future automated electron cryo-microscopy (cryo-EM).
Survey on the attention based RNN model and its applications in computer vision
In this survey, we introduce some attention based RNN models which can focus on different parts of the input for each output item, in order to explore and take advantage of the implicit relations between the input and the output items.
Qualitative detection of oil adulteration with machine learning approaches
The study focused on the machine learning analysis approaches to identify the adulteration of 9 kinds of edible oil qualitatively and answered the following three questions: Is the oil sample adulterant?
