Search Results for author:
Found 71 papers, 18 papers with code
OPPO’s Machine Translation Systems for WMT20
In this paper we demonstrate our (OPPO’s) machine translation systems for the WMT20 Shared Task on News Translation for all the 22 language pairs.
Spatial-context-aware deep neural network for multi-class image classification
Multi-label image classification is a fundamental but challenging task in computer vision.
Monocular Road Planar Parallax Estimation
By warping the consecutive frames using the road plane as a reference, the 3D structure can be estimated from the planar parallax and the residual image displacements.
Spiking CapsNet: A Spiking Neural Network With A Biologically Plausible Routing Rule Between Capsules
Our Spiking CapsNet fully combines the strengthens of SNN and CapsNet, and shows strong robustness to noise and affine transformation.
Aspect-driven User Preference and News Representation Learning for News Recommendation
News recommender systems are essential for helping users to efficiently and effectively find out those interesting news from a large amount of news.
Text-based Person Search in Full Images via Semantic-Driven Proposal Generation
Finding target persons in full scene images with a query of text description has important practical applications in intelligent video surveillance. However, different from the real-world scenarios where the bounding boxes are not available, existing text-based person retrieval methods mainly focus on the cross modal matching between the query text descriptions and the gallery of cropped pedestrian images.
Adversarial Relighting against Face Recognition
To this end, we first propose the physical model-based adversarial relighting attack (ARA) denoted as albedo-quotient-based adversarial relighting attack (AQ-ARA).
Hierarchical Aggregation for 3D Instance Segmentation
Instance segmentation on point clouds is a fundamental task in 3D scene perception.
Ranked #1 on
3D Instance Segmentation
on S3DIS
(mCov metric)
Pseudo Facial Generation With Extreme Poses for Face Recognition
Many of them settle it by generating fake frontal faces from extreme ones, whereas they are tough to maintain the identity information with high computational consumption and uncontrolled disturbances.
AOSLO-net: A deep learning-based method for automatic segmentation of retinal microaneurysms from adaptive optics scanning laser ophthalmoscope images
Microaneurysms (MAs) are one of the earliest signs of diabetic retinopathy (DR), a frequent complication of diabetes that can lead to visual impairment and blindness.
Hyperspectral Image Denoising with Log-Based Robust PCA
It is a challenging task to remove heavy and mixed types of noise from Hyperspectral images (HSIs).
Weakly-supervised Cross-view 3D Human Pose Estimation
Instead, exploiting multi-view information is a practical way to achieve absolute 3D human pose estimation.
THOR, Trace-based Hardware-adaptive layer-ORiented Natural Gradient Descent Computation
It is well-known that second-order optimizer can accelerate the training of deep neural networks, however, the huge computation cost of second-order optimization makes it impractical to apply in real practice.
Reducing Streaming ASR Model Delay with Self Alignment
From LibriSpeech evaluation, self alignment outperformed existing schemes: 25% and 56% less delay compared to FastEmit and constrained alignment at the similar word error rate.
Deep Online Correction for Monocular Visual Odometry
Second, the poses predicted by CNNs are further improved by minimizing photometric errors via gradient updates of poses during inference phases.
Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective
The outputs from the teacher network are used as soft labels for supervising the training of a new network.
Ranked #3 on
Knowledge Distillation
on ImageNet
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.
Towards Cross-Modal Forgery Detection and Localization on Live Surveillance Videos
Traditional video forensics approaches can detect and localize forgery traces in each video frame using computationally-expensive spatial-temporal analysis, while falling short in real-time verification of live video feeds.
Time Series
Video Forensics
Cryptography and Security
Rethinking Soft Labels for Knowledge Distillation: A Bias–Variance Tradeoff Perspective
In this paper, we investigate the bias-variance tradeoff brought by distillation with soft labels.
Stacked Homography Transformations for Multi-View Pedestrian Detection
This task is confronted with two challenges: how to establish the 3D correspondences from views to the BEV map and how to assemble occupancy information across views.
Survey of the Detection and Classification of Pulmonary Lesions via CT and X-Ray
In recent years, the prevalence of several pulmonary diseases, especially the coronavirus disease 2019 (COVID-19) pandemic, has attracted worldwide attention.
Matrix optimization based Euclidean embedding with outliers
Euclidean embedding from noisy observations containing outlier errors is an important and challenging problem in statistics and machine learning.
ResizeMix: Mixing Data with Preserved Object Information and True Labels
Especially, CutMix uses a simple but effective method to improve the classifiers by randomly cropping a patch from one image and pasting it on another image.
Causality-Aware Neighborhood Methods for Recommender Systems
In this work, we unify traditional neighborhood recommendation methods with the matching estimator, and develop robust ranking methods for the causal effect of recommendations.
DataVault: A Data Storage Infrastructure for the Einstein Toolkit
Data sharing is essential in the numerical simulations research.
General Relativity and Quantum Cosmology Databases
Predicting seasonal influenza using supermarket retail records
In this paper, we propose the use of a novel data source, namely retail market data to improve seasonal influenza forecasting.
On Efficient and Robust Metrics for RANSAC Hypotheses and 3D Rigid Registration
This paper focuses on developing efficient and robust evaluation metrics for RANSAC hypotheses to achieve accurate 3D rigid registration.
Kernel Two-Dimensional Ridge Regression for Subspace Clustering
It directly uses 2D data as inputs such that the learning of representations benefits from inherent structures and relationships of the data.
Transformer Transducer: One Model Unifying Streaming and Non-streaming Speech Recognition
In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model.
Deep Momentum Uncertainty Hashing
It embodies the uncertainty of the hashing network to the corresponding input image.
AutoPose: Searching Multi-Scale Branch Aggregation for Pose Estimation
Such simplification limits the fusion of information at different scales and fails to maintain high-resolution representations.
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation
In the classification tree, as the number of parent class nodes are significantly less, their logits are less noisy and can be utilized to suppress the wrong/noisy logits existed in the fine-grained class nodes.
Ranked #5 on
Few-Shot Object Detection
on LVIS v1.0 val
SiamParseNet: Joint Body Parsing and Label Propagation in Infant Movement Videos
In this paper, we propose a semi-supervised body parsing model, termed SiamParseNet (SPN), to jointly learn single frame body parsing and label propagation between frames in a semi-supervised fashion.
OPPO's Machine Translation System for the IWSLT 2020 Open Domain Translation Task
In this paper, we demonstrate our machine translation system applied for the Chinese-Japanese bidirectional translation task (aka.
Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation
Then for the novel task, we prove that the minimization of the $\ell_1$-regularized log-determinant Bregman divergence with the additional constraint that the support is a subset of the estimated support union could reduce the sufficient sample complexity of successful support recovery to $O(\log(|S_{\text{off}}|))$ where $|S_{\text{off}}|$ is the number of off-diagonal elements in the support union and is much less than $N$ for sparse matrices.
FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
In this paper, we propose a Fast Network Adaptation (FNA++) method, which can adapt both the architecture and parameters of a seed network (e. g. an ImageNet pre-trained network) to become a network with different depths, widths, or kernel sizes via a parameter remapping technique, making it possible to use NAS for segmentation and detection tasks a lot more efficiently.
Boundary Guidance Hierarchical Network for Real-Time Tongue Segmentation
Finally, the proposed hybrid loss in a four hierarchy-pixel, patch, map and boundary guides the network to effectively segment the tongue regions and accurate tongue boundaries.
Active Lighting Recurrence by Parallel Lighting Analogy for Fine-Grained Change Detection
Besides, we also theoretically prove the invariance of our ALR approach to the ambiguity of normal and lighting decomposition.
Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss
We present results on the LibriSpeech dataset showing that limiting the left context for self-attention in the Transformer layers makes decoding computationally tractable for streaming, with only a slight degradation in accuracy.
Fast Neural Network Adaptation via Parameter Remapping and Architecture Search
In our experiments, we conduct FNA on MobileNetV2 to obtain new networks for both segmentation and detection that clearly out-perform existing networks designed both manually and by NAS.
CAE-LO: LiDAR Odometry Leveraging Fully Unsupervised Convolutional Auto-Encoder for Interest Point Detection and Feature Description
As an important technology in 3D mapping, autonomous driving, and robot navigation, LiDAR odometry is still a challenging task.
FasterSeg: Searching for Faster Real-time Semantic Segmentation
We present FasterSeg, an automatically designed semantic segmentation network with not only state-of-the-art performance but also faster speed than current methods.
Ranked #1 on
Semantic Segmentation
on BDD
AugFPN: Improving Multi-scale Feature Learning for Object Detection
In this paper, we begin by first analyzing the design defects of feature pyramid in FPN, and then introduce a new feature pyramid architecture named AugFPN to address these problems.
Learning Where to Focus for Efficient Video Object Detection
Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur.
VarGFaceNet: An Efficient Variable Group Convolutional Neural Network for Lightweight Face Recognition
To improve the discriminative and generalization ability of lightweight network for face recognition, we propose an efficient variable group convolutional network called VarGFaceNet.
Ranked #1 on
Face Verification
on Labeled Faces in the Wild
Sensor-Augmented Neural Adaptive Bitrate Video Streaming on UAVs
In this paper, we present SA-ABR, a new sensor-augmented system that generates ABR video streaming algorithms with the assistance of various kinds of inherent sensor data that are used to pilot UAVs.
Improved Mix-up with KL-Entropy for Learning From Noisy Labels
On the websites, there exist a lot of image data which contains inaccurate annotations, but training on these datasets may make networks easier to over-fit the noisy labels and cause performance degradation.
Improved Hybrid Layered Image Compression using Deep Learning and Traditional Codecs
Recently deep learning-based methods have been applied in image compression and achieved many promising results.
VarGNet: Variable Group Convolutional Neural Network for Efficient Embedded Computing
In this paper, we propose a novel network design mechanism for efficient embedded computing.
Ranked #3 on
Face Verification
on CFP-FP
Densely Connected Search Space for More Flexible Neural Architecture Search
We revisit the search space design in most previous NAS methods and find the number and widths of blocks are set manually.
Ranked #403 on
Image Classification
on ImageNet
FRNET: Flattened Residual Network for Infant MRI Skull Stripping
Skull stripping for brain MR images is a basic segmentation task.
FrameRank: A Text Processing Approach to Video Summarization
In constructing the dataset, because of the subjectivity of user-generated video summarization, we manually annotate 25 summaries for each video, which are in total 1300 summaries.
Simultaneous Spectral-Spatial Feature Selection and Extraction for Hyperspectral Images
In a feature representation point of view, a nature approach to handle this situation is to concatenate the spectral and spatial features into a single but high dimensional vector and then apply a certain dimension reduction technique directly on that concatenated vector before feed it into the subsequent classifier.
High Fidelity Face Manipulation with Extreme Poses and Expressions
Furthermore, due to the lack of high-resolution face manipulation databases to verify the effectiveness of our method, we collect a new high-quality Multi-View Face (MVF-HQ) database.
Progressive Sparse Local Attention for Video object detection
Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressively sparser stride and uses the correspondence to propagate features.
Enhancing Remote Sensing Image Retrieval with Triplet Deep Metric Learning Network
With the rapid growing of remotely sensed imagery data, there is a high demand for effective and efficient image retrieval tools to manage and exploit such data.
EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search
In our implementations, architectures are first searched on a small dataset, e. g., CIFAR-10.
ECGadv: Generating Adversarial Electrocardiogram to Misguide Arrhythmia Classification System
Deep neural networks (DNNs)-powered Electrocardiogram (ECG) diagnosis systems recently achieve promising progress to take over tedious examinations by cardiologists.
Cross-Technology Communications for Heterogeneous IoT Devices Through Artificial Doppler Shifts
To this end, we propose DopplerFi, a communication framework that enables a two-way communication channel between BLE and Wi-Fi by injecting artificial Doppler shifts, which can be decoded by sensing the patterns in the Gaussian frequency shift keying (GFSK) demodulator and Channel State Information (CSI).
Networking and Internet Architecture
Joint Neural Architecture Search and Quantization
Here our goal is to automatically find a compact neural network model with high performance that is suitable for mobile devices.
In-the-wild Facial Expression Recognition in Extreme Poses
In the computer research area, facial expression recognition is a hot research problem.
Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-identification
We propose a novel deep network called Mancs that solves the person re-identification problem from the following aspects: fully utilizing the attention mechanism for the person misalignment problem and properly sampling for the ranking loss to obtain more stable person representation.
Reinforced Evolutionary Neural Architecture Search
To address this issue, we propose the Reinforced Evolutionary Neural Architecture Search (RE- NAS), which is an evolutionary method with the reinforced mutation for NAS.
Unsupervised Domain Adaptive Re-Identification: Theory and Practice
We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation.
Ranked #12 on
Unsupervised Domain Adaptation
on Market to Duke
Quality Classified Image Analysis with Application to Face Detection and Recognition
We will present experimental results to show that our quality classified framework can accurately classify images based on the type and severity of image degradations and can significantly boost the performances of state-of-the-art face detector and recognizer in dealing with image datasets containing mixed quality images.
Automatic Visual Theme Discovery from Joint Image and Text Corpora
Furthermore, not all tags have the same descriptive power for visual contents and large vocabulary available from natural language could result in a very diverse set of keywords.
6D Dynamic Camera Relocalization From Single Reference Image
Based on inexpensive platform with unreliable absolute repositioning accuracy (ARA), we propose a hand-eye calibration free strategy to actively relocate camera into the same 6D pose that produces the input reference image, by sequentially correcting 3D relative rotation and translation.
3D Keypoint Detection Based on Deep Neural Network with Sparse Autoencoder
Researchers have proposed various methods to extract 3D keypoints from the surface of 3D mesh models over the last decades, but most of them are based on geometric methods, which lack enough flexibility to meet the requirements for various applications.
Topical differences between Chinese language Twitter and Sina Weibo
Using a large corpus of Weibo and Chinese language tweets, covering the period from January $1$ to December $31$, $2012$, we obtain a list of topics using clustered \#tags that we can then use to compare the two platforms.
Fine-Grained Change Detection of Misaligned Scenes With Varied Illuminations
To guarantee detection sensitivity and accuracy of minute changes, in an observation, we capture a group of images under multiple illuminations, which need only to be roughly aligned to the last time lighting conditions.
Prediction of the Yield of Enzymatic Synthesis of Betulinic Acid Ester Using Artificial Neural Networks and Support Vector Machine
To simplify the number of times of optimization in experimental works, here, we use artificial neural network (ANN) and support vector machine (SVM) models for the prediction of yields of 3\b{eta}-O-phthalic ester of betulinic acid synthesized by betulinic acid and phthalic anhydride using lipase as biocatalyst.