Search Results for author:
Found 100 papers, 27 papers with code
Efficient N:M Sparse DNN Training Using Algorithm, Architecture, and Dataflow Co-Design
At the algorithm level, a bidirectional weight pruning method, dubbed BDWP, is proposed to leverage the N:M sparsity of weights during both forward and backward passes of DNN training, which can significantly reduce the computational cost while maintaining model accuracy.
Content Reduction, Surprisal and Information Density Estimation for Long Documents
We consider two interesting research questions: 1) how is information distributed over long documents, and 2) how does content reduction, such as token selection and text summarization, affect the information density in long documents.
Joint Gaze-Location and Gaze-Object Detection
In contrast, we reframe the gaze following detection task as detecting human head locations and their gaze followings simultaneously, aiming at jointly detect human gaze location and gaze object in a unified and single-stage pipeline.
Agglomerative Transformer for Human-Object Interaction Detection
We propose an agglomerative Transformer (AGER) that enables Transformer-based human-object interaction (HOI) detectors to flexibly exploit extra instance-level cues in a single-stage and end-to-end manner for the first time.
StableVQA: A Deep No-Reference Quality Assessment Model for Video Stability
Indeed, most existing quality assessment models evaluate video quality as a whole without specifically taking the subjective experience of video stability into consideration.
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models
By minimalistic, we restrict our family of BVQA models to build only upon basic blocks: a video preprocessor (for aggressive spatiotemporal downsampling), a spatial quality analyzer, an optional temporal quality analyzer, and a quality regressor, all with the simplest possible instantiations.
NTIRE 2023 Quality Assessment of Video Enhancement Challenge
61 participating teams submitted their prediction results during the development phase, with a total of 3168 submissions.
Advancing Zero-Shot Digital Human Quality Assessment through Text-Prompted Evaluation
To address this gap, we propose SJTU-H3D, a subjective quality assessment database specifically designed for full-body digital humans.
First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment
Affordance-Centric Question-driven Task Completion (AQTC) has been proposed to acquire knowledge from videos to furnish users with comprehensive and systematic instructions.
GMS-3DQA: Projection-based Grid Mini-patch Sampling for 3D Model Quality Assessment
Model-based 3DQA methods extract features directly from the 3D models, which are characterized by their high degree of complexity.
AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment
With the rapid advancements of the text-to-image generative model, AI-generated images (AGIs) have been widely applied to entertainment, education, social media, etc.
Learning Prescriptive ReLU Networks
We study the problem of learning optimal policy from a set of discrete treatment options using observational data.
Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
In this work, we conduct a systematic study of exposure bias in diffusion models and, intriguingly, we find that the exposure bias could be alleviated with a new sampling method, without retraining the model.
MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos
User-generated content (UGC) live videos are often bothered by various distortions during capture procedures and thus exhibit diverse visual qualities.
A Perceptual Quality Assessment Exploration for AIGC Images
\underline{AI} \underline{G}enerated \underline{C}ontent (\textbf{AIGC}) has gained widespread attention with the increasing efficiency of deep learning in content creation.
VDPVE: VQA Dataset for Perceptual Video Enhancement
Few researchers have specifically proposed a video quality assessment method for video enhancement, and there is also no comprehensive video quality assessment dataset available in public.
Subjective and Objective Quality Assessment for in-the-Wild Computer Graphics Images
Computer graphics images (CGIs) are artificially generated by means of computer programs and are widely perceived under various scenarios, such as games, streaming media, etc.
DANet: Density Adaptive Convolutional Network with Interactive Attention for 3D Point Clouds
Local features and contextual dependencies are crucial for 3D point cloud analysis.
Full Point Encoding for Local Feature Aggregation in 3D Point Clouds
In particular, we achieve state-of-the-art semantic segmentation results of 76% mIoU on S3DIS 6-fold and 72. 2% on S3DIS Area5.
Audio-Visual Quality Assessment for User Generated Content: Database and Method
Specifically, we construct the first UGC AVQA database named the SJTU-UAV database, which includes 520 in-the-wild UGC audio and video (A/V) sequences, and conduct a user study to obtain the mean opinion scores of the A/V sequences.
Incipient Fault Detection in Power Distribution System: A Time-Frequency Embedded Deep Learning Based Approach
Incipient fault detection in power distribution systems is crucial to improve the reliability of the grid.
EEP-3DQA: Efficient and Effective Projection-based 3D Model Quality Assessment
Currently, great numbers of efforts have been put into improving the effectiveness of 3D model quality assessment (3DQA) methods.
Scalable Optimal Multiway-Split Decision Trees with Constraints
However, existing MIP methods that build on an arc-based formulation do not scale well as the number of binary variables is in the order of $\mathcal{O}(2^dN)$, where $d$ and $N$ refer to the depth of the tree and the size of the dataset.
Learning Complementary Policies for Human-AI Teams
We then extend our approach to leverage opportunities and mitigate risks that arise in important contexts in practice: 1) when a team is composed of multiple humans with differential and potentially complementary abilities, 2) when the observational data includes consistent deterministic actions, and 3) when the covariate distribution of future decisions differ from that in the historical data.
DDH-QA: A Dynamic Digital Humans Quality Assessment Database
In recent years, large amounts of effort have been put into pushing forward the real-world application of dynamic digital human (DDH).
DQnet: Cross-Model Detail Querying for Camouflaged Object Detection
Optimizing a convolutional neural network (CNN) for camouflaged object detection (COD) tends to activate local discriminative regions while ignoring complete object extent, causing the partial activation issue which inevitably leads to missing or redundant regions of objects.
Representation Learning for Continuous Action Spaces is Beneficial for Efficient Policy Learning
Meanwhile, we divide the whole learning task into learning with the large-scale representation models in an unsupervised manner and learning with the small-scale policy model in the RL manner. The small policy model facilitates policy learning, while not sacrificing generalization and expressiveness via the large representation model.
Perceptual Quality Assessment for Digital Human Heads
Digital humans are attracting more and more research interest during the last decade, the generation, representation, rendering, and animation of which have been put into large amounts of effort.
MM-PCQA: Multi-Modal Learning for No-reference Point Cloud Quality Assessment
In specific, we split the point clouds into sub-models to represent local geometry distortions such as point shift and down-sampling.
Ranked #1 on
Point Cloud Quality Assessment
on SJTU-PCQA
Treating Point Cloud as Moving Camera Videos: A No-Reference Quality Assessment Metric
Point cloud is one of the most widely used digital representation formats for three-dimensional (3D) contents, the visual quality of which may suffer from noise and geometric shift distortions during the production procedure as well as compression and downsampling distortions during the transmission process.
Towards Learning in Grey Spatiotemporal Systems: A Prophet to Non-consecutive Spatiotemporal Dynamics
To infer region-wise proximity under flexible factor-wise combinations and enable dynamic neighborhood aggregations, we further disentangle compounded influences of exogenous factors on region-wise proximity and learn to aggregate them.
Domain-invariant Prototypes for Semantic Segmentation
In this paper, we present an easy-to-train framework that learns domain-invariant prototypes for domain adaptive semantic segmentation.
MLRIP: Pre-training a military language representation model with informative factual knowledge and professional knowledge base
Incorporating prior knowledge into pre-trained language models has proven to be effective for knowledge-driven NLP tasks, such as entity typing and relation extraction.
Constrained Prescriptive Trees via Column Generation
We introduce a novel path-based mixed-integer program (MIP) formulation which identifies a (near) optimal policy efficiently via column generation.
A Distributionally Robust Resilience Enhancement Strategy for Distribution Networks Considering Decision-Dependent Contingencies
When performing the resilience enhancement for distribution networks, there are two obstacles to reliably model the uncertain contingencies: 1) decision-dependent uncertainty (DDU) due to various line hardening decisions, and 2) distributional ambiguity due to limited outage information during extreme weather events (EWEs).
Subjective Quality Assessment for Images Generated by Computer Graphics
However, limited work has been put forward to tackle the problem of computer graphics generated images' quality assessment (CG-IQA).
A No-reference Quality Assessment Metric for Point Cloud Based on Captured Video Sequences
Point cloud is one of the most widely used digital formats of 3D models, the visual quality of which is quite sensitive to distortions such as downsampling, noise, and compression.
Blind Surveillance Image Quality Assessment via Deep Neural Network Combined with the Visual Saliency
In this paper, we first conduct an example experiment (i. e. the face detection task) to demonstrate that the quality of the SIs has a crucial impact on the performance of the IVSS, and then propose a saliency-based deep neural network for the blind quality assessment of the SIs, which helps IVSS to filter the low-quality SIs and improve the detection and recognition performance.
A No-Reference Deep Learning Quality Assessment Method for Super-resolution Images Based on Frequency Maps
Therefore, in this paper, we propose a no-reference deep-learning image quality assessment method based on frequency maps because the artifacts caused by SISR algorithms are quite sensitive to frequency information.
Deep Neural Network for Blind Visual Quality Assessment of 4K Content
In this paper, we propose a deep learning-based BIQA model for 4K content, which on one hand can recognize true and pseudo 4K content and on the other hand can evaluate their perceptual visual quality.
Perceptual Quality Assessment for Fine-Grained Compressed Images
Nowadays, the mainstream full-reference (FR) metrics are effective to predict the quality of compressed images at coarse-grained levels (the bit rates differences of compressed images are obvious), however, they may perform poorly for fine-grained compressed images whose bit rates differences are quite subtle.
Video-based Human-Object Interaction Detection from Tubelet Tokens
We present a novel vision Transformer, named TUTOR, which is able to learn tubelet tokens, served as highly-abstracted spatiotemporal representations, for video-based human-object interaction (V-HOI) detection.
A Deep Learning based No-reference Quality Assessment Model for UGC Videos
The proposed model utilizes very sparse frames to extract spatial features and dense frames (i. e. the video chunk) with a very low spatial resolution to extract motion features, which thereby has low computational complexity.
Ranked #4 on
Video Quality Assessment
on YouTube-UGC
Cyber-Physical Vulnerability Assessment of P2P Energy Exchanges in Active Distribution Networks
Owing to the decreasing costs of distributed energy resources (DERs) as well as decarbonization policies, power systems are undergoing a modernization process.
Hydrogen and Battery Storage Technologies for Low Cost Energy Decarbonization in Distribution Networks
Deep energy decarbonization cannot be achieved without high penetration of renewables.
A Unified Review of Deep Learning for Automated Medical Coding
Automated medical coding, an essential task for healthcare operation and delivery, makes unstructured data manageable by predicting medical codes from clinical documents.
Enhancing Counterfactual Classification via Self-Training
We approach this task as a domain adaptation problem and propose a self-training algorithm which imputes outcomes with categorical values for finite unseen actions in the observational data to simulate a randomized trial through pseudolabeling, which we refer to as Counterfactual Self-Training (CST).
DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks
However, the existing N:M algorithms only address the challenge of how to train N:M sparse neural networks in a uniform fashion (i. e. every layer has the same N:M sparsity) and suffer from a significant accuracy drop for high sparsity (i. e. when sparsity > 80\%).
Loss Functions for Discrete Contextual Pricing with Observational Data
The goal of this paper is to formulate loss functions that can be used for evaluating pricing policies directly from observational data, rather than going through an intermediate demand estimation stage, which may suffer from bias.
iShape: A First Step Towards Irregular Shape Instance Segmentation
In this paper, we introduce a brand new dataset to promote the study of instance segmentation for objects with irregular shapes.
Ranked #1 on
Instance Segmentation
on iShape
Multitask Balanced and Recalibrated Network for Medical Code Prediction
Nevertheless, automated medical coding is still challenging because of the imbalanced class problem, complex code association, and noise in lengthy documents.
Proactive Rolling-Horizon based Scheduling of Hydrogen Systems for Resilient Power Grids
Deploying distributed energy resources (DERs) and other smart grid technologies have increased the complexity of power grids and made them more vulnerable to natural disasters and cyber-physical-human (CPH) threats.
Learning-Based Nonlinear $H^\infty$ Control via Game-Theoretic Differential Dynamic Programming
In this work, we present a learning-based nonlinear $H^\infty$ control algorithm that guarantee system performance under learned dynamics and disturbance estimate.
No-Reference Quality Assessment for 3D Colored Point Cloud and Mesh Models
Therefore, many related studies such as point cloud quality assessment (PCQA) and mesh quality assessment (MQA) have been carried out to measure the visual quality degradations of 3D models.
Ranked #3 on
Point Cloud Quality Assessment
on WPC
Learned Interpretable Residual Extragradient ISTA for Sparse Coding
Recently, the study on learned iterative shrinkage thresholding algorithm (LISTA) has attracted increasing attentions.
Learning Audio-Visual Dereverberation
We introduce Visually-Informed Dereverberation of Audio (VIDA), an end-to-end approach that learns to remove reverberation based on both the observed monaural sound and visual scene.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Fisher-Pitman permutation tests based on nonparametric Poisson mixtures with application to single cell genomics
This paper investigates the theoretical and empirical performance of Fisher-Pitman-type permutation tests for assessing the equality of unknown Poisson mixture distributions.
Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videos
The proposed VQA framework consists of three modules, the feature extraction module, the quality regression module, and the quality pooling module.
Ranked #12 on
Video Quality Assessment
on MSU NR VQA Database
Proactive Scheduling of Hydrogen Systems for Resilience Enhancement of Distribution Networks
Recent advances in smart grid technologies bring opportunities to better control the modern and complex power grids with renewable integration.
End-to-End Jet Classification of Boosted Top Quarks with the CMS Open Data
We describe a novel application of the end-to-end deep learning technique to the task of discriminating top quark-initiated jets from those originating from the hadronization of a light quark or a gluon.
Multitask Recalibrated Aggregation Network for Medical Code Prediction
Medical coding translates professionally written medical reports into standardized codes, which is an essential part of medical information systems and health insurance reimbursement.
Deep Consensus Learning
For the real image corresponding to the input layout, its mask also is computed by the inference network, and then used by the generator to reconstruct the real image.
Deep Learning Based 3D Segmentation: A Survey
This paper fills the gap and provides a comprehensive survey of the recent progress made in deep learning based 3D segmentation.
Sum-Rate Maximization in Distributed Intelligent Reflecting Surfaces-Aided mmWave Communications
The solution to transmit beamforming at the BS and the phase shifts at the IRS are derived by using the successive convex approximation (SCA)-based algorithm, and a greedy algorithm is proposed to design the IRS switch vector.
Non-uniform Motion Deblurring with Blurry Component Divided Guidance
To tackle the above problems, we present a deep two-branch network to deal with blurry images via a component divided module, which divides an image into two components based on the representation of blurry degree.
Counterfactual Self-Training
We approach this task as a domain adaptation problem and propose a self-training algorithm which imputes outcomes for the unseen actions in the observational data to simulate a randomized trial.
Uplink Achievable Rate Maximization for Reconfigurable Intelligent Surface Aided Millimeter Wave Systems with Resolution-Adaptive ADCs
In this letter, we investigate the uplink of a reconfigurable intelligent surface (RIS)-aided millimeter-wave (mmWave) multi-user system.
Multi-Objective PMU Allocation for Resilient Power System Monitoring
Phasor measurement units (PMUs) enable better system monitoring and security enhancement in smart grids.
Fatigue-aware Bandits for Dependent Click Models
Based on user's feedback, the platform learns the relevance of the underlying content as well as the discounting effect due to content fatigue.
Secrecy Rate Maximization for Intelligent Reflecting Surface Aided SWIPT Systems
Simultaneous wireless information and power transfer (SWIPT) and intelligent reflecting surface (IRS) are two promising techniques for providing enhanced wireless communication capability and sustainable energy supply to energy-constrained wireless devices.
Reconfigurable Intelligent Surfaces Aided mmWave NOMA: Joint Power Allocation,Phase Shifts, and Hybrid Beamforming Optimization
Then, we solve the power allocation problem under fixed phase shifts of the RIS and hybrid beamforming.
Model Distillation for Revenue Optimization: Interpretable Personalized Pricing
Data-driven pricing strategies are becoming increasingly common, where customers are offered a personalized price based on features that are predictive of their valuation of a product.
Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis
This paper focuses on a recent emerged task, layout-to-image, to learn generative models that are capable of synthesizing photo-realistic images from spatial layout (i. e., object bounding boxes configured in an image lattice) and style (i. e., structural and appearance variations encoded by latent vectors).
Ranked #2 on
Layout-to-Image Generation
on COCO-Stuff 128x128
Machine learning based co-creative design framework
We propose a flexible, co-creative framework bringing together multiple machine learning techniques to assist human users to efficiently produce effective creative designs.
Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation
Most learning-based super-resolution (SR) methods aim to recover high-resolution (HR) image from a given low-resolution (LR) image via learning on LR-HR image pairs.
PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation
Our method is a natural extension of 2D-keypoint approaches that successfully work on RGB based 6DoF estimation.
Ranked #1 on
6D Pose Estimation using RGBD
on YCB-Video
(Mean ADD-S metric)
Making Predictive Coding Networks Generative
This paper studies this phenomenon, and proposes a simple solution that promotes the generation of input samples that resemble the training inputs.
Image Synthesis From Reconfigurable Layout and Style
Despite remarkable recent progress on both unconditional and conditional image synthesis, it remains a long-standing problem to learn generative models that are capable of synthesizing realistic and sharp images from reconfigurable spatial layout (i. e., bounding boxes + class labels in an image lattice) and style (i. e., structural and appearance variations encoded by latent vectors), especially at high resolution.
Ranked #2 on
Layout-to-Image Generation
on COCO-Stuff 64x64
Attentive Normalization
In state-of-the-art deep neural networks, both feature normalization and feature attention have become ubiquitous.
Ranked #71 on
Instance Segmentation
on COCO minival
3D Virtual Garment Modeling from RGB Images
The predicted landmarks are used for estimating sizing information of the garment.
A support vector regression-based multi-fidelity surrogate model
Computational simulations with different fidelity have been widely used in engineering design.
Pose Guided Fashion Image Synthesis Using Deep Generative Model
In order to formulate the framework, we employ one generator and two discriminators for image synthesis.
High-low level support vector regression prediction approach (HL-SVR) for data modeling with input parameters of unequal sample sizes
The proposed approach is consisted of low-level SVR models for the input parameters of larger sample sizes and high-level SVR model for the input parameters of smaller sample sizes.
Dynamic Learning with Frequent New Product Launches: A Sequential Multinomial Logit Bandit Problem
Motivated by the phenomenon that companies introduce new products to keep abreast with customers' rapidly changing tastes, we consider a novel online learning setting where a profit-maximizing seller needs to learn customers' preferences through offering recommendations, which may contain existing products and new products that are launched in the middle of a selling period.
Ranking-Based Autoencoder for Extreme Multi-label Classification
Extreme Multi-label classification (XML) is an important yet challenging machine learning task, that assigns to each instance its most relevant candidate labels from an extremely large label collection, where the numbers of labels, features and instances could be thousands or millions.
Dynamic Learning of Sequential Choice Bandit Problem under Marketing Fatigue
Based on user feedback, the platform dynamically learns users' abandonment distribution and their valuations of messages to determine the length of the sequence and the order of the messages, while maximizing the cumulative payoff over a horizon of length T. We refer to this online learning task as the sequential choice bandit problem.
Real time backbone for semantic segmentation
The rapid development of autonomous driving in recent years presents lots of challenges for scene understanding.
Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translation
In experiments, the proposed SPAP is tested in GANs on the Celeba-HQ-128 dataset~\cite{karras2017progressive}, and tested in CycleGANs on the Image-to-Image translation datasets including the Cityscape dataset~\cite{cordts2016cityscapes}, Facade and Aerial Maps dataset~\cite{zhu2017unpaired}, both obtaining better performance.
Sketching Method for Large Scale Combinatorial Inference
In order to test the hypotheses on their topological structures, we propose two adjacency matrix sketching frameworks: neighborhood sketching and subgraph sketching.
Interpretable Spatio-temporal Attention for Video Action Recognition
Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action recognition.
Machine Learning in High Energy Physics Community White Paper
In this document we discuss promising future research and development areas for machine learning in particle physics.
BIG-bench Machine Learning
Vocal Bursts Intensity Prediction
AF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization System
Based on the extended fingerprint database, the accuracy of indoor localization system can be improved with reduced human effort.
Networking and Internet Architecture
Partial Labeled Gastric Tumor Segmentation via patch-based Reiterative Learning
Gastric cancer is the second leading cause of cancer-related deaths worldwide, and the major hurdle in biomedical image analysis is the determination of the cancer extent.
Towards Interpretable R-CNN by Unfolding Latent Structures
We focus on weakly-supervised extractive rationale generation, that is learning to unfold latent discriminative part configurations of object instances automatically and simultaneously in detection without using any supervision for part configurations.
OpenFermion: The Electronic Structure Package for Quantum Computers
Quantum simulation of chemistry and materials is predicted to be an important application for both near-term and fault-tolerant quantum devices.
Quantum Physics Chemical Physics Computational Physics
Multimodal Content Analysis for Effective Advertisements on YouTube
The objective of this work is then to measure the effectiveness of an advertisement, and to recommend a useful set of features to advertisement designers to make it more successful and approachable to users.
Non-convex Statistical Optimization for Sparse Tensor Graphical Model
We consider the estimation of sparse graphical models that characterize the dependency structure of high-dimensional tensor-valued data.
Stabilized Nearest Neighbor Classifier and Its Statistical Properties
In this paper, we introduce a general measure of classification instability (CIS) to quantify the sampling variability of the prediction made by a classification method.
Consistent selection of tuning parameters via variable selection stability
The key idea is to select the tuning parameters so that the resultant penalized regression model is stable in variable selection.
