Search Results for author:
Found 239 papers, 95 papers with code
Diversity and Consistency: Exploring Visual Question-Answer Pair Generation
Moreover, this task can be used to improve visual question generation and visual question answering.
Data Augmentation for Few-Shot Knowledge Graph Completion from Hierarchical Perspective
To this end, we propose to solve the FKGC problem with the data augmentation technique.
Evolutionary Topology Search for Tensor Network Decomposition
Tensor network (TN) decomposition is a promising framework to represent extremely high-dimensional problems with few parameters.
MCS: An In-battle Commentary System for MOBA Games
This paper introduces a generative system for in-battle real-time commentary in mobile MOBA games.
Imaging for All-Day Wearable Smart Glasses
In recent years smart glasses technology has rapidly advanced, opening up entirely new areas for mobile computing.
Adaptive State-Space Mamba for Real-Time Sensor Data Anomaly Detection
State-space modeling has emerged as a powerful paradigm for sequence analysis in various tasks such as natural language processing, time-series forecasting, and signal processing.
Uncertainty-Aware Graph Self-Training with Expectation-Maximization Regularization
In this paper, we propose a novel \emph{uncertainty-aware graph self-training} approach for semi-supervised node classification.
Graph-Based Uncertainty-Aware Self-Training with Stochastic Node Labeling
Self-training has become a popular semi-supervised learning technique for leveraging unlabeled data.
Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning
Reasoning large language models are rapidly evolving across various domains.
Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models
Recently, the rapid development of AIGC has significantly boosted the diversities of fake media spread in the Internet, posing unprecedented threats to social security, politics, law, and etc.
Falcon: A Remote Sensing Vision-Language Foundation Model
This paper introduces a holistic vision-language foundation model tailored for remote sensing, named Falcon.
NeuGrasp: Generalizable Neural Surface Reconstruction with Background Priors for Material-Agnostic Object Grasp Detection
Robotic grasping in scenes with transparent and specular objects presents great challenges for methods relying on accurate depth information.
Lightweight yet Efficient: An External Attentive Graph Convolutional Network with Positional Prompts for Sequential Recommendation
To this end, we propose an External Attentive Graph convolutional network with Positional prompts for Sequential recommendation, namely EA-GPS.
Joint Modelling Histology and Molecular Markers for Cancer Classification
We introduce a novel digital pathology approach to jointly predict molecular markers and histology features and model their interactions for cancer classification.
Bridging Traffic State and Trajectory for Dynamic Road Network and Trajectory Representation Learning
Meanwhile, TRACK designs a traffic transformer encoder to capture the spatial-temporal dynamics of road segments from traffic state data.
Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
However, simultaneously addressing both concerns is challenging; secure aggregation facilitates poisoning attacks as most anomaly detection techniques require access to unencrypted local model updates, which are obscured by secure aggregation.
A Sustainable Circular Framework for Financing Infrastructure Climate Adaptation: Integrated Carbon Markets
Climate physical risks pose an increasing threat to urban infrastructure, necessitating urgent climate adaptation measures to protect lives and assets.
TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learning
TAPFed uses a proposed threshold functional encryption scheme and allows for a certain number of malicious aggregators while maintaining security and privacy.
ECG-guided individual identification via PPG
To this end, electrocardiogram (ECG) signals have been introduced as a novel modality to enhance the density of input information.
Multi-Agent Norm Perception and Induction in Distributed Healthcare
This paper presents a Multi-Agent Norm Perception and Induction Learning Model aimed at facilitating the integration of autonomous agent systems into distributed healthcare environments through dynamic interaction processes.
A Survey on Inference Optimization Techniques for Mixture of Experts Models
This survey provides both a structured overview of existing solutions and identifies key challenges and promising research directions in MoE inference optimization.
Lightweight yet Fine-grained: A Graph Capsule Convolutional Network with Subspace Alignment for Shared-account Sequential Recommendation
To this end, we propose a Lightweight Graph Capsule Convolutional Network with subspace alignment for shared-account sequential recommendation, named LightGC$^2$N.
Yi-Lightning Technical Report
This technical report presents Yi-Lightning, our latest flagship large language model (LLM).
ScaleKD: Strong Vision Transformers Could Be Excellent Teachers
The student backbones trained by our method transfer well on downstream MS-COCO and ADE20K datasets.
Ranked #1 on
Knowledge Distillation
on ImageNet
LProtector: An LLM-driven Vulnerability Detection System
This paper presents LProtector, an automated vulnerability detection system for C/C++ codebases driven by the large language model (LLM) GPT-4o and Retrieval-Augmented Generation (RAG).
HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference
We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference.
Prune and Repaint: Content-Aware Image Retargeting for any Ratio
By focusing on the content and structure of the foreground, our PruneRepaint approach adaptively avoids key content loss and deformation, while effectively mitigating artifacts with local repainting.
FeBiM: Efficient and Compact Bayesian Inference Engine Empowered with Ferroelectric In-Memory Computing
As the first FeFET-based in-memory Bayesian inference engine, FeBiM achieves an impressive storage density of 26. 32 Mb/mm$^{2}$ and a computing efficiency of 581. 40 TOPS/W in a representative Bayesian classification task.
Implicit neural representation for free-breathing MR fingerprinting (INR-MRF): co-registered 3D whole-liver water T1, water T2, proton density fat fraction, and R2* mapping
Purpose: To develop an MRI technique for free-breathing 3D whole-liver quantification of water T1, water T2, proton density fat fraction (PDFF), R2*.
Aria: An Open Multimodal Native Mixture-of-Experts Model
Information comes in diverse modalities.
Ranked #5 on
Video Question Answering
on TVBench
JoyType: A Robust Design for Multilingual Visual Text Creation
In this paper, we introduce a novel approach for multilingual visual text creation, named JoyType, designed to maintain the font style of text during the image generation process.
Multi-scale Temporal Fusion Transformer for Incomplete Vehicle Trajectory Prediction
Motion prediction plays an essential role in autonomous driving systems, enabling autonomous vehicles to achieve more accurate local-path planning and driving decisions based on predictions of the surrounding vehicles.
OVA-DETR: Open Vocabulary Aerial Object Detection Using Image-Text Alignment and Fusion
Then, we propose Bidirectional Vision-Language Fusion (Bi-VLF), which includes a dual-attention fusion encoder and a multi-level text-guided Fusion Decoder.
Spherical World-Locking for Audio-Visual Localization in Egocentric Videos
Egocentric videos provide comprehensive contexts for user and scene understanding, spanning multisensory perception to behavioral interaction.
AutoVCoder: A Systematic Framework for Automated Verilog Code Generation using LLMs
Recently, the use of large language models (LLMs) for software code generation, e. g., C/C++ and Python, has proven a great success.
Universal Multi-view Black-box Attack against Object Detectors via Layout Optimization
Specifically, we treat the placement of image stickers on the UV texture as a circle-based layout optimization problem, whose objective is to find the optimal circle layout filled with image stickers so that it can deceive the object detector under the multi-view scenario.
MSTF: Multiscale Transformer for Incomplete Trajectory Prediction
MSTF integrates a Multiscale Attention Head (MAH) and an Information Increment-based Pattern Adaptive (IIPA) module.
Crafting Customisable Characters with LLMs: Introducing SimsChat, a Persona-Driven Role-Playing Agent Framework
Large Language Models (LLMs) demonstrate remarkable ability to comprehend instructions and generate human-like text, enabling sophisticated agent simulation beyond basic behavior replication.
Knowledge-driven Subspace Fusion and Gradient Coordination for Multi-modal Learning
Multi-modal learning plays a crucial role in cancer diagnosis and prognosis.
KernelWarehouse: Rethinking the Design of Dynamic Convolution
Dynamic convolution learns a linear mixture of n static kernels weighted with their input-dependent attentions, demonstrating superior performance than normal convolution.
Unified Modeling Enhanced Multimodal Learning for Precision Neuro-Oncology
Multimodal learning, integrating histology images and genomics, promises to enhance precision oncology with comprehensive views at microscopic and molecular levels.
Genomics-guided Representation Learning for Pathologic Pan-cancer Tumor Microenvironment Subtype Prediction
The characterization of Tumor MicroEnvironment (TME) is challenging due to its complexity and heterogeneity.
Spatiotemporal Graph Neural Network Modelling Perfusion MRI
Perfusion MRI (pMRI) offers valuable insights into tumor vascularity and promises to predict tumor genotypes, thus benefiting prognosis for glioma patients, yet effective models tailored to 4D pMRI are still lacking.
Phy-Diff: Physics-guided Hourglass Diffusion Model for Diffusion MRI Synthesis
Our model introduces the physical principles of dMRI in the noise evolution in the diffusion process and introduce a query-based conditional mapping within the difussion model.
Domain Game: Disentangle Anatomical Feature for Single Domain Generalized Segmentation
Single domain generalization aims to address the challenge of out-of-distribution generalization problem with only one source domain available.
D-CoRP: Differentiable Connectivity Refinement for Functional Brain Networks
Existing models for brain networks typically primarily focus on brain regions or overlook the complexity of brain connectivities.
Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View
Compositional reasoning capabilities are usually considered as fundamental skills to characterize human perception.
Deep learning improved autofocus for motion artifact reduction and its application in quantitative susceptibility mapping
Purpose: To develop a pipeline for motion artifact correction in mGRE and quantitative susceptibility mapping (QSM).
Efficient Orchestrated AI Workflows Execution on Scale-out Spatial Architecture
Given the increasing complexity of AI applications, traditional spatial architectures frequently fall short.
What Radio Waves Tell Us about Sleep
The ability to assess sleep at home, capture sleep stages, and detect the occurrence of apnea (without on-body sensors) simply by analyzing the radio waves bouncing off people's bodies while they sleep is quite powerful.
Cross-modal Diffusion Modelling for Super-resolved Spatial Transcriptomics
However, current ST platforms suffer from low resolution, hindering in-depth understanding of spatial gene expression.
MAProtoNet: A Multi-scale Attentive Interpretable Prototypical Part Network for 3D Magnetic Resonance Imaging Brain Tumor Classification
Specifically, we introduce a concise multi-scale module to merge attentive features from quadruplet attention layers, and produces attribution maps.
Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs
Recently, this success has been extended to 3D AIGC, with state-of-the-art methods generating textured 3D models from single images or text.
Enhancing Adversarial Training with Prior Knowledge Distillation for Robust Image Compression
Adversarial training has been validated in image compression models as a common method to enhance model robustness.
Yi: Open Foundation Models by 01.AI
The Yi model family is based on 6B and 34B pretrained language models, then we extend them to chat models, 200K long context models, depth-upscaled models, and vision-language models.
Ranked #1 on
Chatbot
on AlpacaEval
(using extra training data)
Data-efficient Event Camera Pre-training via Disentangled Masked Modeling
Our pre-training overcomes the limitations of previous methods, which either sacrifice temporal information by converting event sequences into 2D images for utilizing pre-trained image models or directly employ paired image data for knowledge distillation to enhance the learning of event streams.
Aligning Knowledge Graph with Visual Perception for Object-goal Navigation
Object-goal navigation is a challenging task that requires guiding an agent to specific objects based on first-person visual observations.
NOAH: Learning Pairwise Object Category Attentions for Image Classification
We observe that the head structures of mainstream DNNs adopt a similar feature encoding pipeline, exploiting global feature dependencies while disregarding local ones.
tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs)
Tensor networks are efficient for extremely high-dimensional representation, but their model selection, known as tensor network structure search (TN-SS), is a challenging problem.
Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
The deep neural networks are known to be vulnerable to well-designed adversarial attacks.
SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge
Surgical tool segmentation and action recognition are fundamental building blocks in many computer-assisted intervention applications, ranging from surgical skills assessment to decision support systems.
A Polarization and Radiomics Feature Fusion Network for the Classification of Hepatocellular Carcinoma and Intrahepatic Cholangiocarcinoma
Our experimental results underscore the potential of this fusion network as a powerful tool for computer-aided diagnosis of HCC and ICC, showcasing the benefits and prospects of integrating polarization imaging techniques into the current image-intensive digital pathological diagnosis.
Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic Segmentation
In order to address this problem, we present Augmentation-free Dense Contrastive Knowledge Distillation (Af-DCD), a new contrastive distillation learning paradigm to train compact and accurate deep neural networks for semantic segmentation applications.
BCN: Batch Channel Normalization for Image Classification
Normalization techniques have been widely used in the field of deep learning due to their capability of enabling higher learning rates and are less careful in initialization.
Soulstyler: Using Large Language Model to Guide Image Style Transfer for Target Object
We introduce a large language model to parse the text and identify stylization goals and specific styles.
Feature Space Renormalization for Semi-supervised Learning
The common framework among recent approaches is to train the model on a large amount of unlabelled data with consistency regularization to constrain the model predictions to be invariant to input perturbation.
RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization
Multi-agent systems are characterized by environmental uncertainty, varying policies of agents, and partial observability, which result in significant risks.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Exploring Data Augmentations on Self-/Semi-/Fully- Supervised Pre-trained Models
Data augmentation has become a standard component of vision pre-trained models to capture the invariance between augmented views.
Asca: less audio data is more insightful
Audio recognition in specialized areas such as birdsong and submarine acoustics faces challenges in large-scale pre-training due to the limitations in available samples imposed by sampling environments and specificity requirements.
KernelWarehouse: Towards Parameter-Efficient Dynamic Convolution
Dynamic convolution learns a linear mixture of $n$ static kernels weighted with their sample-dependent attentions, demonstrating superior performance compared to normal convolution.
Analyzing and controlling diversity in quantum-behaved particle swarm optimization
Then, the correlations between the two types of diversities and the search performance are tested and analyzed on several benchmark functions, and the distance-to-average-point diversity is showed to have stronger association with the search performance during the evolving processes.
Long-range Meta-path Search on Large-scale Heterogeneous Graphs
Utilizing long-range dependency, a concept extensively studied in homogeneous graphs, remains underexplored in heterogeneous graphs, especially on large ones, posing two significant challenges: Reducing computational costs while maximizing effective information utilization in the presence of heterogeneity, and overcoming the over-smoothing issue in graph neural networks.
Ranked #3 on
Node Property Prediction
on ogbn-mag
RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World
In this paper, we propose a novel Reflected Light Attack (RFLA), featuring effective and stealthy in both the digital and physical world, which is implemented by placing the color transparent plastic sheet and a paper cut of a specific shape in front of the mirror to create different colored geometries on the target object.
Inverse Evolution Layers: Physics-informed Regularizers for Deep Neural Networks
Traditional image processing methods employing partial differential equations (PDEs) offer a multitude of meaningful regularizers, along with valuable theoretical foundations for a wide range of image-related tasks.
GroundNLQ @ Ego4D Natural Language Queries Challenge 2023
Motivated by this, we leverage a two-stage pre-training strategy to train egocentric feature extractors and the grounding model on video narrations, and further fine-tune the model on annotated data.
Optimized Vectorizing of Building Structures with Switch: High-Efficiency Convolutional Channel-Switch Hybridization Strategy
The building planar graph reconstruction, a. k. a.
PGformer: Proxy-Bridged Game Transformer for Multi-Person Highly Interactive Extreme Motion Prediction
Multi-person motion prediction is a challenging task, especially for real-world scenarios of highly interacted persons.
Adaptive Contextual Biasing for Transducer Based Streaming Speech Recognition
By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words.
HetReGAT-FC: heterogeneous residual graph attention network via feature completion
To this end, we propose a Heterogeneous Residual Graph Attention Network via Feature Completion (HetReGAT-FC).
A Novel Driver Distraction Behavior Detection Method Based on Self-supervised Learning with Masked Image Modeling
In order to solve these problems, this paper proposes a new self-supervised learning method based on masked image modeling for driver distraction behavior detection.
SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective
To address this issue, we propose a novel TN paradigm, named SVD-inspired TN decomposition (SVDinsTN), which allows us to efficiently solve the TN-SS problem from a regularized modeling perspective, eliminating the repeated structure evaluations.
NORM: Knowledge Distillation via N-to-One Representation Matching
By sequentially splitting the expanded student representation into N non-overlapping feature segments having the same number of feature channels as the teacher's, they can be readily forced to approximate the intact teacher representation simultaneously, formulating a novel many-to-one representation matching mechanism conditioned on a single teacher-student layer pair.
Impact of Light and Shadow on Robustness of Deep Neural Networks
Deep neural networks (DNNs) have made remarkable strides in various computer vision tasks, including image classification, segmentation, and object detection.
Physics-based network fine-tuning for robust quantitative susceptibility mapping from high-pass filtered phase
Purpose: To improve the generalization ability of convolutional neural network (CNN) based prediction of quantitative susceptibility mapping (QSM) from high-pass filtered phase (HPFP) image.
Alternating Local Enumeration (TnALE): Solving Tensor Network Structure Search with Fewer Evaluations
Tensor network (TN) is a powerful framework in machine learning, but selecting a good TN model, known as TN structure search (TN-SS), is a challenging and computationally intensive task.
Meta-multigraph Search: Rethinking Meta-structure on Heterogeneous Information Networks
Meta-structures are widely used to define which subset of neighbors to aggregate information in heterogeneous information networks (HINs).
Learning Neural Duplex Radiance Fields for Real-Time View Synthesis
Neural radiance fields (NeRFs) enable novel view synthesis with unprecedented visual quality.
The Second Monocular Depth Estimation Challenge
This paper discusses the results for the second edition of the Monocular Depth Estimation Challenge (MDEC).
Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense
While having achieved great success in rich real-life applications, deep neural network (DNN) models have long been criticized for their vulnerability to adversarial attacks.
mcLARO: Multi-Contrast Learned Acquisition and Reconstruction Optimization for simultaneous quantitative multi-parametric mapping
Results: The retrospective ablation study showed improved image sharpness of mcLARO compared to the baseline network without multi-contrast sampling pattern optimization or image feature fusion, and negligible bias and narrow 95% limits of agreement on regional T1, T2, T2* and QSM values were obtained by the under-sampled reconstructions compared to the fully sampled reconstruction.
Multi-task Learning of Histology and Molecular Markers for Classifying Diffuse Glioma
This paper presents a first attempt to jointly predict molecular markers and histology features and model their interactions for classifying diffuse glioma bases on whole slide images.
CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis
Diffusion model has emerged as an effective technique for image synthesis by modelling complex and variable data distributions.
DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-Resolution
Moreover, DisC-Diff leverages a disentangled multi-stream network to fully exploit complementary information from multi-contrast MRI, improving model interpretation under multiple conditions of multi-contrast inputs.
Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks
Our analysis indicates that the transformed low-rank parameterization can promisingly enhance robust generalization for t-NNs.
Practice of the conformer enhanced AUDIO-VISUAL HUBERT on Mandarin and English
Considering the bimodal nature of human speech perception, lips, and teeth movement has a pivotal role in automatic speech recognition.
GMConv: Modulating Effective Receptive Fields for Convolutional Kernels
Inspired by the property that ERFs typically exhibit a Gaussian distribution, we propose a Gaussian Mask convolutional kernel (GMConv) in this work.
Improved Differential-neural Cryptanalysis for Round-reduced Simeck32/64
Inspired by this framework, we develop the Inception neural network that is compatible with the round function of Simeck to improve the accuracy of the neural distinguishers, thus improving the accuracy of (9-12)-round neural distinguishers for Simeck32/64.
Spatially Covariant Lesion Segmentation
Compared to natural images, medical images usually show stronger visual patterns and therefore this adds flexibility and elasticity to resource-limited clinical applications by injecting proper priors into neural networks.
Centralized Cooperative Exploration Policy for Continuous Control Tasks
To explicitly encourage exploration in continuous control tasks, we propose CCEP (Centralized Cooperative Exploration Policy), which utilizes underestimation and overestimation of value functions to maintain the capacity of exploration.
Towards Understanding the Generalization of Deepfake Detectors from a Game-Theoretical View
Deepfake detectors encode multi-order interactions among visual concepts, in which the low-order interactions usually have substantially negative contributions to deepfake detection.
FDViT: Improve the Hierarchical Architecture of Vision Transformer
In this paper, we propose FDViT to improve the hierarchical architecture of the vision transformer by using a flexible downsampling layer that is not limited to integer stride to smoothly reduce the sizes of the middle feature maps.
Accelerating Self-Imitation Learning from Demonstrations via Policy Constraints and Q-Ensemble
Both imitation learning (IL) and learning from demonstrations (LfD) improve the training process by using expert demonstrations, but imperfect expert demonstrations can mislead policy improvement.
Differentiable Meta Multigraph Search with Partial Message Propagation on Heterogeneous Information Networks
To address these issues, we propose a novel method called Partial Message Meta Multigraph search (PMMM) to automatically optimize the neural architecture design on HINs.
Hypergraph Transformer for Skeleton-based Action Recognition
Skeleton-based action recognition aims to recognize human actions given human joint coordinates with skeletal interconnections.
Ranked #12 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics
TRL aims to convert complicated raw trajectories into low-dimensional representation vectors, which can be applied to various downstream tasks, such as trajectory classification, clustering, and similarity computation.
LARO: Learned Acquisition and Reconstruction Optimization to accelerate Quantitative Susceptibility Mapping
In this paper, we present our new framework, called Learned Acquisition and Reconstruction Optimization (LARO), which aims to accelerate the multi-echo gradient echo (mGRE) pulse sequence for QSM.
Instance Segmentation for Chinese Character Stroke Extraction, Datasets and Benchmarks
Moreover, there are no standardized benchmarks to provide a fair comparison between different stroke extraction methods, which, we believe, is a major impediment to the development of Chinese character stroke understanding and related tasks.
Hierarchical Multi-Interest Co-Network For Coarse-Grained Ranking
This paper proposes a Hierarchical Multi-Interest Co-Network (HCN) to capture users' diverse interests in the coarse-grained ranking stage.
Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checking
Chinese Spell Checking (CSC) aims to detect and correct Chinese spelling errors.
Rethinking Prototypical Contrastive Learning through Alignment, Uniformity and Correlation
Particularly, in the classification down-stream tasks with linear probes, our proposed method outperforms the state-of-the-art instance-wise and prototypical contrastive learning methods on the ImageNet-100 dataset by 2. 96% and the ImageNet-1K dataset by 2. 46% under the same settings of batch size and epochs.
DRKF: Distilled Rotated Kernel Fusion for Efficient Rotation Invariant Descriptors in Local Feature Matching
The performance of local feature descriptors degrades in the presence of large rotation variations.
Omni-Dimensional Dynamic Convolution
Learning a single static convolutional kernel in each convolutional layer is the common training paradigm of modern Convolutional Neural Networks (CNNs).
DBT-DMAE: An Effective Multivariate Time Series Pre-Train Model under Missing Data
Multivariate time series(MTS) is a universal data type related to many practical applications.
MAFormer: A Transformer Network with Multi-scale Attention Fusion for Visual Recognition
We develop a simple but effective module to explore the full potential of transformers for visual representation by learning fine-grained and coarse-grained features at a token level and dynamically fusing them.
AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applications
To automatically correct handwritten assignments, the traditional approach is to use an OCR model to recognize characters and compare them to answers.
Siamese Prototypical Contrastive Learning
One of the drawbacks of CSL is that the loss term requires a large number of negative samples to provide better mutual information bound ideally.
Generative Action Description Prompts for Skeleton-based Action Recognition
More specifically, we employ a pre-trained large-scale language model as the knowledge engine to automatically generate text descriptions for body parts movements of actions, and propose a multi-modal training scheme by utilizing the text encoder to generate feature vectors for different body parts and supervise the skeleton encoder for action representation learning.
Ranked #7 on
Skeleton Based Action Recognition
on N-UCLA
Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition
For 3D video-based tasks such as action recognition, however, directly applying spatiotemporal transformers on video data will bring heavy computation and memory burdens due to the largely increased number of patches and the quadratic complexity of self-attention computation.
Ranked #10 on
Action Recognition
on Diving-48
Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippet
In this paper, we propose Snipper, a unified framework to perform multi-person 3D pose estimation, tracking, and motion forecasting simultaneously in a single stage.
SALO: An Efficient Spatial Accelerator Enabling Hybrid Sparse Attention Mechanisms for Long Sequences
However, the quadratic complexity of self-attention w. r. t the sequence length incurs heavy computational and memory burdens, especially for tasks with long sequences.
SP-ViT: Learning 2D Spatial Priors for Vision Transformers
Unlike convolutional inductive biases, which are forced to focus exclusively on hard-coded local regions, our proposed SPs are learned by the model itself and take a variety of spatial relations into account.
Ranked #155 on
Image Classification
on ImageNet
Permutation Search of Tensor Network Structures via Local Sampling
Recent works put much effort into tensor network structure search (TN-SS), aiming to select suitable tensor network (TN) structures, involving the TN-ranks, formats, and so on, for the decomposition or learning tasks.
Gleo-Det: Deep Convolution Feature-Guided Detector with Local Entropy Optimization for Salient Points
3) With the guidance of convolution features, we define the cost function from both positive and negative sides.
Adaptive Channel Allocation for Robust Differentiable Architecture Search
Our method, dubbed Adaptive Channel Allocation (ACA) strategy, is a general-purpose approach for differentiable architecture search, which universally works in DARTS variants without introducing human priors, indicators, or hyper-parameters.
Multi-modal learning for predicting the genotype of glioma
In this study, we propose a multi-modal learning framework using three separate encoders to extract features of focal tumor image, tumor geometrics and global brain networks.
Type-Driven Multi-Turn Corrections for Grammatical Error Correction
First, they simply mix additionally-constructed training instances and original ones to train models, which fails to help models be explicitly aware of the procedure of gradual corrections.
Fast density peaks clustering algorithm in polar coordinate system
Density peaks clustering (DPC) algorithm provides an efficient method to quickly find cluster centers with decision graphs.
Predicting conversion of mild cognitive impairment to Alzheimer's disease
In this study, we develop a self-supervised contrastive learning approach to generate structural brain networks from routine anatomical MRI under the guidance of diffusion MRI.
Mutual Contrastive Low-rank Learning to Disentangle Whole Slide Image Representations for Glioma Grading
In this proposed scheme, we design a normalized modality contrastive loss (NMC-loss), which could promote to disentangle multi-modality complementary representation of FFPE and frozen sections from the same patient.
$A^{3}D$: A Platform of Searching for Robust Neural Architectures and Efficient Adversarial Attacks
To alleviate these problems, in this paper, we first propose a novel platform called auto adversarial attack and defense ($A^{3}D$), which can help search for robust neural network architectures and efficient adversarial attacks.
Transformations in Learned Image Compression from a Modulation Perspective
In the view of TSM, the existing transformation methods are mathematically reduced to a linear modulation.
The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking
However, there exists a gap between the learned knowledge of PLMs and the goal of CSC task.
Exploring Structural Sparsity in Neural Image Compression
Neural image compression have reached or out-performed traditional methods (such as JPEG, BPG, WebP).
Collaborative learning of images and geometrics for predicting isocitrate dehydrogenase status of glioma
Further, the collaborative learning model achieves better performance than either the CNN or the GNN alone.
Improved (Related-key) Differential-based Neural Distinguishers for SIMON and SIMECK Block Ciphers
In CRYPTO 2019, Gohr made a pioneering attempt and successfully applied deep learning to the differential cryptanalysis against NSA block cipher SPECK32/64, achieving higher accuracy than the pure differential distinguishers.
Context-Aware Compilation of DNN Training Pipelines across Edge and Cloud
Experimental results show that our system not only adapts well to, but also draws on the varying contexts, delivering a practical and efficient solution to edge-cloud model training.
Ranked #2 on
Recommendation Systems
on MovieLens 1M
(Precision metric)
Universal Efficient Variable-rate Neural Image Compression
Recently, Learning-based image compression has reached comparable performance with traditional image codecs(such as JPEG, BPG, WebP).
Towards Robust Knowledge Graph Embedding via Multi-task Reinforcement Learning
This will lead to low-quality and unreliable representations of KGs.
LibCity: An Open Library for Traffic Prediction
This paper presents LibCity, a unified, comprehensive, and extensible library for traffic prediction, which provides researchers with a credible experimental tool and a convenient development framework.
Unrestricted Adversarial Attacks on ImageNet Competition
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input.
Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problems
Math Word Problem (MWP) solving needs to discover the quantitative relationships over natural language narratives.
Adversarial Attacks on ML Defense Models Competition
Due to the vulnerability of deep neural networks (DNNs) to adversarial examples, a large number of defense techniques have been proposed to alleviate this problem in recent years.
Ego4D: Around the World in 3,000 Hours of Egocentric Video
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite.
Predicting isocitrate dehydrogenase mutation status in glioma using structural brain networks and graph neural networks
Here we propose a method to predict IDH mutation using GNN, based on the structural brain network of patients.
L3C-Stereo: Lossless Compression for Stereo Images
To tackle this, we propose L3C-Stereo, a multi-scale lossless compression model consisting of two main modules: the warping module and the probability estimation module.
Adaptive unsupervised learning with enhanced feature representation for intra-tumor partitioning and survival prediction for glioblastoma
In this paper, we propose an adaptive unsupervised learning approach for efficient MRI intra-tumor partitioning and glioblastoma survival prediction.
Semi-supervised classification of radiology images with NoTeacher: A Teacher that is not Mean
Specifically, we describe adaptations for scenarios with 2D and 3D inputs, uni and multi-label classification, and class distribution mismatch between labeled and unlabeled portions of the training data.
End-to-End User Behavior Retrieval in Click-Through RatePrediction Model
Recently, researchers have found that the performance of CTR model can be improved greatly by taking user behavior sequence into consideration, especially long-term user behavior sequence.
Integrating Large Circular Kernels into CNNs through Neural Architecture Search
We first propose a simple yet efficient implementation of the convolution using circular kernels, and empirically show the significant advantages of large circular kernels over the counterpart square kernels.
Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacy
In this work, we study a crucial question which has been vastly overlooked by existing works: what are the optimal numbers of queries and replies in FL with DP so that the final model accuracy is maximized.
A Hybrid mmWave and Camera System for Long-Range Depth Imaging
mmWave radars offer excellent depth resolution even at very long ranges owing to their high bandwidth.
Self-Supervised Nonlinear Transform-Based Tensor Nuclear Norm for Multi-Dimensional Image Recovery
Recently, transform-based tensor nuclear norm minimization methods are considered to capture low-rank tensor structures to recover third-order tensors in multi-dimensional image processing applications.
Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking
Chinese Spell Checking (CSC) aims to detect and correct erroneous characters for user-generated text in the Chinese language.
Ranked #2 on
Chinese Spell Checking
on SIGHAN 2015
Graph-Constrained Structure Search for Tensor Network Representation
Recent works paid effort on the structure search issue for tensor network (TN) representation, of which the aim is to select the optimal network for TN contraction to fit a tensor.
Egocentric Activity Recognition and Localization on a 3D Map
Given a video captured from a first person perspective and the environment context of where the video is recorded, can we recognize what the person is doing and identify where the action occurs in the 3D space?
Motion Artifact Reduction in Quantitative Susceptibility Mapping using Deep Neural Network
An approach to reduce motion artifacts in Quantitative Susceptibility Mapping using deep learning is proposed.
Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness
Inpainting arbitrary missing regions is challenging because learning valid features for various masked regions is nontrivial.
Ranked #5 on
Image Inpainting
on CelebA-HQ
Temporal Feature Fusion with Sampling Pattern Optimization for Multi-echo Gradient Echo Acquisition and Image Reconstruction
Quantitative imaging in MRI usually involves acquisition and reconstruction of a series of images at multi-echo time points, which possibly requires more scan time and specific reconstruction technique compared to conventional qualitative imaging.
BrainNetGAN: Data augmentation of brain connectivity using generative adversarial network for dementia classification
The proposed BrainNetGAN is a generative adversarial network variant to augment the brain structural connectivity matrices for binary dementia classification tasks.
NeRD: Neural Representation of Distribution for Medical Image Segmentation
We introduce Neural Representation of Distribution (NeRD) technique, a module for convolutional neural networks (CNNs) that can estimate the feature distribution by optimizing an underlying function mapping image coordinates to the feature distribution.
On the Memory Mechanism of Tensor-Power Recurrent Models
Tensor-power (TP) recurrent model is a family of non-linear dynamical systems, of which the recurrence relation consists of a p-fold (a. k. a., degree-p) tensor product.
Blockchain-based Transparency Framework for Privacy Preserving Third-party Services
We also formally show the security guarantee provided by TAB, and analyze the privacy guarantee and trustworthiness it provides.
Cryptography and Security Networking and Internet Architecture
Measuring Decentralization in Bitcoin and Ethereum using Multiple Metrics and Granularities
Decentralization has been widely acknowledged as a core virtue of blockchains.
Cryptography and Security Databases
Expectation-Maximization Regularized Deep Learning for Weakly Supervised Tumor Segmentation for Glioblastoma
EMReDL showed to effectively segment the infiltrated tumor from the partially labelled region of potential infiltration.
On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times
Then, we theoretically derive: 1) the conditions for the DP based FedAvg to converge as the number of global iterations (GI) approaches infinity; 2) the method to set the number of local iterations (LI) to minimize the negative influence of DP noises.
Protecting Big Data Privacy Using Randomized Tensor Network Decomposition and Dispersed Tensor Computation
The distributed tensor representations are dispersed on multiple clouds / fogs or servers / devices with metadata privacy, this provides both distributed trust and management to seamlessly secure big data storage, communication, sharing, and computation.
Adversarial Attack on Deep Cross-Modal Hamming Retrieval
Specifically, given a target model, we first construct its substitute model to exploit cross-modal correlations within hamming space, with which we create adversarial examples by limitedly querying from a target model.
Improving BERT with Syntax-aware Local Attention
Pre-trained Transformer-based neural language models, such as BERT, have achieved remarkable results on varieties of NLP tasks.
NN-EMD: Efficiently Training Neural Networks using Encrypted Multi-Sourced Datasets
We propose a novel framework, NN-EMD, to train DNN over multiple encrypted datasets collected from multiple sources.
Bayesian optimization assisted unsupervised learning for efficient intra-tumor partitioning in MRI and survival prediction for glioblastoma patients
Although successful in tumor sub-region segmentation and survival prediction, radiomics based on machine learning algorithms, is challenged by its robustness, due to the vague intermediate process and track changes.
How Far Does BERT Look At: Distance-based Clustering and Analysis of BERT's Attention
Recent research on the multi-head attention mechanism, especially that in pre-trained models such as BERT, has shown us heuristics and clues in analyzing various aspects of the mechanism.
Channel Pruning via Multi-Criteria based on Weight Dependency
However, these methods ignore a small part of weights in the next layer which disappears as the feature map is removed.
An Empirical-cum-Statistical Approach to Power-Performance Characterization of Concurrent GPU Kernels
Growing deployment of power and energy efficient throughput accelerators (GPU) in data centers demands enhancement of power-performance co-optimization capabilities of GPUs.
Distributed, Parallel, and Cluster Computing Hardware Architecture Graphics
How Far Does BERT Look At:Distance-based Clustering and Analysis of BERT$'$s Attention
Recent research on the multi-head attention mechanism, especially that in pre-trained models such as BERT, has shown us heuristics and clues in analyzing various aspects of the mechanism.
Non-local Meets Global: An Iterative Paradigm for Hyperspectral Image Restoration
Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) restoration, which includes the tasks of denoising, compressed HSI reconstruction and inpainting.
Architectural Implications of Graph Neural Networks
Graph neural networks (GNN) represent an emerging line of deep learning models that operate on graph structures.
Joint Generative Learning and Super-Resolution For Real-World Camera-Screen Degradation
Firstly, the downsampling degradation GAN(DD-GAN) is trained to model the degradation and produces more various of LR images, which is validated to be efficient for data augmentation.
Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition
The key lies in the design of the graph structure, which encodes skeleton topology information.
Topology-Change-Aware Volumetric Fusion for Dynamic Scene Reconstruction
In the classic volumetric fusion-based framework, a mesh is usually extracted from the TSDF volume as the canonical surface representation to help estimating deformation field.
PFGDF: Pruning Filter via Gaussian Distribution Feature for Deep Neural Networks Acceleration
Deep learning has achieved impressive results in many areas, but the deployment of edge intelligent devices is still very slow.
NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results
For track 2, some existing methods are evaluated, showing promising solutions to the weakly-supervised video quality mapping problem.
NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.
Balancing Efficiency and Flexibility for DNN Acceleration via Temporal GPU-Systolic Array Integration
We propose Simultaneous Multi-mode Architecture (SMA), a novel architecture design and execution model that offers general-purpose programmability on DNN accelerators in order to accelerate end-to-end applications.
H-OWAN: Multi-distorted Image Restoration with Tensor 1x1 Convolution
It is a challenging task to restore images from their variants with combined distortions.
Hyperspectral Super-Resolution via Coupled Tensor Ring Factorization
In this paper, we propose a new model, named coupled tensor ring factorization (CTRF), for HSR.
Cross-Modal Learning with Adversarial Samples
Extensive experiments on two cross-modal benchmark datasets show that the adversarial examples produced by our CMLA are efficient in fooling a target deep cross-modal hashing network.
Single Image Reflection Removal through Cascaded Refinement
IBCLN is a cascaded network that iteratively refines the estimates of transmission and reflection layers in a manner that they can boost the prediction quality to each other, and information across steps of the cascade is transferred using an LSTM.
Ranked #3 on
Reflection Removal
on SIR^2(Postcard)
TruNet: Short Videos Generation from Long Videos via Story-Preserving Truncation
In this work, we introduce a new problem, named as {\em story-preserving long video truncation}, that requires an algorithm to automatically truncate a long-duration video into multiple short and attractive sub-videos with each one containing an unbroken story.
Hierarchical hidden community detection for protein complex prediction
Results: We propose a method called HirHide (Hierarchical Hidden Community Detection), which can be combined with traditional community detection methods to enable them to discover hierarchical hidden communities.
Molecular Networks
Image Inpainting with Learnable Bidirectional Attention Maps
Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with color discrepancy and blurriness.
Ranked #2 on
Image Inpainting
on Paris StreetView
Deep Concept-wise Temporal Convolutional Networks for Action Localization
In this paper, we empirically find that stacking more conventional temporal convolution layers actually deteriorates action classification performance, possibly ascribing to that all channels of 1D feature map, which generally are highly abstract and can be regarded as latent concepts, are excessively recombined in temporal convolution.
Gated Convolutional Networks with Hybrid Connectivity for Image Classification
We propose a simple yet effective method to reduce the redundancy of DenseNet by substantially decreasing the number of stacked modules by replacing the original bottleneck by our SMG module, which is augmented by local residual.
Ranked #66 on
Image Classification
on CIFAR-10
User independent Emotion Recognition with Residual Signal-Image Network
To the best of author's knowledge, our method is the first attempt to classify large scale subject-independent emotion with 7962 pieces of EDA signals from 457 subjects.
Best Practices for Learning Domain-Specific Cross-Lingual Embeddings
Cross-lingual embeddings aim to represent words in multiple languages in a shared vector space by capturing semantic similarities across languages.
Multi-Objective Pruning for CNNs Using Genetic Algorithm
In this work, we propose a heuristic genetic algorithm (GA) for pruning convolutional neural networks (CNNs) according to the multi-objective trade-off among error, computation and sparsity.
Guaranteed Matrix Completion Under Multiple Linear Transformations
Low-rank matrix completion (LRMC) is a classical model in both computer vision (CV) and machine learning, and has been successfully applied to various real applications.
Collaborative Spatiotemporal Feature Learning for Video Action Recognition
By sharing the convolution kernels of different views, spatial and temporal features are collaboratively learned and thus benefit from each other.
Ranked #18 on
Action Classification
on MiT
Adapting Image Super-Resolution State-of-the-arts and Learning Multi-model Ensemble for Video Super-Resolution
Recently, image super-resolution has been widely studied and achieved significant progress by leveraging the power of deep convolutional neural networks.
POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion
In particular, there exist two requirements for fashion outfit recommendation: the Compatibility of the generated fashion outfits, and the Personalization in the recommendation process.
