Search Results for author:
Found 210 papers, 78 papers with code
A Novel Framework Based on Medical Concept Driven Attention for Explainable Medical Code Prediction via External Knowledge
Medical code prediction from clinical notes aims at automatically associating medical codes with the clinical notes.
Word Reordering for Zero-shot Cross-lingual Structured Prediction
Adapting word order from one language to another is a key problem in cross-lingual structured prediction.
Task-oriented Domain-specific Meta-Embedding for Text Classification
Meta-embedding learning, which combines complementary information in different word embeddings, have shown superior performances across different Natural Language Processing tasks.
A Unified Encoding of Structures in Transition Systems
Transition systems usually contain various dynamic structures (e. g., stacks, buffers).
Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data
The former indicates that representation collapse in local model will subsequently impact the global model and other local models.
Innovative Quantitative Analysis for Disease Progression Assessment in Familial Cerebral Cavernous Malformations
To alleviate this problem, we propose a quantitative statistical framework for FCCM, comprising an efficient annotation module, an FCCM lesion segmentation module, and an FCCM lesion quantitative statistics module.
OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models
We also observe that the initiation denoising timestep for noise blending is the key to identity preservation and layout.
Segmentation Guided Sparse Transformer for Under-Display Camera Image Restoration
Specifically, we utilize sparse self-attention to filter out redundant information and noise, directing the model's attention to focus on the features more relevant to the degraded regions in need of reconstruction.
Feynman Diagrams as Computational Graphs
We propose a computational graph representation of high-order Feynman diagrams in Quantum Field Theory (QFT), applicable to any combination of spatial, temporal, momentum, and frequency domains.
Zero-Shot Aerial Object Detection with Visual Description Regularization
Instead of directly encoding the descriptions into class embedding space which suffers from the representation gap problem, we propose to infuse the prior inter-class visual similarity conveyed in the descriptions into the embedding learning.
PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
We introduce a privacy auditing scheme for ML models that relies on membership inference attacks using generated data as "non-members".
PromptRR: Diffusion Models as Prompt Generators for Single Image Reflection Removal
For the prompt generation, we first propose a prompt pre-training strategy to train a frequency prompt encoder that encodes the ground-truth image into LF and HF prompts.
Anything in Any Scene: Photorealistic Video Object Insertion
Our proposed general framework encompasses three key processes: 1) integrating a realistic object into a given scene video with proper placement to ensure geometric realism; 2) estimating the sky and environmental lighting distribution and simulating realistic shadows to enhance the light realism; 3) employing a style transfer network that refines the final video output to maximize photorealism.
GroundingGPT:Language Enhanced Multi-modal Grounding Model
Beyond capturing global information like other multi-modal models, our proposed model excels at tasks demanding a detailed understanding of local information within the input.
Dual Teacher Knowledge Distillation with Domain Alignment for Face Anti-spoofing
In this paper, we propose a domain adversarial attack (DAA) method to mitigate the training instability problem by adding perturbations to the input images, which makes them indistinguishable across domains and enables domain alignment.
Knowledge Enhanced Conditional Imputation for Healthcare Time-series
This study presents a novel approach to addressing the challenge of missing data in multivariate time series, with a particular focus on the complexities of healthcare data.
Towards Real-World Blind Face Restoration with Generative Diffusion Prior
We propose BFRffusion which is thoughtfully designed to effectively extract features from low-quality face images and could restore realistic and faithful facial details with the generative prior of the pretrained Stable Diffusion.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Multi-task Language Understanding
on MMLU
(using extra training data)
Research on Multilingual Natural Scene Text Detection Algorithm
Natural scene text detection is a significant challenge in computer vision, with tremendous potential applications in multilingual, diverse, and complex text scenarios.
VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruning
Then, we model these visual cues and correspondences by a joint visual-spatial fusion module, simultaneously embedding visual cues into correspondences for pruning.
Learning to Skip for Language Modeling
Overparameterized large-scale language models have impressive generalization performance of in-context few-shot learning.
Boost Adversarial Transferability by Uniform Scale and Mix Mask Method
To address these challenges, we propose a framework called Uniform Scale and Mix Mask Method (US-MM) for adversarial example generation.
Complementary Advantages of ChatGPTs and Human Readers in Reasoning: Evidence from English Text Reading Comprehension
Our study reveals that human readers and ChatGPTs have their respective advantages and disadvantages in drawing inferences from text reading comprehension, unlocking a complementary relationship in text-based reasoning.
Pseudo Label-Guided Data Fusion and Output Consistency for Semi-Supervised Medical Image Segmentation
Inspired by semi-supervised algorithms that use both labeled and unlabeled data for training, we propose the PLGDF framework, which builds upon the mean teacher network for segmenting medical images with less annotation.
Controlled Decoding from Language Models
KL-regularized reinforcement learning (RL) is a popular alignment framework to control the language model responses towards high reward outcomes.
Language Modelling
Multi-Objective Reinforcement Learning
+1
VCL Challenges 2023 at ICCV 2023 Technical Report: Bi-level Adaptation Method for Test-time Adaptive Object Detection
This report outlines our team's participation in VCL Challenges B Continual Test_time Adaptation, focusing on the technical details of our approach.
SCB-Dataset3: A Benchmark for Detecting Student Classroom Behavior
The use of deep learning methods to automatically detect students' classroom behavior is a promising approach for analyzing their class performance and improving teaching effectiveness.
Estimation and Testing of Forecast Rationality with Many Moments
We in this paper utilize P-GMM (Cheng and Liao, 2015) moment selection procedure to select valid and relevant moments for estimating and testing forecast rationality under the flexible loss proposed by Elliott et al. (2005).
Base Station Beamforming Design for Near-field XL-IRS Beam Training
However, this approach may cause degraded beam training performance in practice due to the near-field channel model of the BS-IRS link.
Deep Video Restoration for Under-Display Camera
With the pipeline, we build the first large-scale UDC video restoration dataset called PexelsUDC, which includes two subsets named PexelsUDC-T and PexelsUDC-P corresponding to different displays for UDC.
Learning Speech Representation From Contrastive Token-Acoustic Pretraining
However, existing contrastive learning methods in the audio field focus on extracting global descriptive information for downstream audio classification tasks, making them unsuitable for TTS, VC, and ASR tasks.
Dual-Decoder Consistency via Pseudo-Labels Guided Data Augmentation for Semi-Supervised Medical Image Segmentation
In this paper, we present a novel semi-supervised learning method, Dual-Decoder Consistency via Pseudo-Labels Guided Data Augmentation (DCPA), for medical image segmentation.
Semantic-aware Consistency Network for Cloth-changing Person Re-Identification
Despite recent progress in CC-ReID, existing approaches are still hindered by the interference of clothing variations since they lack effective constraints to keep the model consistently focused on clothing-irrelevant regions.
Blind Face Restoration for Under-Display Camera via Dictionary Guided Transformer
However, due to the characteristics of the display, images taken by UDC suffer from significant quality degradation.
FashionLOGO: Prompting Multimodal Large Language Models for Fashion Logo Embeddings
Logo embedding plays a crucial role in various e-commerce applications by facilitating image retrieval or recognition, such as intellectual property protection and product search.
Development of a Knowledge Graph Embeddings Model for Pain
This paper describes the construction of such knowledge graph embedding models of pain concepts, extracted from the unstructured text of mental health electronic health records, combined with external knowledge created from relations described in SNOMED CT, and their evaluation on a subject-object link prediction task.
Deep Semantic Graph Matching for Large-scale Outdoor Point Clouds Registration
The adjacent points with the same category labels are then clustered together using the Euclidean clustering algorithm to obtain the semantic instances, which are represented by three kinds of attributes including spatial location information, semantic categorical information, and global geometric shape information.
Fine-grained building roof instance segmentation based on domain adapted pretraining and composite dual-backbone
The diversity of building architecture styles of global cities situated on various landforms, the degraded optical imagery affected by clouds and shadows, and the significant inter-class imbalance of roof types pose challenges for designing a robust and accurate building roof instance segmentor.
HGDNet: A Height-Hierarchy Guided Dual-Decoder Network for Single View Building Extraction and Height Estimation
Unifying the correlative single-view satellite image building extraction and height estimation tasks indicates a promising way to share representations and acquire generalist model for large-scale urban 3D reconstruction.
Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation
Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps.
Class-Incremental Semantic Segmentation
Knowledge Distillation
Class-Specific Distribution Alignment for Semi-Supervised Medical Image Classification
Despite the success of deep neural networks in medical image classification, the problem remains challenging as data annotation is time-consuming, and the class distribution is imbalanced due to the relative scarcity of diseases.
Image Classification
Semi-supervised Medical Image Classification
Minimally-Supervised Speech Synthesis with Conditional Diffusion Model and Language Model: A Comparative Study of Semantic Coding
However, existing methods suffer from three problems: the high dimensionality and waveform distortion of discrete speech representations, the prosodic averaging problem caused by the duration prediction model in non-autoregressive frameworks, and the information redundancy and dimension explosion problems of existing semantic encoding methods.
LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement
In this paper, we address this limitation by proposing a degradation-aware learning scheme for LLIE using diffusion models, which effectively integrates degradation and image priors into the diffusion process, resulting in improved image enhancement.
Semi-Supervised Medical Image Segmentation with Co-Distribution Alignment
Medical image segmentation has made significant progress when a large amount of labeled data are available.
An Intelligent Remote Sensing Image Quality Inspection System
Due to the inevitable presence of quality problems, quality inspection of remote sensing images is indeed an indispensable step between the acquisition and the application of them.
Bridging the Gap: Multi-Level Cross-Modality Joint Alignment for Visible-Infrared Person Re-Identification
Visible-Infrared person Re-IDentification (VI-ReID) is a challenging cross-modality image retrieval task that aims to match pedestrians' images across visible and infrared cameras.
Cross-Modality Person Re-identification
Image Classification
+4
Joint Adversarial and Collaborative Learning for Self-Supervised Action Recognition
Considering the instance-level discriminative ability, contrastive learning methods, including MoCo and SimCLR, have been adapted from the original image representation learning task to solve the self-supervised skeleton-based action recognition task.
BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training
In this study, we systematically analyze and compare various mainstream and cutting-edge automatic metrics from the perspective of their guidance for training machine translation systems.
Seeing is not Believing: An Identity Hider for Human Vision Privacy Protection
Massive captured face images are stored in the database for the identification of individuals.
Improving Text Matching in E-Commerce Search with A Rationalizable, Intervenable and Fast Entity-Based Relevance Model
We also show that pretraining the QE module with auto-generated QE data from user logs can further improve the overall performance.
PCDAL: A Perturbation Consistency-Driven Active Learning Approach for Medical Image Segmentation and Classification
To address this limitation, we propose an AL-based method that can be simultaneously applied to 2D medical image classification, segmentation, and 3D medical image segmentation tasks.
Valley: Video Assistant with Large Language model Enhanced abilitY
Large language models (LLMs), with their remarkable conversational capabilities, have demonstrated impressive performance across various applications and have emerged as formidable AI assistants.
Boosting Fast and High-Quality Speech Synthesis with Linear Diffusion
When decreasing the number of sampling steps (i. e., the number of line segments used to fit the path), the ease of fitting straight lines compared to curves allows us to generate higher quality samples from a random noise with fewer iterations.
GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions
Second, we introduce a residual dense transformer block (RDTB) as the final GridFormer layer.
Improving speech translation by fusing speech and text
To tackle these gaps, we propose \textbf{F}use-\textbf{S}peech-\textbf{T}ext (\textbf{FST}), a cross-modal model which supports three distinct input modalities for translation: speech, text, and fused speech-text.
Graph Propagation Transformer for Graph Representation Learning
The core insight of our method is to fully consider the information propagation among nodes and edges in a graph when building the attention module in the transformer blocks.
Ranked #2 on
Graph Regression
on PCQM4M-LSC
(Validation MAE metric)
PaLM 2 Technical Report
Through extensive evaluations on English and multilingual language, and reasoning tasks, we demonstrate that PaLM 2 has significantly improved quality on downstream tasks across different model sizes, while simultaneously exhibiting faster and more efficient inference compared to PaLM.
Ranked #1 on
Question Answering
on StrategyQA
Student Classroom Behavior Detection based on YOLOv7-BRA and Multi-Model Fusion
We constructed a dataset, which contained 11, 248 labels and 4, 001 images, with an emphasis on the common behavior of raising hands in a classroom setting (Student Classroom Behavior dataset, SCB-Dataset).
RFR-WWANet: Weighted Window Attention-Based Recovery Feature Resolution Network for Unsupervised Image Registration
Furthermore, shifted window partitioning operations are inflexible, indicating that they cannot perceive the semantic information over uncertain distances and automatically bridge the global connections between windows.
A Soft Coordination Method of Heterogeneous Devices in Distribution System Voltage Control
The proposed method achieves the soft coordination by establishing a modified actor-critic algorithm to train a proxy model of inverters.
GRIG: Few-Shot Generative Residual Image Inpainting
Image inpainting is the task of filling in missing or masked region of an image with semantically meaningful contents.
The Cascaded Forward Algorithm for Neural Network Training
Backpropagation algorithm has been widely used as a mainstream learning procedure for neural networks in the past decade, and has played a significant role in the development of deep learning.
Feature Completion Transformer for Occluded Person Re-identification
In this paper, different from most previous works that discard the occluded region, we propose a Feature Completion Transformer (FCFormer) to implicitly complement the semantic information of occluded parts in the feature space.
Noise2Music: Text-conditioned Music Generation with Diffusion Models
We introduce Noise2Music, where a series of diffusion models is trained to generate high-quality 30-second music clips from text prompts.
Ranked #2 on
Text-to-Music Generation
on MusicCaps
Spatio-Temporal Point Process for Multiple Object Tracking
As such, we propose a novel framework that can effectively predict and mask-out the noisy and confusing detection results before associating the objects into trajectories.
Spatio-Temporal Context Modeling for Road Obstacle Detection
The results indicate that our method with spatio-temporal context modeling is superior to existing methods for road obstacle detection.
A Multi-Scale Framework for Out-of-Distribution Detection in Dermoscopic Images
The automatic detection of skin diseases via dermoscopic images can improve the efficiency in diagnosis and help doctors make more accurate judgments.
Mortality Prediction with Adaptive Feature Importance Recalibration for Peritoneal Dialysis Patients: a deep-learning-based study on a real-world longitudinal follow-up dataset
Here, our objective is to develop a deep learning model for a real-time, individualized, and interpretable mortality prediction model - AICare.
Robust Remote Sensing Scene Classification with Multi-View Voting and Entropy Ranking
Deep convolutional neural networks have been widely used in scene classification of remotely sensed images.
UnifySpeech: A Unified Framework for Zero-shot Text-to-Speech and Voice Conversion
Text-to-speech (TTS) and voice conversion (VC) are two different tasks both aiming at generating high quality speaking voice according to different input modality.
Learning to Detect and Segment for Open Vocabulary Object Detection
With such a conditional design, the detection model is bridged by the semantic embedding to offer strongly generalizable class-wise box and mask prediction.
Restoring Vision in Hazy Weather with Hierarchical Contrastive Learning
HCD consists of a hierarchical dehazing network (HDN) and a novel hierarchical contrastive loss (HCL).
Emotion Selectable End-to-End Text-based Speech Editing
To achieve this task, we propose Emo-CampNet (emotion CampNet), which can provide the option of emotional attributes for the generated speech in text-based speech editing and has the one-shot ability to edit unseen speakers' speech.
Towards Real World HDRTV Reconstruction: A Data Synthesis-based Approach
To solve this problem, we propose a learning-based data synthesis approach to learn the properties of real-world SDRTVs by integrating several tone mapping priors into both network structures and loss functions.
A Survey of Deep Face Restoration: Denoise, Super-Resolution, Deblur, Artifact Removal
Second, we discuss the challenges of face restoration.
Rethinking Image Restoration for Object Detection
To address the issue, we propose a targeted adversarial attack in the restoration procedure to boost object detection performance after restoration.
DLUNet: Semi-supervised Learning based Dual-Light UNet for Multi-organ Segmentation
In the training phase, it consists of two light UNets, which make full use of label and unlabeled data simultaneously by using consistent-based learning.
An Initial Investigation for Detecting Vocoder Fingerprints of Fake Audio
Many effective attempts have been made for fake audio detection.
Multiple Instance Neural Networks Based on Sparse Attention for Cancer Detection using T-cell Receptor Sequences
Among different types of data used to answer this biological question, studies based on T cell receptors (TCRs) are under recent spotlight due to the growing appreciation of the roles of the host immunity system in tumor biology.
P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos
While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging.
On Mitigating Hard Clusters for Face Clustering
Face clustering is a promising way to scale up face recognition systems using large-scale unlabeled face images.
Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection
This work aims to solve the problem from two perspectives: uncertainty modeling and hard example mining.
Ranked #70 on
Object Detection
on COCO test-dev
SJ-HD^2R: Selective Joint High Dynamic Range and Denoising Imaging for Dynamic Scenes
To further leverage these two paradigms, we propose a selective and joint HDR and denoising (SJ-HD$^2$R) imaging framework, utilizing scenario-specific priors to conduct the path selection with an accuracy of more than 93. 3$\%$.
Multi-View Imputation and Cross-Attention Network Based on Incomplete Longitudinal and Multimodal Data for Conversion Prediction of Mild Cognitive Impairment
To address these challenges, a multi-view imputation and cross-attention network (MCNet) was proposed to integrate data imputation and MCI conversion prediction in a unified framework.
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.
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.
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.
Uncertainty-based Network for Few-shot Image Classification
Specifically, we first data augment and classify the query instance and calculate the mutual information of these classification scores.
FRIH: Fine-grained Region-aware Image Harmonization
Image harmonization aims to generate a more realistic appearance of foreground and background for a composite image.
The Value of Information in Stopping Problems
We consider stopping problems in which a decision maker (DM) faces an unknown state of nature and decides sequentially whether to stop and take an irreversible action; pay a fee and obtain additional information; or wait without acquiring information.
Understanding CNNs from excitations
To organize these excitations into final saliency maps, we introduce a double-chain backpropagation procedure.
Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition
Subject-invariant facial action unit (AU) recognition remains challenging for the reason that the data distribution varies among subjects.
GigaST: A 10,000-hour Pseudo Speech Translation Corpus
The training set is translated by a strong machine translation system and the test set is translated by human.
PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision
Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions like consistency loss to guide the learning, which, inevitably, leads to inferior results in real-world scenarios with unseen poses.
Ranked #37 on
3D Human Pose Estimation
on MPI-INF-3DHP
A Long Short-term Memory Based Recurrent Neural Network for Interventional MRI Reconstruction
Here we proposed a convolutional long short-term memory (Conv-LSTM) based recurrent neural network (RNN), or ConvLR, to reconstruct interventional images with golden-angle radial sampling.
EventFormer: AU Event Transformer for Facial Action Unit Event Detection
Facial action units (AUs) play an indispensable role in human emotion analysis.
Geometric Synthesis: A Free lunch for Large-scale Palmprint Recognition Model Pretraining
In this paper, by observing that palmar creases are the key information to deep-learning-based palmprint recognition, we propose to synthesize training data by manipulating palmar creases.
An STDP-Based Supervised Learning Algorithm for Spiking Neural Networks
Compared with rate-based artificial neural networks, Spiking Neural Networks (SNN) provide a more biological plausible model for the brain.
End-to-end video instance segmentation via spatial-temporal graph neural networks
Specifically, graph nodes representing instance features are used for detection and segmentation while graph edges representing instance relations are used for tracking.
NeuralDPS: Neural Deterministic Plus Stochastic Model with Multiband Excitation for Noise-Controllable Waveform Generation
We have also verified through experiments that this method can effectively control the noise components in the predicted speech and adjust the SNR of speech.
DAMO-NLP at SemEval-2022 Task 11: A Knowledge-based System for Multilingual Named Entity Recognition
Our system wins 10 out of 13 tracks in the MultiCoNER shared task.
Multilingual Named Entity Recognition
Named Entity Recognition
+1
CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editing
It can solve unnatural prosody in the edited region and synthesize the speech corresponding to the unseen words in the transcript.
Single UHD Image Dehazing via Interpretable Pyramid Network
Currently, most single image dehazing models cannot run an ultra-high-resolution (UHD) image with a single GPU shader in real-time.
ADD 2022: the First Audio Deep Synthesis Detection Challenge
Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021.
Singing-Tacotron: Global duration control attention and dynamic filter for End-to-end singing voice synthesis
Firstly, we propose a global duration control attention mechanism for the SVS model.
SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations
Unlike the original per grid cell object masks, SODAR is implicitly supervised to learn mask representations that encode geometric structure of nearby objects and complement adjacent representations with context.
LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling
Compared with traditional task-irrelevant downsampling methods, task-oriented neural networks have shown improved performance in point cloud downsampling range.
COVID-19 Hospitalizations Forecasts Using Internet Search Data
As the COVID-19 spread over the globe and new variants of COVID-19 keep occurring, reliable real-time forecasts of COVID-19 hospitalizations are critical for public health decision on medical resources allocations such as ICU beds, ventilators, and personnel to prepare for the surge of COVID-19 pandemics.
IoTGAN: GAN Powered Camouflage Against Machine Learning Based IoT Device Identification
In this research, we propose a novel attack strategy named IoTGAN to manipulate an IoT device's traffic such that it can evade machine learning based IoT device identification.
Deep Probabilistic Graph Matching
Most previous learning-based graph matching algorithms solve the \textit{quadratic assignment problem} (QAP) by dropping one or more of the matching constraints and adopting a relaxed assignment solver to obtain sub-optimal correspondences.
GLAN: A Graph-based Linear Assignment Network
The experimental results on a synthetic dataset reveal that our method outperforms state-of-the-art baselines and achieves consistently high accuracy with the increment of the problem size.
Powerful Graph Convolutioal Networks with Adaptive Propagation Mechanism for Homophily and Heterophily
To address this problem, in this paper we design a novel propagation mechanism, which can automatically change the propagation and aggregation process according to homophily or heterophily between node pairs.
Camera-aware Style Separation and Contrastive Learning for Unsupervised Person Re-identification
Unsupervised person re-identification (ReID) is a challenging task without data annotation to guide discriminative learning.
ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition
As text representations take the most important role in MNER, in this paper, we propose {\bf I}mage-{\bf t}ext {\bf A}lignments (ITA) to align image features into the textual space, so that the attention mechanism in transformer-based pretrained textual embeddings can be better utilized.
Ranked #1 on
Multi-modal Named Entity Recognition
on Twitter-17
Multi-modal Named Entity Recognition
named-entity-recognition
+1
GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
Scaling language models with more data, compute and parameters has driven significant progress in natural language processing.
Ranked #10 on
Language Modelling
on LAMBADA
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition
In this paper, to make better use of the movement patterns introduced by extreme augmentations, a Contrastive Learning framework utilizing Abundant Information Mining for self-supervised action Representation (AimCLR) is proposed.
Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer
Therefore, we propose a transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components (e. g. human body or joint parts) and selectively match non-occluded parts correspondingly.
MC-Blur: A Comprehensive Benchmark for Image Deblurring
Blur artifacts can seriously degrade the visual quality of images, and numerous deblurring methods have been proposed for specific scenarios.
Topological and Algebraic Structures of Atanassov's Intuitionistic Fuzzy-Values Space
By introducing a new operator for IFVs via the linear order based on a score function and an accuracy function, we show that such an operator is a strong negation on IFVs.
Direct Multi-view Multi-person 3D Pose Estimation
Instead of estimating 3D joint locations from costly volumetric representation or reconstructing the per-person 3D pose from multiple detected 2D poses as in previous methods, MvP directly regresses the multi-person 3D poses in a clean and efficient way, without relying on intermediate tasks.
Ranked #3 on
3D Multi-Person Pose Estimation
on Panoptic
(using extra training data)
CMTR: Cross-modality Transformer for Visible-infrared Person Re-identification
The existing convolutional neural network-based methods mainly face the problem of insufficient perception of modalities' information, and can not learn good discriminative modality-invariant embeddings for identities, which limits their performance.
Cross-Modality Person Re-identification
Person Re-Identification
PnP-DETR: Towards Efficient Visual Analysis with Transformers
Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result.
Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition
To address these issues, we propose our DAN with three key components: Feature Clustering Network (FCN), Multi-head cross Attention Network (MAN), and Attention Fusion Network (AFN).
Ranked #8 on
Facial Expression Recognition (FER)
on AffectNet
Facial Expression Recognition
Facial Expression Recognition (FER)
MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations
Entity retrieval, which aims at disambiguating mentions to canonical entities from massive KBs, is essential for many tasks in natural language processing.
Ranked #1 on
Entity Retrieval
on ZESHEL
Joint Graph Learning and Matching for Semantic Feature Correspondence
In this paper, we propose a joint \emph{graph learning and matching} network, named GLAM, to explore reliable graph structures for boosting graph matching.
Secoco: Self-Correcting Encoding for Neural Machine Translation
This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with input noise for robust neural machine translation by introducing self-correcting predictors.
Learning Class-level Prototypes for Few-shot Learning
Few-shot learning aims to recognize new categories using very few labeled samples.
Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables
One is a 1D weight vector used for image-level scenario adaptation, the other is a 3D weight map aimed for pixel-wise category fusion.
Multi-View Cross-Lingual Structured Prediction with Minimum Supervision
In structured prediction problems, cross-lingual transfer learning is an efficient way to train quality models for low-resource languages, and further improvement can be obtained by learning from multiple source languages.
Risk Minimization for Zero-shot Sequence Labeling
In this paper, we propose a novel unified framework for zero-shot sequence labeling with minimum risk training and design a new decomposable risk function that models the relations between the predicted labels from the source models and the true labels.
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
Ultra-High-Definition Image Dehazing via Multi-Guided Bilateral Learning
To address the problem, we propose a novel network capable of real-time dehazing of 4K images on a single GPU, which consists of three deep CNNs.
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
Autocorrect in the Process of Translation --- Multi-task Learning Improves Dialogue Machine Translation
Automatic translation of dialogue texts is a much needed demand in many real life scenarios.
Adaptive Feature Alignment for Adversarial Training
Based on this observation, we propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths.
Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report
As the quality of mobile cameras starts to play a crucial role in modern smartphones, more and more attention is now being paid to ISP algorithms used to improve various perceptual aspects of mobile photos.
The Volctrans Neural Speech Translation System for IWSLT 2021
For offline speech translation, our best end-to-end model achieves 8. 1 BLEU improvements over the benchmark on the MuST-C test set and is even approaching the results of a strong cascade solution.
GSPMD: General and Scalable Parallelization for ML Computation Graphs
We present GSPMD, an automatic, compiler-based parallelization system for common machine learning computations.
Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning
We find empirically that the contextual representations computed on the retrieval-based input view, constructed through the concatenation of a sentence and its external contexts, can achieve significantly improved performance compared to the original input view based only on the sentence.
Ranked #1 on
Named Entity Recognition (NER)
on CMeEE
FedCom: A Byzantine-Robust Local Model Aggregation Rule Using Data Commitment for Federated Learning
The results demonstrate its effectiveness and superior performance compared to the state-of-the-art Byzantine-robust schemes in defending against typical data poisoning and model poisoning attacks under practical Non-IID data distributions.
Half-Truth: A Partially Fake Audio Detection Dataset
Therefore, this paper develops such a dataset for half-truth audio detection (HAD).
IDOL-Net: An Interactive Dual-Domain Parallel Network for CT Metal Artifact Reduction
Since the dual-domain MAR methods can leverage the hybrid information from both sinogram and image domains, they have significantly improved the performance compared to single-domain methods.
Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translation
Automatic translation of dialogue texts is a much needed demand in many real life scenarios.
A Universal Model for Cross Modality Mapping by Relational Reasoning
With the aim of matching a pair of instances from two different modalities, cross modality mapping has attracted growing attention in the computer vision community.
Regional and Sectoral Structures and Their Dynamics of Chinese Economy: A Network Perspective from Multi-Regional Input-Output Tables
Quantified metrics assessing the relative importance of the province-sectors in the national economy echo the national and regional economic development policies to a certain extent.
Community Detection
Physics and Society
General Economics
Economics
Applications
Attention Models for Point Clouds in Deep Learning: A Survey
Recently, the advancement of 3D point clouds in deep learning has attracted intensive research in different application domains such as computer vision and robotic tasks.
DAN-Net: Dual-Domain Adaptive-Scaling Non-local Network for CT Metal Artifact Reduction
With the rapid development of deep learning in the field of medical imaging, several network models have been proposed for metal artifact reduction (MAR) in CT.
Isolation mechanisms for high-speed packet-processing pipelines
We have open sourced the code for Menshen's hardware and software at https://isolation. quest/.
Networking and Internet Architecture Hardware Architecture
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
To overcome such limitations, we propose a new Tokens-To-Token Vision Transformer (T2T-ViT), which incorporates 1) a layer-wise Tokens-to-Token (T2T) transformation to progressively structurize the image to tokens by recursively aggregating neighboring Tokens into one Token (Tokens-to-Token), such that local structure represented by surrounding tokens can be modeled and tokens length can be reduced; 2) an efficient backbone with a deep-narrow structure for vision transformer motivated by CNN architecture design after empirical study.
Ranked #400 on
Image Classification
on ImageNet
Search for axion-like dark matter using solid-state nuclear magnetic resonance
We calibrated the detector and characterized the excitation spectrum and relaxation parameters of the nuclear spin ensemble with pulsed magnetic resonance measurements in a 4. 4 T magnetic field.
High Energy Physics - Experiment Other Condensed Matter Instrumentation and Detectors
Ultra-High-Definition Image HDR Reconstruction via Collaborative Bilateral Learning
First, we propose a dual-path network to extract content and chromatic features at a reduced resolution of the low dynamic range (LDR) input.
FASG: Feature Aggregation Self-training GCN for Semi-supervised Node Classification
Recently, Graph Convolutioal Networks (GCNs) have achieved significant success in many graph-based learning tasks, especially for node classification, due to its excellent ability in representation learning.
Multi-Scale Separable Network for Ultra-High-Definition Video Deblurring
Although recent research has witnessed a significant progress on the video deblurring task, these methods struggle to reconcile inference efficiency and visual quality simultaneously, especially on ultra-high-definition (UHD) videos (e. g., 4K resolution).
AggMask: Exploring locally aggregated learning of mask representations for instance segmentation
Recently proposed one-stage instance segmentation models (\emph{e. g.}, SOLO) learn to directly predict location-specific object mask with fully-convolutional networks.
An Investigation of Potential Function Designs for Neural CRF
The neural linear-chain CRF model is one of the most widely-used approach to sequence labeling.
Exploring the limits of Concurrency in ML Training on Google TPUs
Recent results in language understanding using neural networks have required training hardware of unprecedentedscale, with thousands of chips cooperating on a single training run.
The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation
Our experiments and analyses demonstrate that neural machine translation performs poorly on commonsense reasoning of the three ambiguity types in terms of both reasoning accuracy ( 6 60. 1{\%}) and reasoning consistency (6 31{\%}).
EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising
In this paper, we propose the Edge enhancement based Densely connected Convolutional Neural Network (EDCNN).
Ranked #1 on
Denoising
on AAPM
Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes
Prior works always fail to deal with this problem in two aspects: (1) lacking utilizing information of the scenes; (2) lacking training data in the crowd and complex scenes.
Rapid Robust Principal Component Analysis: CUR Accelerated Inexact Low Rank Estimation
Robust principal component analysis (RPCA) is a widely used tool for dimension reduction.
Automated Concatenation of Embeddings for Structured Prediction
Pretrained contextualized embeddings are powerful word representations for structured prediction tasks.
Ranked #1 on
Chunking
on Penn Treebank
Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor
The objective function of knowledge distillation is typically the cross-entropy between the teacher and the student's output distributions.
AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network
The linear-chain Conditional Random Field (CRF) model is one of the most widely-used neural sequence labeling approaches.
Ranked #3 on
Chunking
on CoNLL 2003 (German)
More Embeddings, Better Sequence Labelers?
Recent work proposes a family of contextual embeddings that significantly improves the accuracy of sequence labelers over non-contextual embeddings.
Ranked #2 on
Chunking
on CoNLL 2003 (German)
Finding Action Tubes with a Sparse-to-Dense Framework
The task of spatial-temporal action detection has attracted increasing attention among researchers.
Ranked #3 on
Action Detection
on UCF Sports
(Video-mAP 0.2 metric)
High Accurate Time-of-Arrival Estimation with Fine-Grained Feature Generation for Internet-of-Things Applications
Conventional schemes often require extra reference signals or more complicated algorithms to improve the time-of-arrival (TOA) estimation accuracy.
Object-aware Multimodal Named Entity Recognition in Social Media Posts with Adversarial Learning
To better exploit visual and textual information in NER, we propose an adversarial gated bilinear attention neural network (AGBAN).
The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation
Specifically, we systematically investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset, and unveil that a major cause is the inaccurate classification of object proposals.
A Multi-Level Approach to Waste Object Segmentation
We address the problem of localizing waste objects from a color image and an optional depth image, which is a key perception component for robotic interaction with such objects.
Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax
Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored. In this work, we provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution.
Learning Combinatorial Solver for Graph Matching
Learning-based approaches to graph matching have been developed and explored for more than a decade, have grown rapidly in scope and popularity in recent years.
Making Robots Draw A Vivid Portrait In Two Minutes
The whole portrait drawing robotic system is named AiSketcher.
Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events
To this end, we present a new large-scale dataset with comprehensive annotations, named Human-in-Events or HiEve (Human-centric video analysis in complex Events), for the understanding of human motions, poses, and actions in a variety of realistic events, especially in crowd & complex events.
Automatic low-bit hybrid quantization of neural networks through meta learning
With the best searched quantization policy, we subsequently retrain or finetune to further improve the performance of the quantized target network.
Deep Learning based OTDOA Positioning for NB-IoT Communication Systems
Positioning is becoming a key component in many Internet of Things (IoT) applications.
Structure-Level Knowledge Distillation For Multilingual Sequence Labeling
Multilingual sequence labeling is a task of predicting label sequences using a single unified model for multiple languages.
CTM: Collaborative Temporal Modeling for Action Recognition
In order to learn powerful feature of videos, we propose a Collaborative Temporal Modeling (CTM) block (Figure 1) to learn temporal information for action recognition.
iqiyi Submission to ActivityNet Challenge 2019 Kinetics-700 challenge: Hierarchical Group-wise Attention
The standard non-local (NL) module is effective in aggregating frame-level features on the task of video classification but presents low parameters efficiency and high computational cost.
Learning a Layout Transfer Network for Context Aware Object Detection
We present a context aware object detection method based on a retrieve-and-transform scene layout model.
Merging External Bilingual Pairs into Neural Machine Translation
As neural machine translation (NMT) is not easily amenable to explicit correction of errors, incorporating pre-specified translations into NMT is widely regarded as a non-trivial challenge.
Classification Calibration for Long-tail Instance Segmentation
In this report, we investigate the performance drop phenomenon of state-of-the-art two-stage instance segmentation models when processing extreme long-tail training data based on the LVIS [5] dataset, and find a major cause is the inaccurate classification of object proposals.
Deformable Surface Tracking by Graph Matching
This paper addresses the problem of deformable surface tracking from monocular images.
Revisiting Knowledge Distillation via Label Smoothing Regularization
Without any extra computation cost, Tf-KD achieves up to 0. 65\% improvement on ImageNet over well-established baseline models, which is superior to label smoothing regularization.
Prototype Recalls for Continual Learning
Without tampering with the performance on initial tasks, our method learns novel concepts given a few training examples of each class in new tasks.
Scale MLPerf-0.6 models on Google TPU-v3 Pods
The recent submission of Google TPU-v3 Pods to the industry wide MLPerf v0. 6 training benchmark demonstrates the scalability of a suite of industry relevant ML models.
Trustable and Automated Machine Learning Running with Blockchain and Its Applications
Experiments show that this synthetic data generation is very effective in applications such as fraud detection in financial data.
Central Similarity Quantization for Efficient Image and Video Retrieval
In this work, we propose a new \emph{global} similarity metric, termed as \emph{central similarity}, with which the hash codes of similar data pairs are encouraged to approach a common center and those for dissimilar pairs to converge to different centers, to improve hash learning efficiency and retrieval accuracy.
Distilling Object Detectors with Fine-grained Feature Imitation
To address the challenge of distilling knowledge in detection model, we propose a fine-grained feature imitation method exploiting the cross-location discrepancy of feature response.
Variational Prototype Replays for Continual Learning
In each classification task, our method learns a set of variational prototypes with their means and variances, where embedding of the samples from the same class can be represented in a prototypical distribution and class-representative prototypes are separated apart.
A note on 'A fully parallel 3D thinning algorithm and its applications'
A 3D thinning algorithm erodes a 3D binary image layer by layer to extract the skeletons.
High-Performance Support Vector Machines and Its Applications
The support vector machines (SVM) algorithm is a popular classification technique in data mining and machine learning.
Fully Automatic Brain Tumor Segmentation using a Normalized Gaussian Bayesian Classifier and 3D Fluid Vector Flow
This paper presents an automatic brain tumor segmentation method based on a Normalized Gaussian Bayesian classification and a new 3D Fluid Vector Flow (FVF) algorithm.
Few-shot Adaptive Faster R-CNN
To address these challenges, we first introduce a pairing mechanism over source and target features to alleviate the issue of insufficient target domain samples.
A Unified Analytical Framework for Trustable Machine Learning and Automation Running with Blockchain
Second, it proposes a unified analytical framework for trustable machine learning by using blockchain technology.
Flash: Efficient Dynamic Routing for Offchain Networks
Mice payments are directly sent by looking up a routing table with a few precomputed paths to reduce probing overhead.
Networking and Internet Architecture
GM-PLL: Graph Matching based Partial Label Learning
Partial Label Learning (PLL) aims to learn from the data where each training example is associated with a set of candidate labels, among which only one is correct.
Image Classification at Supercomputer Scale
Deep learning is extremely computationally intensive, and hardware vendors have responded by building faster accelerators in large clusters.
