Search Results for author:
Found 196 papers, 67 papers with code
Panoptic Studio: A Massively Multiview System for Social Motion Capture
We present an approach to capture the 3D structure and motion of a group of people engaged in a social interaction.
End-to-End Comparative Attention Networks for Person Re-identification
The CAN model is able to learn which parts of images are relevant for discerning persons and automatically integrates information from different parts to determine whether a pair of images belongs to the same person.
Panoptic Studio: A Massively Multiview System for Social Interaction Capture
The core challenges in capturing social interactions are: (1) occlusion is functional and frequent; (2) subtle motion needs to be measured over a space large enough to host a social group; (3) human appearance and configuration variation is immense; and (4) attaching markers to the body may prime the nature of interactions.
Recurrent Image Captioner: Describing Images with Spatial-Invariant Transformation and Attention Filtering
Along with the prosperity of recurrent neural network in modelling sequential data and the power of attention mechanism in automatically identify salient information, image captioning, a. k. a., image description, has been remarkably advanced in recent years.
Video-based Person Re-identification with Accumulative Motion Context
Video based person re-identification plays a central role in realistic security and video surveillance.
Learning Policies for Markov Decision Processes from Data
We assume that the policy belongs to a class of parameterized policies which are defined using features associated with the state-action pairs.
Multi-View Image Generation from a Single-View
This paper addresses a challenging problem -- how to generate multi-view cloth images from only a single view input.
Stochastic Sequential Neural Networks with Structured Inference
Inheriting these advantages of stochastic neural sequential models, we propose a structured and stochastic sequential neural network, which models both the long-term dependencies via recurrent neural networks and the uncertainty in the segmentation and labels via discrete random variables.
Video-based Person Re-identification with Accumulative Motion Context
Video based person re-identification plays a central role in realistic security and video surveillance.
Neural Person Search Machines
We investigate the problem of person search in the wild in this work.
Ranked #4 on
Person Re-Identification
on CUHK-SYSU
ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching.
Triangle Generative Adversarial Networks
The generators are designed to learn the two-way conditional distributions between the two domains, while the discriminators implicitly define a ternary discriminative function, which is trained to distinguish real data pairs and two kinds of fake data pairs.
Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions
This architecture contains an autoencoder and a special prototype layer, where each unit of that layer stores a weight vector that resembles an encoded training input.
Action-depedent Control Variates for Policy Optimization via Stein's Identity
Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems.
N-gram Model for Chinese Grammatical Error Diagnosis
Detection and correction of Chinese grammatical errors have been two of major challenges for Chinese automatic grammatical error diagnosis. This paper presents an N-gram model for automatic detection and correction of Chinese grammatical errors in NLPTEA 2017 task.
On Connecting Stochastic Gradient MCMC and Differential Privacy
Significant success has been realized recently on applying machine learning to real-world applications.
Large-scale Bisample Learning on ID Versus Spot Face Recognition
In this paper, we propose a deep learning based large-scale bisample learning (LBL) method for IvS face recognition.
Pattern-revising Enhanced Simple Question Answering over Knowledge Bases
Question Answering over Knowledge Bases (KB-QA), which automatically answer natural language questions based on the facts contained by a knowledge base, is one of the most important natural language processing (NLP) tasks.
Shrinkage-based Bias-Variance Trade-off for Deep Reinforcement Learning
Deep reinforcement learning has achieved remarkable successes in solving various challenging artificial intelligence tasks.
Variational Inference with Tail-adaptive f-Divergence
Variational inference with {\alpha}-divergences has been widely used in modern probabilistic machine learning.
Sequence-based Person Attribute Recognition with Joint CTC-Attention Model
Attribute recognition has become crucial because of its wide applications in many computer vision tasks, such as person re-identification.
Competitive Experience Replay
We propose a novel method called competitive experience replay, which efficiently supplements a sparse reward by placing learning in the context of an exploration competition between a pair of agents.
Learning to Search Efficient DenseNet with Layer-wise Pruning
Deep neural networks have achieved outstanding performance in many real-world applications with the expense of huge computational resources.
Predicting Solar Flares Using a Long Short-Term Memory Network
The essence of our approach is to model data samples in an AR as time series and use LSTMs to capture temporal information of the data samples.
AdaptiveFace: Adaptive Margin and Sampling for Face Recognition
Training large-scale unbalanced data is the central topic in face recognition.
Dense Scale Network for Crowd Counting
The key component of our network is the dense dilated convolution block, in which each dilation layer is densely connected with the others to preserve information from continuously varied scales.
Guided Adaptive Credit Assignment for Sample Efficient Policy Optimization
In this work, we propose a guided adaptive credit assignment method to do effectively credit assignment for policy gradient methods.
Triply Robust Off-Policy Evaluation
Ours is a general approach that can be used to augment any existing OPE method that utilizes the direct method.
Semi-Supervised Hierarchical Recurrent Graph Neural Network for City-Wide Parking Availability Prediction
However, it is a non-trivial task for predicting citywide parking availability because of three major challenges: 1) the non-Euclidean spatial autocorrelation among parking lots, 2) the dynamic temporal autocorrelation inside of and between parking lots, and 3) the scarcity of information about real-time parking availability obtained from real-time sensors (e. g., camera, ultrasonic sensor, and GPS).
Towards Omni-Supervised Face Alignment for Large Scale Unlabeled Videos
In this paper, we propose a spatial-temporal relational reasoning networks (STRRN) approach to investigate the problem of omni-supervised face alignment in videos.
A Comprehensive Study and Comparison of Core Technologies for MPEG 3D Point Cloud Compression
Point cloud based 3D visual representation is becoming popular due to its ability to exhibit the real world in a more comprehensive and immersive way.
Deep Learning for 3D Point Clouds: A Survey
To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds.
Reinforcement Learning Tracking Control for Robotic Manipulator With Kernel-Based Dynamic Model
In this algorithm, a reward function is defined according to the features of tracking control in order to speed up the learning process, and then an RL tracking controller with a kernel-based transition dynamic model is proposed.
Learning functions varying along a central subspace
The estimation error of this variance quantity is also given in this paper.
Curvature Regularized Surface Reconstruction from Point Cloud
We propose a variational functional and fast algorithms to reconstruct implicit surface from point cloud data with a curvature constraint.
Predicting Coronal Mass Ejections Using SDO/HMI Vector Magnetic Data Products and Recurrent Neural Networks
We present two recurrent neural networks (RNNs), one based on gated recurrent units and the other based on long short-term memory, for predicting whether an active region (AR) that produces an M- or X-class flare will also produce a coronal mass ejection (CME).
PuzzleNet: Scene Text Detection by Segment Context Graph Learning
Recently, a series of decomposition-based scene text detection methods has achieved impressive progress by decomposing challenging text regions into pieces and linking them in a bottom-up manner.
Inferring Vector Magnetic Fields from Stokes Profiles of GST/NIRIS Using a Convolutional Neural Network
By learning the latent patterns in the training data prepared by the physics-based ME tool, the proposed CNN method is able to infer vector magnetic fields from the Stokes profiles of GST/NIRIS.
Solar and Stellar Astrophysics
SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis
In particular, the prediction of aspect-sentiment pairs is converted into multi-label classification, aiming to capture the dependency between words in a pair.
Ranked #14 on
Stock Market Prediction
on Astock
Global context reasoning for semantic segmentation of 3d point clouds
In this paper, we propose a Point Global Context Reasoning (PointGCR) module to capture global contextual information along the channel dimension.
Polestar: An Intelligent, Efficient and National-Wide Public Transportation Routing Engine
Then, we introduce a general route search algorithm coupled with an efficient station binding method for efficient route candidate generation.
Hybrid Discriminative-Generative Training via Contrastive Learning
In this paper we show that through the perspective of hybrid discriminative-generative training of energy-based models we can make a direct connection between contrastive learning and supervised learning.
Semantic Context Encoding for Accurate 3D Point Cloud Segmentation
In this paper, we propose a simple yet effective Point Context Encoding (PointCE) module to capture semantic contexts of a point cloud and adaptively highlight intermediate feature maps.
A Color Elastica Model for Vector-Valued Image Regularization
Here, we introduce an addition to the Polyakov action for color images that minimizes the color manifold curvature.
Identifying and Tracking Solar Magnetic Flux Elements with Deep Learning
Deep learning has drawn a lot of interest in recent years due to its effectiveness in processing big and complex observational data gathered from diverse instruments.
AutoFS: Automated Feature Selection via Diversity-aware Interactive Reinforcement Learning
Motivated by such a computational dilemma, this study is to develop a novel feature space navigation method.
DARWIN: A Highly Flexible Platform for Imaging Research in Radiology
Our platform is consists of a radiomics module and a deep learning module.
Interactive Reinforcement Learning for Feature Selection with Decision Tree in the Loop
In this journal version, we propose a novel interactive and closed-loop architecture to simultaneously model interactive reinforcement learning (IRL) and decision tree feedback (DTF).
Doubly Robust Off-Policy Learning on Low-Dimensional Manifolds by Deep Neural Networks
Our theory shows that deep neural networks are adaptive to the low-dimensional geometric structures of the covariates, and partially explains the success of deep learning for causal inference.
Magnetoelectric coupling and decoupling in multiferroic hexagonal YbFeO3 thin films
The coupling between ferroelectric and magnetic orders in multiferroic materials and the nature of magnetoelectric (ME) effects are enduring experimental challenges.
Materials Science Other Condensed Matter
Dirac semimetal PdTe2 temperature-dependent quasiparticle dynamics and electron-phonon coupling
Two distinct carrier and coherent phonons relaxation processes were identified in the 5 K - 300 K range.
Materials Science Superconductivity
Joint Air Quality and Weather Prediction Based on Multi-Adversarial Spatiotemporal Networks
Specifically, we first propose a heterogeneous recurrent graph neural network to model the spatiotemporal autocorrelation among air quality and weather monitoring stations.
UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning
Existed pre-training methods either focus on single-modal tasks or multi-modal tasks, and cannot effectively adapt to each other.
Ranked #3 on
Image Captioning
on MS COCO
Statistics of non-polarized points in the CMB polarization maps
We show that the total number density of non-polarized points of the E- and B-families is closely related to the presence of lensing and the tensor-to-scalar ratio $r$.
Cosmology and Nongalactic Astrophysics
Unsupervised Active Pre-Training for Reinforcement Learning
On DMControl suite, APT beats all baselines in terms of asymptotic performance and data efficiency and dramatically improves performance on tasks that are extremely difficult for training from scratch.
Spatial Object Recommendation with Hints: When Spatial Granularity Matters
We design a novel multi-task learning model called MPR (short for Multi-level POI Recommendation), where each task aims to return the top-k POIs at a certain spatial granularity level.
Out-of-distribution Prediction with Invariant Risk Minimization: The Limitation and An Effective Fix
Nevertheless, we find that the performance of IRM can be dramatically degraded under \emph{strong $\Lambda$ spuriousness} -- when the spurious correlation between the spurious features and the class label is strong due to the strong causal influence of their common cause, the domain label, on both of them (see Fig.
Disentangling Observed Causal Effects from Latent Confounders using Method of Moments
Thus, we provide a principled approach to tackling the joint problem of causal discovery and latent variable inference.
CoordiQ : Coordinated Q-learning for Electric Vehicle Charging Recommendation
Electric vehicles have been rapidly increasing in usage, but stations to charge them have not always kept up with demand, so efficient routing of vehicles to stations is critical to operating at maximum efficiency.
Out-of-Town Recommendation with Travel Intention Modeling
Second, a user-specific travel intention is formulated as an aggregation combining home-town preference and generic travel intention together, where the generic travel intention is regarded as a mixture of inherent intentions that can be learned by Neural Topic Model (NTM).
Intelligent Electric Vehicle Charging Recommendation Based on Multi-Agent Reinforcement Learning
Electric Vehicle (EV) has become a preferable choice in the modern transportation system due to its environmental and energy sustainability.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
PML: Progressive Margin Loss for Long-tailed Age Classification
In this paper, we propose a progressive margin loss (PML) approach for unconstrained facial age classification.
Behavior From the Void: Unsupervised Active Pre-Training
We introduce a new unsupervised pre-training method for reinforcement learning called APT, which stands for Active Pre-Training.
Multi-modal Trajectory Prediction for Autonomous Driving with Semantic Map and Dynamic Graph Attention Network
Predicting future trajectories of surrounding obstacles is a crucial task for autonomous driving cars to achieve a high degree of road safety.
Vehicle Re-identification Method Based on Vehicle Attribute and Mutual Exclusion Between Cameras
Vehicle Re-identification aims to identify a specific vehicle across time and camera view.
JIZHI: A Fast and Cost-Effective Model-As-A-Service System for Web-Scale Online Inference at Baidu
In this work, we present JIZHI - a Model-as-a-Service system - that per second handles hundreds of millions of online inference requests to huge deep models with more than trillions of sparse parameters, for over twenty real-time recommendation services at Baidu, Inc.
Multi-Agent Cooperative Bidding Games for Multi-Objective Optimization in e-Commercial Sponsored Search
Although a few studies use multi-agent reinforcement learning to set up a cooperative game, they still suffer the following drawbacks: (1) They fail to avoid collusion solutions where all the advertisers involved in an auction collude to bid an extremely low price on purpose.
MugRep: A Multi-Task Hierarchical Graph Representation Learning Framework for Real Estate Appraisal
Real estate appraisal refers to the process of developing an unbiased opinion for real property's market value, which plays a vital role in decision-making for various players in the marketplace (e. g., real estate agents, appraisers, lenders, and buyers).
An Operator-Splitting Method for the Gaussian Curvature Regularization Model with Applications to Surface Smoothing and Imaging
In our method, we decouple the full nonlinearity of Gaussian curvature from differential operators by introducing two matrix- and vector-valued functions.
Knowledge accumulating: The general pattern of learning
Artificial Intelligence has been developed for decades with the achievement of great progress.
DuTrust: A Sentiment Analysis Dataset for Trustworthiness Evaluation
Therefore, in order to systematically evaluate the factors for building trustworthy systems, we propose a novel and well-annotated sentiment analysis dataset to evaluate robustness and interpretability.
APS: Active Pretraining with Successor Features
We introduce a new unsupervised pretraining objective for reinforcement learning.
Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks
Most of existing statistical theories on deep neural networks have sample complexities cursed by the data dimension and therefore cannot well explain the empirical success of deep learning on high-dimensional data.
A Multimodal Sentiment Dataset for Video Recommendation
Based on this, we propose a multimodal sentiment analysis dataset, named baiDu Video Sentiment dataset (DuVideoSenti), and introduce a new sentiment system which is designed to describe the sentimental style of a video on recommendation scenery.
There are free lunches
In this paper we propose a novel idea, "There are free lunches" (TAFL) Theorem, which states that some algorithms can achieve the best performance in all possible tasks, in the condition that tasks are given in a specific order.
Spatial-Temporal Transformer for 3D Point Cloud Sequences
We test the effectiveness our PST2 with two different tasks on point cloud sequences, i. e., 4D semantic segmentation and 3D action recognition.
Emoji-based Co-attention Network for Microblog Sentiment Analysis
In this paper, we propose an emoji-based co-attention network that learns the mutual emotional semantics between text and emojis on microblogs.
URLB: Unsupervised Reinforcement Learning Benchmark
Deep Reinforcement Learning (RL) has emerged as a powerful paradigm to solve a range of complex yet specific control tasks.
Generalized Data Weighting via Class-level Gradient Manipulation
To be specific, GDW unrolls the loss gradient to class-level gradients by the chain rule and reweights the flow of each gradient separately.
Enhanced Fast Boolean Matching based on Sensitivity Signatures Pruning
In this paper, we introduce Boolean sensitivity into Boolean matching and design several sensitivity-related signatures to enhance fast Boolean matching.
NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition
For the sake of trade-off between efficiency and performance, a group of works merely perform SA operation within local patches, whereas the global contextual information is abandoned, which would be indispensable for visual recognition tasks.
Detecting and Tracking Small and Dense Moving Objects in Satellite Videos: A Benchmark
Satellite video cameras can provide continuous observation for a large-scale area, which is important for many remote sensing applications.
Neural Collaborative Graph Machines for Table Structure Recognition
We also show that the proposed NCGM can modulate collaborative pattern of different modalities conditioned on the context of intra-modality cues, which is vital for diversified table cases.
Ranked #6 on
Table Recognition
on PubTabNet
Domain-oriented Language Pre-training with Adaptive Hybrid Masking and Optimal Transport Alignment
Also, the word co-occurrences guided semantic learning of pre-training models can be largely augmented by entity-level association knowledge.
Generalized DataWeighting via Class-Level Gradient Manipulation
To be specific, GDW unrolls the loss gradient to class-level gradients by the chain rule and reweights the flow of each gradient separately.
Learning to Walk with Dual Agents for Knowledge Graph Reasoning
Graph walking based on reinforcement learning (RL) has shown great success in navigating an agent to automatically complete various reasoning tasks over an incomplete knowledge graph (KG) by exploring multi-hop relational paths.
Contextual Debiasing for Visual Recognition With Causal Mechanisms
As a common problem in the visual world, contextual bias means the recognition may depend on the co-occurrence context rather than the objects themselves, which is even more severe in multi-label tasks due to multiple targets and the absence of location.
Ranked #9 on
Multi-Label Classification
on MS-COCO
Deep Nonparametric Estimation of Operators between Infinite Dimensional Spaces
Learning operators between infinitely dimensional spaces is an important learning task arising in wide applications in machine learning, imaging science, mathematical modeling and simulations, etc.
Continual Learning with Recursive Gradient Optimization
Learning multiple tasks sequentially without forgetting previous knowledge, called Continual Learning(CL), remains a long-standing challenge for neural networks.
Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning
In this work, we propose Exploratory data for Offline RL (ExORL), a data-centric approach to offline RL.
CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery
We introduce Contrastive Intrinsic Control (CIC), an algorithm for unsupervised skill discovery that maximizes the mutual information between state-transitions and latent skill vectors.
Network resilience in the aging brain
Degeneration and adaptation are two competing sides of the same coin called resilience in the progressive processes of brain aging or diseases.
Arrhythmia Classifier Using Convolutional Neural Network with Adaptive Loss-aware Multi-bit Networks Quantization
In order to adapt to our compression method, we need a smaller and simpler network.
PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling
We propose a generative adversarial network for point cloud upsampling, which can not only make the upsampled points evenly distributed on the underlying surface but also efficiently generate clean high frequency regions.
UNIMO-2: End-to-End Unified Vision-Language Grounded Learning
In particular, we propose to conduct grounded learning on both images and texts via a sharing grounded space, which helps bridge unaligned images and texts, and align the visual and textual semantic spaces on different types of corpora.
Elastica Models for Color Image Regularization
Recently, the authors proposed a color elastica model, which minimizes both the surface area and elastica of the image manifold.
Joint Covering Congestion Rents in Multi-area Power Systems Considering Loop Flow Effects
We consider the problem of how multiple areas should jointly cover congestion rents of internal and tie-lines in an interconnected power system.
Knowledge Mining with Scene Text for Fine-Grained Recognition
Recently, the semantics of scene text has been proven to be essential in fine-grained image classification.
Predicting Solar Energetic Particles Using SDO/HMI Vector Magnetic Data Products and a Bidirectional LSTM Network
Solar energetic particles (SEPs) are an essential source of space radiation, which are hazards for humans in space, spacecraft, and technology in general.
The Devil is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-Training
The self-supervised Masked Image Modeling (MIM) schema, following "mask-and-reconstruct" pipeline of recovering contents from masked image, has recently captured the increasing interest in the multimedia community, owing to the excellent ability of learning visual representation from unlabeled data.
Fetal Brain Tissue Annotation and Segmentation Challenge Results
Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context.
Arrhythmia Classifier using Binarized Convolutional Neural Network for Resource-Constrained Devices
In this paper, a binarized convolutional neural network suitable for ECG monitoring is proposed, which is hardware-friendly and more suitable for use in resource-constrained wearable devices.
Feature and Instance Joint Selection: A Reinforcement Learning Perspective
Feature selection and instance selection are two important techniques of data processing.
A Fine-grained Interpretability Evaluation Benchmark for Neural NLP
Based on this benchmark, we conduct experiments on three typical models with three saliency methods, and unveil their strengths and weakness in terms of interpretability.
Multimodal Masked Autoencoders Learn Transferable Representations
We provide an empirical study of M3AE trained on a large-scale image-text dataset, and find that M3AE is able to learn generalizable representations that transfer well to downstream tasks.
Unbiased Implicit Feedback via Bi-level Optimization
Recent works reveal a huge gap between the implicit feedback and user-item relevance due to the fact that implicit feedback is also closely related to the item exposure.
Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint
Overparameterized neural networks enjoy great representation power on complex data, and more importantly yield sufficiently smooth output, which is crucial to their generalization and robustness.
Self-Supervised 3D Monocular Object Detection by Recycling Bounding Boxes
We evaluate the pretext task using the RTM3D detection model as baseline, with and without the application of data augmentation.
Masked World Models for Visual Control
Yet the current approaches typically train a single model end-to-end for learning both visual representations and dynamics, making it difficult to accurately model the interaction between robots and small objects.
Model-based Reinforcement Learning
Reinforcement Learning (RL)
+1
GMN: Generative Multi-modal Network for Practical Document Information Extraction
Document Information Extraction (DIE) has attracted increasing attention due to its various advanced applications in the real world.
Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting
To address the coupling problem, we propose a Cycle Self-Training (CST) framework for SSOD, which consists of two teachers T1 and T2, two students S1 and S2.
RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via Repeating
Binary neural network (BNN) is an extreme quantization version of convolutional neural networks (CNNs) with all features and weights mapped to just 1-bit.
A Ligand-and-structure Dual-driven Deep Learning Method for the Discovery of Highly Potent GnRH1R Antagonist to treat Uterine Diseases
Gonadotrophin-releasing hormone receptor (GnRH1R) is a promising therapeutic target for the treatment of uterine diseases.
TaCo: Textual Attribute Recognition via Contrastive Learning
To realize this goal, we design the learning paradigm from three perspectives: 1) generating attribute views, 2) extracting subtle but crucial details, and 3) exploiting valued view pairs for learning, to fully unlock the pre-training potential.
Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models
Remarkably, we also show that adversarial training with our proposed attacks can significantly improve the robustness of spatiotemporal traffic forecasting models.
Palm up: Playing in the Latent Manifold for Unsupervised Pretraining
In this work, we aim to bring the best of both worlds and propose an algorithm that exhibits an exploratory behavior whilst it utilizes large diverse datasets.
Instruction-Following Agents with Multimodal Transformer
Our \ours method consists of a multimodal transformer that encodes visual observations and language instructions, and a transformer-based policy that predicts actions based on encoded representations.
Towards Better Few-Shot and Finetuning Performance with Forgetful Causal Language Models
Large language models (LLM) trained using the next-token-prediction objective, such as GPT3 and PaLM, have revolutionized natural language processing in recent years by showing impressive zero-shot and few-shot capabilities across a wide range of tasks.
PAI3D: Painting Adaptive Instance-Prior for 3D Object Detection
3D object detection is a critical task in autonomous driving.
Masked Autoencoding for Scalable and Generalizable Decision Making
We are interested in learning scalable agents for reinforcement learning that can learn from large-scale, diverse sequential data similar to current large vision and language models.
High Dimensional Binary Classification under Label Shift: Phase Transition and Regularization
Label Shift has been widely believed to be harmful to the generalization performance of machine learning models.
Hierarchical Prompt Learning for Multi-Task Learning
Considering this, we present Hierarchical Prompt (HiPro) learning, a simple and effective method for jointly adapting a pre-trained VLM to multiple downstream tasks.
CSAT‑FTCN: A Fuzzy‑Oriented Model with Contextual Self‑attention Network for Multimodal Emotion Recognition
Moreover, the CSAT-FTCN can obtain the dependency relationships of target utterances on internal own key information and external contextual information to understand emotions in a more profound sense.
Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment
Recent progress in scaling up large language models has shown impressive capabilities in performing few-shot learning across a wide range of text-based tasks.
Chain of Hindsight Aligns Language Models with Feedback
Applying our method to large language models, we observed that Chain of Hindsight significantly surpasses previous methods in aligning language models with human preferences.
Aligning Text-to-Image Models using Human Feedback
Our results demonstrate the potential for learning from human feedback to significantly improve text-to-image models.
Window transformer for dialogue document: a joint framework for causal emotion entailment
The Causal Emotion Entailment (CEE) task aims to extract all potential pairs of emotions and corresponding causes from the unannotated emotion document in the conversational context.
Ranked #2 on
Causal Emotion Entailment
on RECCON
Time Associated Meta Learning for Clinical Prediction
We view time-associated disease prediction as classification tasks at multiple time points.
Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation
Recently, Table Structure Recognition (TSR) task, aiming at identifying table structure into machine readable formats, has received increasing interest in the community.
Deep Nonparametric Estimation of Intrinsic Data Structures by Chart Autoencoders: Generalization Error and Robustness
Our paper establishes statistical guarantees on the generalization error of chart autoencoders, and we demonstrate their denoising capabilities by considering $n$ noisy training samples, along with their noise-free counterparts, on a $d$-dimensional manifold.
GQE-Net: A Graph-based Quality Enhancement Network for Point Cloud Color Attribute
To reduce color distortion in point clouds, we propose a graph-based quality enhancement network (GQE-Net) that uses geometry information as an auxiliary input and graph convolution blocks to extract local features efficiently.
Beta-VAE has 2 Behaviors: PCA or ICA?
Beta-VAE is a very classical model for disentangled representation learning, the use of an expanding bottleneck that allow information into the decoder gradually is key to representation disentanglement as well as high-quality reconstruction.
On Degeneracy Issues in Multi-parametric Programming and Critical Region Exploration based Distributed Optimization in Smart Grid Operations
Improving renewable energy resource utilization efficiency is crucial to reducing carbon emissions, and multi-parametric programming has provided a systematic perspective in conducting analysis and optimization toward this goal in smart grid operations.
A Survey on Vertical Federated Learning: From a Layered Perspective
From the hardware layer to the vertical federated system layer, researchers contribute to various aspects of VFL.
Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA
Different to conventional STVQA models which take the linguistic semantics and visual semantics in scene text as two separate features, in this paper, we propose a paradigm of "Locate Then Generate" (LTG), which explicitly unifies this two semantics with the spatial bounding box as a bridge connecting them.
Arrhythmia Classifier Based on Ultra-Lightweight Binary Neural Network
With the development of deep learning, numerous ECG classification algorithms based on deep learning have emerged.
A geometry-aware deep network for depth estimation in monocular endoscopy
To address this issue, we introduce a gradient loss to penalize edge fluctuations ambiguous around stepped edge structures and a normal loss to explicitly express the sensitivity to frequently small structures, and propose a geometric consistency loss to spreads the spatial information across the sample grids to constrain the global geometric anatomy structures.
Environment-Aware Codebook for Reconfigurable Intelligent Surface-Aided MISO Communications
Reconfigurable intelligent surface (RIS) is a revolutionary technology that can customize the wireless channel and improve the energy efficiency of next-generation cellular networks.
Enhancing Short-Term Wind Speed Forecasting using Graph Attention and Frequency-Enhanced Mechanisms
In this paper, a Graph-attentive Frequency-enhanced Spatial-Temporal Wind Speed Forecasting model based on graph attention and frequency-enhanced mechanisms, i. e., GFST-WSF, is proposed to improve the accuracy of short-term wind speed forecasting.
DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models
We focus on diffusion models, defining the fine-tuning task as an RL problem, and updating the pre-trained text-to-image diffusion models using policy gradient to maximize the feedback-trained reward.
The False Promise of Imitating Proprietary LLMs
This approach looks to cheaply imitate the proprietary model's capabilities using a weaker open-source model.
Emergent Agentic Transformer from Chain of Hindsight Experience
Our method consists of relabelling target return of each trajectory to the maximum total reward among in sequence of trajectories and training an autoregressive model to predict actions conditioning on past states, actions, rewards, target returns, and task completion tokens, the resulting model, Agentic Transformer (AT), can learn to improve upon itself both at training and test time.
Blockwise Parallel Transformer for Large Context Models
Transformers have emerged as the cornerstone of state-of-the-art natural language processing models, showcasing exceptional performance across a wide range of AI applications.
Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman
We theoretically prove that even if we fix the space complexity to $O(n^k)$ (for any $k\geq 2$) in $(k, t)$-FWL, we can construct an expressiveness hierarchy up to solving the graph isomorphism problem.
Ranked #2 on
Graph Regression
on ZINC-500k
Bkd-FedGNN: A Benchmark for Classification Backdoor Attacks on Federated Graph Neural Network
To address these limitations, we propose Bkd-FedGNN, a benchmark for backdoor attacks on FedGNN.
UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction
We hope the proposed UUKG fosters research on urban knowledge graphs and broad smart city applications.
Robust Spatiotemporal Traffic Forecasting with Reinforced Dynamic Adversarial Training
Therefore, improving the adversarial robustness of these models is crucial for ITS.
A Preference-aware Meta-optimization Framework for Personalized Vehicle Energy Consumption Estimation
To this end, this paper proposes a preference-aware meta-optimization framework Meta-Pec for personalized vehicle energy consumption estimation.
Connections between Operator-splitting Methods and Deep Neural Networks with Applications in Image Segmentation
In this paper, we give an algorithmic explanation for deep neural networks, especially in their connections with operator splitting.
PottsMGNet: A Mathematical Explanation of Encoder-Decoder Based Neural Networks
We use the two-phase Potts model for image segmentation as an example for our explanations.
NTIRE 2023 Quality Assessment of Video Enhancement Challenge
61 participating teams submitted their prediction results during the development phase, with a total of 3168 submissions.
Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Network
Accurate traffic forecasting at intersections governed by intelligent traffic signals is critical for the advancement of an effective intelligent traffic signal control system.
Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration
We propose a novel end-to-end document understanding model called SeRum (SElective Region Understanding Model) for extracting meaningful information from document images, including document analysis, retrieval, and office automation.
Time consistency of dynamic risk measures and dynamic performance measures generated by distortion functions
We prove that these two classes of risk measures coincides.
Graph Contrastive Learning Meets Graph Meta Learning: A Unified Method for Few-shot Node Tasks
In our study, we first identify two crucial advantages of contrastive learning compared to meta learning, including (1) the comprehensive utilization of graph nodes and (2) the power of graph augmentations.
CINFormer: Transformer network with multi-stage CNN feature injection for surface defect segmentation
To address these issues, we propose a transformer network with multi-stage CNN (Convolutional Neural Network) feature injection for surface defect segmentation, which is a UNet-like structure named CINFormer.
Decision Fusion Network with Perception Fine-tuning for Defect Classification
In addition, we propose a perception fine-tuning module (PFM) that fine-tunes the foreground and background during the segmentation stage.
Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing
Finally, how to generate diverse and plausible results from a 2D clothing image.
One for All: Towards Training One Graph Model for All Classification Tasks
For in-context learning on graphs, OFA introduces a novel graph prompting paradigm that appends prompting substructures to the input graph, which enables it to address varied tasks without fine-tuning.
Ring Attention with Blockwise Transformers for Near-Infinite Context
Transformers have emerged as the architecture of choice for many state-of-the-art AI models, showcasing exceptional performance across a wide range of AI applications.
Exploration with Principles for Diverse AI Supervision
Training large transformers using next-token prediction has given rise to groundbreaking advancements in AI.
Reinforcement Learning (RL)
Unsupervised Reinforcement Learning
Machine Learning for Urban Air Quality Analytics: A Survey
In this article, we present a comprehensive survey of ML-based air quality analytics, following a roadmap spanning from data acquisition to pre-processing, and encompassing various analytical tasks such as pollution pattern mining, air quality inference, and forecasting.
Multi-omics Sampling-based Graph Transformer for Synthetic Lethality Prediction
We showcase the effectiveness of MSGT-SL on real-world SL tasks, demonstrating the empirical benefits gained from the graph transformer and multi-omics data.
Chain-of-Choice Hierarchical Policy Learning for Conversational Recommendation
Conversational Recommender Systems (CRS) illuminate user preferences via multi-round interactive dialogues, ultimately navigating towards precise and satisfactory recommendations.
ChipNeMo: Domain-Adapted LLMs for Chip Design
ChipNeMo aims to explore the applications of large language models (LLMs) for industrial chip design.
The Power of the Senses: Generalizable Manipulation from Vision and Touch through Masked Multimodal Learning
For tasks requiring object manipulation, we seamlessly and effectively exploit the complementarity of our senses of vision and touch.
PT-Tuning: Bridging the Gap between Time Series Masked Reconstruction and Forecasting via Prompt Token Tuning
In this paper, we first point out that the unification of task objectives and adaptation for task difficulty are critical for bridging the gap between time series masked reconstruction and forecasting.
DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding
This work presents DocPedia, a novel large multimodal model (LMM) for versatile OCR-free document understanding, capable of parsing images up to 2, 560$\times$2, 560 resolution.
Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer
A straightforward solution is performing model fine-tuning tailored to a specific scenario, but it is computationally intensive and requires multiple model copies for various scenarios.
Survey on Trustworthy Graph Neural Networks: From A Causal Perspective
Moreover, we introduce a taxonomy of Causality-Inspired GNNs (CIGNNs) based on the type of causal learning capability they are equipped with, i. e., causal reasoning and causal representation learning.
LLMLight: Large Language Models as Traffic Signal Control Agents
Traffic Signal Control (TSC) is a crucial component in urban traffic management, aiming to optimize road network efficiency and reduce congestion.
Dual-space Hierarchical Learning for Goal-guided Conversational Recommendation
In this paper, we propose Dual-space Hierarchical Learning (DHL) to leverage multi-level goal sequences and their hierarchical relationships for conversational recommendation.
Double-well Net for Image Segmentation
In this study, our goal is to integrate classical mathematical models with deep neural networks by introducing two novel deep neural network models for image segmentation known as Double-well Nets.
TrustLLM: Trustworthiness in Large Language Models
This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions.
MCRPL: A Pretrain, Prompt & Fine-tune Paradigm for Non-overlapping Many-to-one Cross-domain Recommendation
To overcome the above challenges, we focus on NMCR, and devise MCRPL as our solution.
Generalization Error Guaranteed Auto-Encoder-Based Nonlinear Model Reduction for Operator Learning
The problem of operator learning, in this context, seeks to extract these physical processes from empirical data, which is challenging due to the infinite or high dimensionality of data.
Distributionally Robust Policy Evaluation under General Covariate Shift in Contextual Bandits
Central to our methodology is the application of robust regression, a distributionally robust technique tailored here to improve the estimation of conditional reward distribution from logging data.
GarchingSim: An Autonomous Driving Simulator with Photorealistic Scenes and Minimalist Workflow
However, the availability of free and open-source simulators is limited, and the installation and configuration process can be daunting for beginners and interdisciplinary researchers.
Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models
Machine learning techniques are now integral to the advancement of intelligent urban services, playing a crucial role in elevating the efficiency, sustainability, and livability of urban environments.
A Cross-View Hierarchical Graph Learning Hypernetwork for Skill Demand-Supply Joint Prediction
The rapidly changing landscape of technology and industries leads to dynamic skill requirements, making it crucial for employees and employers to anticipate such shifts to maintain a competitive edge in the labor market.
UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction
Urban knowledge graph has recently worked as an emerging building block to distill critical knowledge from multi-sourced urban data for diverse urban application scenarios.
World Model on Million-Length Video And Language With Blockwise RingAttention
To address these challenges, we curate a large dataset of diverse videos and books, utilize the Blockwise RingAttention technique to scalably train on long sequences, and gradually increase context size from 4K to 1M tokens.
LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendations
Additionally, we introduce graph relationship understanding and analysis functions into LLMs to enhance their focus on connectivity information in graph data.
DRL-Based Orchestration of Multi-User MISO Systems with Stacked Intelligent Metasurfaces
Stacked intelligent metasurfaces (SIM) represents an advanced signal processing paradigm that enables over-the-air processing of electromagnetic waves at the speed of light.
Multiview Subspace Clustering of Hyperspectral Images based on Graph Convolutional Networks
In conclusion, the proposed model can effectively improve the clustering ac-curacy of HSI.
Make Large Language Model a Better Ranker
ALRO is designed to bridge the gap between the capabilities of LLMs and the nuanced requirements of ranking tasks within recommender systems.
Are LLMs Effective Backbones for Fine-tuning? An Experimental Investigation of Supervised LLMs on Chinese Short Text Matching
The recent success of Large Language Models (LLMs) has garnered significant attention in both academia and industry.
Teeth-SEG: An Efficient Instance Segmentation Framework for Orthodontic Treatment based on Anthropic Prior Knowledge
Teeth localization, segmentation, and labeling in 2D images have great potential in modern dentistry to enhance dental diagnostics, treatment planning, and population-based studies on oral health.
Attention-Aware Laparoscopic Image Desmoking Network with Lightness Embedding and Hybrid Guided Embedding
This paper presents a novel method of smoke removal from the laparoscopic images.
Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data
Synthetic data is gaining increasing relevance for training machine learning models.
TextSquare: Scaling up Text-Centric Visual Instruction Tuning
Text-centric visual question answering (VQA) has made great strides with the development of Multimodal Large Language Models (MLLMs), yet open-source models still fall short of leading models like GPT4V and Gemini, partly due to a lack of extensive, high-quality instruction tuning data.
MABNet: A Lightweight Stereo Network Based on Multibranch Adjustable Bottleneck Module
MABNet is based on a novel Multibranch Adjustable Bottleneck (MAB) module, which is less demanding on parameters and computation.
Diversified Multiple Instance Learning for Document-Level Multi-Aspect Sentiment Classification
To this end, we propose a novel Diversified Multiple Instance Learning Network (D-MILN), which is able to achieve aspect-level sentiment classification with only document-level weak supervision.
Improving Abstractive Dialogue Summarization with Hierarchical Pretraining and Topic Segment
With the increasing abundance of meeting transcripts, meeting summary has attracted more and more attention from researchers.
