Search Results for author:
Found 145 papers, 55 papers with code
SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation
For semantic segmentation in urban scene understanding, RGB cameras alone often fail to capture a clear holistic topology, especially in challenging lighting conditions.
Ranked #1 on
Thermal Image Segmentation
on PST900
Calibration-free BEV Representation for Infrastructure Perception
Effective BEV object detection on infrastructure can greatly improve traffic scenes understanding and vehicle-toinfrastructure (V2I) cooperative perception.
MetaGrad: Adaptive Gradient Quantization with Hypernetworks
A popular track of network compression approach is Quantization aware Training (QAT), which accelerates the forward pass during the neural network training and inference.
Key-Exchange Convolutional Auto-Encoder for Data Augmentation in Early Knee OsteoArthritis Classification
In this paper, we propose a learning model based on the convolutional Auto-Encoder and a hybrid loss strategy to generate new data for early KOA (KL-0 vs KL-2) diagnosis.
Improving Interpretability via Explicit Word Interaction Graph Layer
Recent NLP literature has seen growing interest in improving model interpretability.
ConQueR: Query Contrast Voxel-DETR for 3D Object Detection
We thus propose a Query Contrast mechanism to explicitly enhance queries towards their best-matched GTs over all unmatched query predictions.
Research on Early Warning and NB-IoT Real-time Monitoring System for Radiation Source Shedding of Gamma Flaw Detection Machine
In conclusion, radiation source can be found timely when it falls off, to avoid radiation accident.
STILN: A Novel Spatial-Temporal Information Learning Network for EEG-based Emotion Recognition
In the temporal contexts learning, we adopt the Bidirectional Long Short-Term Memory Network (Bi-LSTM) network to capture the dependencies among the EEG frames.
Temporal-spatial Representation Learning Transformer for EEG-based Emotion Recognition
Both the temporal dynamics and spatial correlations of Electroencephalogram (EEG), which contain discriminative emotion information, are essential for the emotion recognition.
Decentralized Federated Reinforcement Learning for User-Centric Dynamic TFDD Control
The explosive growth of dynamic and heterogeneous data traffic brings great challenges for 5G and beyond mobile networks.
DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest Recommendation
Point-of-Interest (POI) recommendation plays a vital role in various location-aware services.
Fast DistilBERT on CPUs
In this work, we propose a new pipeline for creating and running Fast Transformer models on CPUs, utilizing hardware-aware pruning, knowledge distillation, quantization, and our own Transformer inference runtime engine with optimized kernels for sparse and quantized operators.
Deep Learning Based Audio-Visual Multi-Speaker DOA Estimation Using Permutation-Free Loss Function
In this paper, we propose a deep learning based multi-speaker direction of arrival (DOA) estimation with audio and visual signals by using permutation-free loss function.
ASD: Towards Attribute Spatial Decomposition for Prior-Free Facial Attribute Recognition
Representing the spatial properties of facial attributes is a vital challenge for facial attribute recognition (FAR).
Towards Trustworthy Multi-label Sewer Defect Classification via Evidential Deep Learning
An automatic vision-based sewer inspection plays a key role of sewage system in a modern city.
Self-supervised Heterogeneous Graph Pre-training Based on Structural Clustering
The two modules can effectively utilize and enhance each other, promoting the model to learn discriminative embeddings.
FreGAN: Exploiting Frequency Components for Training GANs under Limited Data
Training GANs under limited data often leads to discriminator overfitting and memorization issues, causing divergent training.
Going Further With Winograd Convolutions: Tap-Wise Quantization for Efficient Inference on 4x4 Tile
The Winograd-enhanced DSA achieves up to 1. 85x gain in energy efficiency and up to 1. 83x end-to-end speed-up for state-of-the-art segmentation and detection networks.
Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environments
The Game Theory & Multi-Agent team at DeepMind studies several aspects of multi-agent learning ranging from computing approximations to fundamental concepts in game theory to simulating social dilemmas in rich spatial environments and training 3-d humanoids in difficult team coordination tasks.
Magnetic Resonance Fingerprinting with compressed sensing and distance metric learning
Adaptively learning a distance metric from the undersampled training data can significantly improve the matching accuracy of the query fingerprints.
PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation
In this paper, we propose the token-Pruned Pose Transformer (PPT) for 2D human pose estimation, which can locate a rough human mask and performs self-attention only within selected tokens.
Ranked #1 on
3D Human Pose Estimation
on Human3.6M
(Multi-View or Monocular metric, using extra
training data)
Joint Learning of Deep Texture and High-Frequency Features for Computer-Generated Image Detection
Based on the finding that multiple different modules in image acquisition will lead to different sensitivity inconsistencies to the convolutional neural network (CNN)-based rendering in images, we propose a deep texture rendering module for texture difference enhancement and discriminative texture representation.
A Brief History of Recommender Systems
Soon after the invention of the Internet, the recommender system emerged and related technologies have been extensively studied and applied by both academia and industry.
FuncFooler: A Practical Black-box Attack Against Learning-based Binary Code Similarity Detection Methods
The binary code similarity detection (BCSD) method measures the similarity of two binary executable codes.
AMinerGNN: Heterogeneous Graph Neural Network for Paper Click-through Rate Prediction with Fusion Query
Paper recommendation with user-generated keyword is to suggest papers that simultaneously meet user's interests and are relevant to the input keyword.
Click-Through Rate Prediction
Graph Representation Learning
+1
TBI-GAN: An Adversarial Learning Approach for Data Synthesis on Traumatic Brain Segmentation
To address these issues, we propose a novel medical image inpainting model named TBI-GAN to synthesize TBI MR scans with paired brain label maps.
Subtype-Former: a deep learning approach for cancer subtype discovery with multi-omics data
In addition, Subtype-Former also achieved outstanding results in pan-cancer subtyping, which can help analyze the commonalities and differences across various cancer types at the molecular level.
WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generation
Concretely, we disentangle encoded features into multiple frequency components and perform low-frequency skip connections to preserve outline and structural information.
Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning
It has the additional complexity of requiring decision-making under imperfect information, similar to Texas hold'em poker, which has a significantly smaller game tree (on the order of $10^{164}$ nodes).
A Competitive Method for Dog Nose-print Re-identification
Vision-based pattern identification (such as face, fingerprint, iris etc.)
Towards Efficient 3D Object Detection with Knowledge Distillation
Then, we build a benchmark to assess existing KD methods developed in the 2D domain for 3D object detection upon six well-constructed teacher-student pairs.
The Best of Both Worlds: Combining Model-based and Nonparametric Approaches for 3D Human Body Estimation
Our framework leverages the best of non-parametric and model-based methods and is also robust to partial occlusion.
Ranked #1 on
3D Absolute Human Pose Estimation
on Human3.6M
(PA-MPJPE metric)
RigidFlow: Self-Supervised Scene Flow Learning on Point Clouds by Local Rigidity Prior
In this work, we focus on scene flow learning on point clouds in a self-supervised manner.
Online Adversarial Distillation for Graph Neural Networks
However, its effect on graph neural networks is less than satisfactory since the graph topology and node attributes are likely to change in a dynamic way and in this case a static teacher model is insufficient in guiding student training.
Deep self-consistent learning of local volatility
We present an algorithm for the calibration of local volatility from market option prices through deep self-consistent learning, by approximating market option prices and local volatility using deep neural networks.
AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach
Compared to previous methods, our AdaStereo realizes a more standard, complete and effective domain adaptation pipeline.
TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation
The 3D position encoding guided by the epipolar field provides an efficient way of encoding correspondences between pixels of different views.
Ranked #14 on
3D Human Pose Estimation
on Human3.6M
(using extra training data)
A Cubic Regularization Approach for Finding Local Minimax Points in Nonconvex Minimax Optimization
However, GDA has been proved to converge to stationary points for nonconvex minimax optimization, which are suboptimal compared with local minimax points.
Delving into Channels: Exploring Hyperparameter Space of Channel Bit Widths with Linear Complexity
We formulate the quantization of deep neural networks as a rate-distortion optimization problem, and present an ultra-fast algorithm to search the bit allocation of channels.
ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning
This paper proposes a novel method, ST-MAML, that empowers model-agnostic meta-learning (MAML) to learn from multiple task distributions.
Long-Range Transformers for Dynamic Spatiotemporal Forecasting
Multivariate Time Series Forecasting focuses on the prediction of future values based on historical context.
Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos
Graph Convolution Network (GCN) has been successfully used for 3D human pose estimation in videos.
Ranked #9 on
3D Human Pose Estimation
on HumanEva-I
Enhanced Seq2Seq Autoencoder via Contrastive Learning for Abstractive Text Summarization
In this paper, we present a denoising sequence-to-sequence (seq2seq) autoencoder via contrastive learning for abstractive text summarization.
ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection
These specific designs enable the detector to be trained on meticulously refined pseudo labeled target data with denoised training signals, and thus effectively facilitate adapting an object detector to a target domain without requiring annotations.
POSO: Personalized Cold Start Modules for Large-scale Recommender Systems
Moreover, POSO can be further generalized to regular users, inactive users and returning users (+2%-3% on Watch Time), as well as item cold start (+3. 8% on Watch Time).
A Credibility-aware Swarm-Federated Deep Learning Framework in Internet of Vehicles
This paper proposes a Swarm-Federated Deep Learning framework in the IoV system (IoV-SFDL) that integrates SL into the FDL framework.
Reconstructing a dynamical system and forecasting time series by self-consistent deep learning
We introduce a self-consistent deep-learning framework which, for a noisy deterministic time series, provides unsupervised filtering, state-space reconstruction, identification of the underlying differential equations and forecasting.
Time-series Imputation of Temporally-occluded Multiagent Trajectories
In multiagent environments, several decision-making individuals interact while adhering to the dynamics constraints imposed by the environment.
SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation
However, it is quite expensive to annotate every frame in a large corpus of videos to construct a comprehensive supervised training dataset.
From Motor Control to Team Play in Simulated Humanoid Football
In a sequence of stages, players first learn to control a fully articulated body to perform realistic, human-like movements such as running and turning; they then acquire mid-level football skills such as dribbling and shooting; finally, they develop awareness of others and play as a team, bridging the gap between low-level motor control at a timescale of milliseconds, and coordinated goal-directed behaviour as a team at the timescale of tens of seconds.
Deep learning in physics: a study of dielectric quasi-cubic particles in a uniform electric field
The present work's objective is two-fold, first to show how an a priori knowledge can be incorporated into neural networks to achieve efficient learning and second to apply the method and study how the induced field and polarizability change when a dielectric particle progressively changes its shape from a sphere to a cube.
Learning Versatile Neural Architectures by Propagating Network Codes
(4) Thorough studies of NCP on inter-, cross-, and intra-tasks highlight the importance of cross-task neural architecture design, i. e., multitask neural architectures and architecture transferring between different tasks.
PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos
By coupling advanced 3D pose estimators and HMR in a serial or parallel manner, these two frameworks can effectively correct human mesh with guidance of a concise pose calibration module.
Ranked #3 on
3D Human Pose Estimation
on Surreal
ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection
Then, the detector is iteratively improved on the target domain by alternatively conducting two steps, which are the pseudo label updating with the developed quality-aware triplet memory bank and the model training with curriculum data augmentation.
Relate and Predict: Structure-Aware Prediction with Jointly Optimized Neural DAG
Understanding relationships between feature variables is one important way humans use to make decisions.
Network Pruning via Resource Reallocation
Channel pruning is broadly recognized as an effective approach to obtain a small compact model through eliminating unimportant channels from a large cumbersome network.
FFConv: Fast Factorized Convolutional Neural Network Inference on Encrypted Data
Despite the faster HECNN inference, the mainstream packing schemes Dense Packing (DensePack) and Convolution Packing (ConvPack) introduce expensive rotation overhead, which prolongs the inference latency of HECNN for deeper and wider CNN architectures.
PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection
3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields.
Ranked #2 on
3D Object Detection
on KITTI Cars Easy val
Towards Reducing Severe Defocus Spread Effects for Multi-Focus Image Fusion via an Optimization Based Strategy
According to the idea that each local region in the fused image should be similar to the sharpest one among source images, this paper presents an optimization-based approach to reduce defocus spread effects.
Exploring Data Augmentation for Multi-Modality 3D Object Detection
Due to the fact that multi-modality data augmentation must maintain consistency between point cloud and images, recent methods in this field typically use relatively insufficient data augmentation.
A Multi-intersection Vehicular Cooperative Control based on End-Edge-Cloud Computing
In particular, we propose a Multi-intersection Vehicular Cooperative Control (MiVeCC) to enable cooperation among vehicles in a large area with multiple unsignalized intersections.
Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
As a special design of this transformer, the information encoded in the encoder is different from that in the decoder, i. e. the encoder encodes temporal-channel information of multiple frames while the decoder decodes the spatial-channel information for the current frame in a voxel-wise manner.
The ANTARES Astronomical Time-Domain Event Broker
We describe the Arizona-NOIRLab Temporal Analysis and Response to Events System (ANTARES), a software instrument designed to process large-scale streams of astronomical time-domain alerts.
Instrumentation and Methods for Astrophysics
FLAVA: Find, Localize, Adjust and Verify to Annotate LiDAR-Based Point Clouds
Recent years have witnessed the rapid progress of perception algorithms on top of LiDAR, a widely adopted sensor for autonomous driving systems.
Game Plan: What AI can do for Football, and What Football can do for AI
The rapid progress in artificial intelligence (AI) and machine learning has opened unprecedented analytics possibilities in various team and individual sports, including baseball, basketball, and tennis.
Energy Consumption and Battery Aging Minimization Using a Q-learning Strategy for a Battery/Ultracapacitor Electric Vehicle
Then, the result from a vehicle without ultracapacitor is used as the baseline, which is compared with the results from the vehicle with ultracapacitor using Q-learning, and two heuristic methods as the energy management strategies.
Learning Time Reduction Using Warm Start Methods for a Reinforcement Learning Based Supervisory Control in Hybrid Electric Vehicle Applications
This study aims to reduce the learning iterations of Q-learning in HEV application and improve fuel consumption in initial learning phases utilizing warm start methods.
Topic-Guided Abstractive Text Summarization: a Joint Learning Approach
We introduce a new approach for abstractive text summarization, Topic-Guided Abstractive Summarization, which calibrates long-range dependencies from topic-level features with globally salient content.
The Detection of Thoracic Abnormalities ChestX-Det10 Challenge Results
The detection of thoracic abnormalities challenge is organized by the Deepwise AI Lab.
Enhanced First and Zeroth Order Variance Reduced Algorithms for Min-Max Optimization
Specifically, a novel variance reduction algorithm SREDA was proposed recently by (Luo et al. 2020) to solve such a problem, and was shown to achieve the optimal complexity dependence on the required accuracy level $\epsilon$.
Exploit Camera Raw Data for Video Super-Resolution via Hidden Markov Model Inference
Extensive experiments demonstrate that owing to the informativeness of the camera raw data, the effectiveness of the network architecture, and the separation of super-resolution and color correction processes, the proposed method achieves superior VSR results compared to the state-of-the-art and can be adapted to any specific camera-ISP.
Spectral Algorithms for Community Detection in Directed Networks
Community detection in large social networks is affected by degree heterogeneity of nodes.
Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation
A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space.
Ranked #8 on
LIDAR Semantic Segmentation
on nuScenes
COLD: Towards the Next Generation of Pre-Ranking System
We name it COLD (Computing power cost-aware Online and Lightweight Deep pre-ranking system).
Weak Supervision and Referring Attention for Temporal-Textual Association Learning
The referring attention is our designed mechanism acting as a scoring function for grounding the given queries over frames temporally.
Gradient Free Minimax Optimization: Variance Reduction and Faster Convergence
In this paper, we focus on such a gradient-free setting, and consider the nonconvex-strongly-concave minimax stochastic optimization problem.
ACMo: Angle-Calibrated Moment Methods for Stochastic Optimization
Due to its simplicity and outstanding ability to generalize, stochastic gradient descent (SGD) is still the most widely used optimization method despite its slow convergence.
Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs
Adaptive gradient methods have attracted much attention of machine learning communities due to the high efficiency.
Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction
Serving the main traffic in our real system now, SIM models user behavior data with maximum length reaching up to 54000, pushing SOTA to 54x.
ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language
Person search by natural language aims at retrieving a specific person in a large-scale image pool that matches the given textual descriptions.
Ranked #10 on
Text based Person Retrieval
on CUHK-PEDES
Resisting Crowd Occlusion and Hard Negatives for Pedestrian Detection in the Wild
Pedestrian detection has been heavily studied in the last decade due to its wide application.
Non-asymptotic Convergence Analysis of Two Time-scale (Natural) Actor-Critic Algorithms
In the first nested-loop design, actor's one update of policy is followed by an entire loop of critic's updates of the value function, and the finite-sample analysis of such AC and NAC algorithms have been recently well established.
Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms
We show that the overall sample complexity for a mini-batch AC to attain an $\epsilon$-accurate stationary point improves the best known sample complexity of AC by an order of $\mathcal{O}(\epsilon^{-1}\log(1/\epsilon))$, and the overall sample complexity for a mini-batch NAC to attain an $\epsilon$-accurate globally optimal point improves the existing sample complexity of NAC by an order of $\mathcal{O}(\epsilon^{-1}/\log(1/\epsilon))$.
Beyond Data Samples: Aligning Differential Networks Estimation with Scientific Knowledge
Learning the differential statistical dependency network between two contexts is essential for many real-life applications, mostly in the high dimensional low sample regime.
The Role of the Hercules Autonomous Vehicle During the COVID-19 Pandemic: An Autonomous Logistic Vehicle for Contactless Goods Transportation
Moreover, many countries have imposed tough lockdown measures to reduce the virus transmission (e. g., retail, catering) during the pandemic, which causes inconveniences for human daily life.
AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching
Compared to previous methods for adaptive stereo matching, our AdaStereo realizes a more standard, complete and effective domain adaptation pipeline.
Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation
Monocular estimation of 3d human pose has attracted increased attention with the availability of large ground-truth motion capture datasets.
Ranked #1 on
3D Human Pose Estimation
on Surreal
(using extra training data)
Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization
Our APG-restart is designed to 1) allow for adopting flexible parameter restart schemes that cover many existing ones; 2) have a global sub-linear convergence rate in nonconvex and nonsmooth optimization; and 3) have guaranteed convergence to a critical point and have various types of asymptotic convergence rates depending on the parameterization of local geometry in nonconvex and nonsmooth optimization.
Hierarchical Transformer Network for Utterance-level Emotion Recognition
To address these problems, we propose a hierarchical transformer framework (apart from the description of other studies, the "transformer" in this paper usually refers to the encoder part of the transformer) with a lower-level transformer to model the word-level input and an upper-level transformer to capture the context of utterance-level embeddings.
Ranked #1 on
Emotion Recognition in Conversation
on EmotionPush
SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud
First, the semantic context information in LiDAR is seldom explored in previous works, which may help identify ambiguous vehicles.
Reanalysis of Variance Reduced Temporal Difference Learning
Furthermore, the variance error (for both i. i. d.\ and Markovian sampling) and the bias error (for Markovian sampling) of VRTD are significantly reduced by the batch size of variance reduction in comparison to those of vanilla TD.
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds.
Learning Depth-Guided Convolutions for Monocular 3D Object Detection
3D object detection from a single image without LiDAR is a challenging task due to the lack of accurate depth information.
Ranked #17 on
Monocular 3D Object Detection
on KITTI Cars Moderate
(using extra training data)
SpiderBoost and Momentum: Faster Variance Reduction Algorithms
SARAH and SPIDER are two recently developed stochastic variance-reduced algorithms, and SPIDER has been shown to achieve a near-optimal first-order oracle complexity in smooth nonconvex optimization.
Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow
Moreover, our framework is able to utilize both labeled and unlabeled frames in the video through joint training, while no additional calculation is required in inference.
Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization
Two types of zeroth-order stochastic algorithms have recently been designed for nonconvex optimization respectively based on the first-order techniques SVRG and SARAH/SPIDER.
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.
RiWalk: Fast Structural Node Embedding via Role Identification
Learning latent representations for the roles of nodes helps to understand the network and to transfer knowledge across networks.
A Generalized Training Approach for Multiagent Learning
This paper investigates a population-based training regime based on game-theoretic principles called Policy-Spaced Response Oracles (PSRO).
Acutum: When Generalization Meets Adaptability
To the best of our knowledge, Acutum is the first adaptive gradient method without second moments.
Towards Effective 2-bit Quantization: Pareto-optimal Bit Allocation for Deep CNNs Compression
In this paper, we address an important problem of how to optimize the bit allocation of weights and activations for deep CNNs compression.
Variable Population Memetic Search: A Case Study on the Critical Node Problem
Population-based memetic algorithms have been successfully applied to solve many difficult combinatorial problems.
Robust Multi-Modality Multi-Object Tracking
Multi-sensor perception is crucial to ensure the reliability and accuracy in autonomous driving system, while multi-object tracking (MOT) improves that by tracing sequential movement of dynamic objects.
Ranked #9 on
Multiple Object Tracking
on KITTI Tracking test
FocusNet: Imbalanced Large and Small Organ Segmentation with an End-to-End Deep Neural Network for Head and Neck CT Images
In this paper, we propose an end-to-end deep neural network for solving the problem of imbalanced large and small organ segmentation in head and neck (HaN) CT images.
From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network
3D object detection from LiDAR point cloud is a challenging problem in 3D scene understanding and has many practical applications.
Efficient and Accurate Face Alignment by Global Regression and Cascaded Local Refinement
In particular, for a given image, our algorithm first estimates its global facial shape through a global regression network (GRegNet) and then using cascaded local refinement networks (LRefNet) to sequentially improve the alignment result.
Ranked #8 on
Face Alignment
on 300W
Geometric Pose Affordance: 3D Human Pose with Scene Constraints
Full 3D estimation of human pose from a single image remains a challenging task despite many recent advances.
Coordinate descent full configuration interaction
We develop an efficient algorithm, coordinate descent FCI (CDFCI), for the electronic structure ground state calculation in the configuration interaction framework.
Chemical Physics Computational Physics
Momentum Schemes with Stochastic Variance Reduction for Nonconvex Composite Optimization
In this paper, we develop novel momentum schemes with flexible coefficient settings to accelerate SPIDER for nonconvex and nonsmooth composite optimization, and show that the resulting algorithms achieve the near-optimal gradient oracle complexity for achieving a generalized first-order stationary condition.
Augmenting Model Robustness with Transformation-Invariant Attacks
The vulnerability of neural networks under adversarial attacks has raised serious concerns and motivated extensive research.
A^2-Net: Molecular Structure Estimation from Cryo-EM Density Volumes
Constructing of molecular structural models from Cryo-Electron Microscopy (Cryo-EM) density volumes is the critical last step of structure determination by Cryo-EM technologies.
SpiderBoost and Momentum: Faster Stochastic Variance Reduction Algorithms
SARAH and SPIDER are two recently developed stochastic variance-reduced algorithms, and SPIDER has been shown to achieve a near-optimal first-order oracle complexity in smooth nonconvex optimization.
Cubic Regularization with Momentum for Nonconvex Optimization
However, such a successful acceleration technique has not yet been proposed for second-order algorithms in nonconvex optimization. In this paper, we apply the momentum scheme to cubic regularized (CR) Newton's method and explore the potential for acceleration.
A Detection and Segmentation Architecture for Skin Lesion Segmentation on Dermoscopy Images
This report summarises our method and validation results for the ISIC Challenge 2018 - Skin Lesion Analysis Towards Melanoma Detection - Task 1: Lesion Segmentation.
Convergence of Cubic Regularization for Nonconvex Optimization under KL Property
Cubic-regularized Newton's method (CR) is a popular algorithm that guarantees to produce a second-order stationary solution for solving nonconvex optimization problems.
A Note on Inexact Condition for Cubic Regularized Newton's Method
This note considers the inexact cubic-regularized Newton's method (CR), which has been shown in \cite{Cartis2011a} to achieve the same order-level convergence rate to a secondary stationary point as the exact CR \citep{Nesterov2006}.
Pose Guided Human Video Generation
Human pose, on the other hand, can represent motion patterns intrinsically and interpretably, and impose the geometric constraints regardless of appearance.
Knowledge Compilation in Multi-Agent Epistemic Logics
Epistemic logics are a primary formalism for multi-agent systems but major reasoning tasks in such epistemic logics are intractable, which impedes applications of multi-agent epistemic logics in automatic planning.
Learnable Histogram: Statistical Context Features for Deep Neural Networks
Statistical features, such as histogram, Bag-of-Words (BoW) and Fisher Vector, were commonly used with hand-crafted features in conventional classification methods, but attract less attention since the popularity of deep learning methods.
Variational Disparity Estimation Framework for Plenoptic Image
This paper presents a computational framework for accurately estimating the disparity map of plenoptic images.
How Images Inspire Poems: Generating Classical Chinese Poetry from Images with Memory Networks
Generating poetry from images is much more challenging than generating poetry from text, since images contain very rich visual information which cannot be described completely using several keywords, and a good poem should convey the image accurately.
Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization
Cubic regularization (CR) is an optimization method with emerging popularity due to its capability to escape saddle points and converge to second-order stationary solutions for nonconvex optimization.
Structured Triplet Learning with POS-tag Guided Attention for Visual Question Answering
Visual question answering (VQA) is of significant interest due to its potential to be a strong test of image understanding systems and to probe the connection between language and vision.
End-to-End Video Classification with Knowledge Graphs
In particular, we unify traditional "knowledgeless" machine learning models and knowledge graphs in a novel end-to-end framework.
Video Object Segmentation with Re-identification
Specifically, our Video Object Segmentation with Re-identification (VS-ReID) model includes a mask propagation module and a ReID module.
Truly Multi-modal YouTube-8M Video Classification with Video, Audio, and Text
Beyond that, we extend the original competition by including text information in the classification, making this a truly multi-modal approach with vision, audio and text.
Zoom-in-Net: Deep Mining Lesions for Diabetic Retinopathy Detection
We propose a convolution neural network based algorithm for simultaneously diagnosing diabetic retinopathy and highlighting suspicious regions.
Learning Deep Representations for Scene Labeling with Semantic Context Guided Supervision
The experiments show that our proposed method makes deep models learn more discriminative feature representations without increasing model size or complexity.
Temporal Segment Networks for Action Recognition in Videos
Furthermore, based on the temporal segment networks, we won the video classification track at the ActivityNet challenge 2016 among 24 teams, which demonstrates the effectiveness of TSN and the proposed good practices.
Ranked #18 on
Action Classification
on Moments in Time
(Top 5 Accuracy metric)
Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction
CTR prediction in real-world business is a difficult machine learning problem with large scale nonlinear sparse data.
Chinese Poetry Generation with Planning based Neural Network
Chinese poetry generation is a very challenging task in natural language processing.
Crafting GBD-Net for Object Detection
The effectiveness of GBD-Net is shown through experiments on three object detection datasets, ImageNet, Pascal VOC2007 and Microsoft COCO.
Transferring Object-Scene Convolutional Neural Networks for Event Recognition in Still Images
These newly designed transferring techniques exploit multi-task learning frameworks to incorporate extra knowledge from other networks and additional datasets into the training procedure of event CNNs.
Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition
In this paper, we propose a hybrid representation, which leverages the discriminative capacity of CNNs and the simplicity of descriptor encoding schema for image recognition, with a focus on scene recognition.
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
The other contribution is our study on a series of good practices in learning ConvNets on video data with the help of temporal segment network.
Ranked #3 on
Multimodal Activity Recognition
on EV-Action
CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016
This paper presents the method that underlies our submission to the untrimmed video classification task of ActivityNet Challenge 2016.
Real-time Action Recognition with Enhanced Motion Vector CNNs
The deep two-stream architecture exhibited excellent performance on video based action recognition.
Ranked #70 on
Action Recognition
on UCF101
T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
Temporal and contextual information of videos are not fully investigated and utilized.
Better Exploiting OS-CNNs for Better Event Recognition in Images
Event recognition from still images is one of the most important problems for image understanding.
Towards Good Practices for Very Deep Two-Stream ConvNets
However, for action recognition in videos, the improvement of deep convolutional networks is not so evident.
Ranked #62 on
Action Recognition
on UCF101
Object-Scene Convolutional Neural Networks for Event Recognition in Images
Meanwhile, we investigate different network architectures for OS-CNN design, and adapt the deep (AlexNet) and very-deep (GoogLeNet) networks to the task of event recognition.
DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
In this paper, we propose deformable deep convolutional neural networks for generic object detection.
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty.
Acyclicity Notions for Existential Rules and Their Application to Query Answering in Ontologies
Existential rules are closely related to the Horn fragments of the OWL 2 ontology language; furthermore, several prominent OWL 2 reasoners implement CQ answering by using the chase to materialise all relevant facts.
A Distance-based Paraconsistent Semantics for DL-Lite
DL-Lite is an important family of description logics.
