Search Results for author:
Found 118 papers, 59 papers with code
Temporal Logic Point Processes
We propose a modeling framework for event data, which excels in small data regime with the ability to incorporate domain knowledge.
In silico bioactivity prediction of proteins interacting with graphene-based nanomaterials guides rational design of biosensor
Graphene based nanomaterials have attracted significant attention for their potentials in biomedical and biotechnology applications in recent years, owing to the outstanding physical and chemical properties.
FSMR: A Feature Swapping Multi-modal Reasoning Approach with Joint Textual and Visual Clues
Multi-modal reasoning plays a vital role in bridging the gap between textual and visual information, enabling a deeper understanding of the context.
Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation
In the M-step, we update both the rule set and model parameters to enhance the likelihood function's lower bound.
Deep Generative Modeling for Financial Time Series with Application in VaR: A Comparative Review
The objectives for financial time series generation are to generate synthetic data paths with good variety, and similar distribution and dynamics to the original historical data.
Evolutionary Alternating Direction Method of Multipliers for Constrained Multi-Objective Optimization with Unknown Constraints
Constrained multi-objective optimization problems (CMOPs) pervade real-world applications in science, engineering, and design.
Inferring Heterogeneous Treatment Effects of Crashes on Highway Traffic: A Doubly Robust Causal Machine Learning Approach
This paper proposes a novel causal machine learning framework to estimate the causal effect of different types of crashes on highway speed.
Few Clicks Suffice: Active Test-Time Adaptation for Semantic Segmentation
Extensive experiments demonstrate that ATASeg bridges the performance gap between TTA methods and their supervised counterparts with only extremely few annotations, even one click for labeling surpasses known SOTA TTA methods by 2. 6% average mIoU on ACDC benchmark.
Language Semantic Graph Guided Data-Efficient Learning
Therefore, to achieve data-efficient learning, researchers typically explore approaches that can leverage more related or unlabeled data without necessitating additional manual labeling efforts, such as Semi-Supervised Learning (SSL), Transfer Learning (TL), and Data Augmentation (DA).
Shape-centered Representation Learning for Visible-Infrared Person Re-identification
One pertains to the dependence on auxiliary models for shape feature extraction in the inference phase, along with the errors in generated infrared shapes due to the intrinsic modality disparity.
Generalized Robust Test-Time Adaptation in Continuous Dynamic Scenarios
Test-time adaptation (TTA) adapts the pre-trained models to test distributions during the inference phase exclusively employing unlabeled test data streams, which holds great value for the deployment of models in real-world applications.
Amortized Network Intervention to Steer the Excitatory Point Processes
Excitatory point processes (i. e., event flows) occurring over dynamic graphs (i. e., evolving topologies) provide a fine-grained model to capture how discrete events may spread over time and space.
FIND: A Function Description Benchmark for Evaluating Interpretability Methods
FIND contains functions that resemble components of trained neural networks, and accompanying descriptions of the kind we seek to generate.
Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Models
To translate well, machine translation (MT) systems and general-purposed language models (LMs) need a deep understanding of both source and target languages and cultures.
Hawkes Processes with Delayed Granger Causality
We aim to explicitly model the delayed Granger causal effects based on multivariate Hawkes processes.
Reinforcement Logic Rule Learning for Temporal Point Processes
Leveraging the temporal point process modeling and learning framework, the rule content and weights will be gradually optimized until the likelihood of the observational event sequences is optimal.
Discovering Intrinsic Spatial-Temporal Logic Rules to Explain Human Actions
Our approach is inspired by the fact that human actions are usually driven by their intentions or desires, and are influenced by environmental factors such as the spatial relationships with surrounding objects.
Variational Disentangled Graph Auto-Encoders for Link Prediction
The proposed framework infers the latent factors that cause edges in the graph and disentangles the representation into multiple channels corresponding to unique latent factors, which contributes to improving the performance of link prediction.
Contrastive Disentangled Learning on Graph for Node Classification
Inspired by the success of contrastive learning, we propose a novel framework for contrastive disentangled learning on graphs, employing a disentangled graph encoder and two carefully crafted self-supervision signals.
Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models
Text-to-image generative models have enabled high-resolution image synthesis across different domains, but require users to specify the content they wish to generate.
Stochastic Natural Thresholding Algorithms
Sparse signal recovery is one of the most fundamental problems in various applications, including medical imaging and remote sensing.
Exploring the Compositional Generalization in Context Dependent Text-to-SQL Parsing
Based on these observations, we propose a method named \texttt{p-align} to improve the compositional generalization of Text-to-SQL models.
Improving Factuality and Reasoning in Language Models through Multiagent Debate
Our findings indicate that this approach significantly enhances mathematical and strategic reasoning across a number of tasks.
Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual Verbalizer
In this paper, we propose a novel Soft prompt learning framework with the Multilingual Verbalizer (SoftMV) for XNLI.
Cross-Lingual Natural Language Inference
Cross-Lingual Transfer
Introspective Tips: Large Language Model for In-Context Decision Making
The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks.
VisDA 2022 Challenge: Domain Adaptation for Industrial Waste Sorting
To test the abilities of computer vision models on this task, we present the VisDA 2022 Challenge on Domain Adaptation for Industrial Waste Sorting.
Robust Test-Time Adaptation in Dynamic Scenarios
Test-time adaptation (TTA) intends to adapt the pretrained model to test distributions with only unlabeled test data streams.
Improving Generalization with Domain Convex Game
A classical solution to DG is domain augmentation, the common belief of which is that diversifying source domains will be conducive to the out-of-distribution generalization.
Open-vocabulary Panoptic Segmentation with Embedding Modulation
Open-vocabulary image segmentation is attracting increasing attention due to its critical applications in the real world.
Dirichlet-based Uncertainty Calibration for Active Domain Adaptation
Active domain adaptation (DA) aims to maximally boost the model adaptation on a new target domain by actively selecting limited target data to annotate, whereas traditional active learning methods may be less effective since they do not consider the domain shift issue.
ConceptFusion: Open-set Multimodal 3D Mapping
ConceptFusion leverages the open-set capabilities of today's foundation models pre-trained on internet-scale data to reason about concepts across modalities such as natural language, images, and audio.
On the Difficulty of Unpaired Infrared-to-Visible Video Translation: Fine-Grained Content-Rich Patches Transfer
Explicit visible videos can provide sufficient visual information and facilitate vision applications.
Borrowing Knowledge From Pre-trained Language Model: A New Data-efficient Visual Learning Paradigm
To address this issue, this paper presents a novel approach that seeks to leverage linguistic knowledge for data-efficient visual learning.
Artificial Intelligence Security Competition (AISC)
The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems.
VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions
However, previous methods often reckon on additional reference images of the same scenes taken from normal conditions, which are quite tough to collect in reality.
Ranked #7 on
Domain Adaptation
on Cityscapes to ACDC
Joint Semantic Transfer Network for IoT Intrusion Detection
The scenario semantic endows source NI and II domain with characteristics from each other to ease the knowledge transfer process via a confused domain discriminator and categorical distribution knowledge preservation.
Composing Ensembles of Pre-trained Models via Iterative Consensus
Such closed-loop communication enables models to correct errors caused by other models, significantly boosting performance on downstream tasks, e. g. improving accuracy on grade school math problems by 7. 5%, without requiring any model finetuning.
Ranked #1 on
Video Question Answering
on ActivityNet-QA
FedForgery: Generalized Face Forgery Detection with Residual Federated Learning
Experiments conducted on publicly available face forgery detection datasets prove the superior performance of the proposed FedForgery.
Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification
Based on our constructed dataset, we prove that with the increase of frames in a tracklet, the performance does meet more enhancement, demonstrating the significance of video-to-video matching in RGB-IR person Re-ID.
Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation
To alleviate these issues, we propose to simultaneously conduct feature alignment in two individual spaces focusing on different domains, and create for each space a domain-oriented classifier tailored specifically for that domain.
SP2: A Second Order Stochastic Polyak Method
We take a step further and develop a method for solving the interpolation equations that uses the local second-order approximation of the model.
Learning Iterative Reasoning through Energy Minimization
Finally, we illustrate that our approach can recursively solve algorithmic problems requiring nested reasoning
Compositional Visual Generation with Composable Diffusion Models
Large text-guided diffusion models, such as DALLE-2, are able to generate stunning photorealistic images given natural language descriptions.
Do We Really Need to Use Constraint Violation in Constrained Evolutionary Multi-Objective Optimization?
Constraint violation has been a building block to design evolutionary multi-objective optimization algorithms for solving constrained multi-objective optimization problems.
Improving Transferability for Domain Adaptive Detection Transformers
We implement the findings and the alignment modules into our adaptation method, and it benchmarks the DETR-style detector on the domain shift settings.
ROMA: Cross-Domain Region Similarity Matching for Unpaired Nighttime Infrared to Daytime Visible Video Translation
To be specific, ROMA could efficiently translate the unpaired nighttime infrared videos into fine-grained daytime visible ones, meanwhile maintain the spatiotemporal consistency via matching the cross-domain region similarity.
SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation
Domain adaptive semantic segmentation attempts to make satisfactory dense predictions on an unlabeled target domain by utilizing the supervised model trained on a labeled source domain.
Ranked #4 on
Semantic Segmentation
on GTAV-to-Cityscapes Labels
Causality Inspired Representation Learning for Domain Generalization
Specifically, we assume that each input is constructed from a mix of causal factors (whose relationship with the label is invariant across domains) and non-causal factors (category-independent), and only the former cause the classification judgments.
Domain Adaptation via Prompt Learning
Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given.
Learning Temporal Rules from Noisy Timeseries Data
Events across a timeline are a common data representation, seen in different temporal modalities.
Pre-Trained Language Models for Interactive Decision-Making
Together, these results suggest that language modeling induces representations that are useful for modeling not just language, but also goals and plans; these representations can aid learning and generalization even outside of language processing.
Mars Entry Trajectory Planning with Range Discretization and Successive Convexification
The virtual control and adaptive trust-region techniques are employed to improve the accuracy, robustness, and computation efficiency of the algorithm.
Fast solver for J2-perturbed Lambert problem using deep neural network
The intelligent initial guess generator is a deep neural network that is trained to correct the initial velocity vector coming from the solution of the unperturbed Lambert problem.
Pareto Domain Adaptation
Domain adaptation (DA) attempts to transfer the knowledge from a labeled source domain to an unlabeled target domain that follows different distribution from the source.
Incentive Compatible Pareto Alignment for Multi-Source Large Graphs
Challenges of the problem include 1) how to align large-scale entities between sources to share information and 2) how to mitigate negative transfer from joint learning multi-source data.
Active Learning for Domain Adaptation: An Energy-Based Approach
Unsupervised domain adaptation has recently emerged as an effective paradigm for generalizing deep neural networks to new target domains.
Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation
Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network.
Exploiting Both Domain-specific and Invariant Knowledge via a Win-win Transformer for Unsupervised Domain Adaptation
Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain.
SPCL: A New Framework for Domain Adaptive Semantic Segmentation via Semantic Prototype-based Contrastive Learning
Although there is significant progress in supervised semantic segmentation, it remains challenging to deploy the segmentation models to unseen domains due to domain biases.
Learning to Compose Visual Relations
The visual world around us can be described as a structured set of objects and their associated relations.
Unsupervised Learning of Compositional Energy Concepts
In this work, we propose COMET, which discovers and represents concepts as separate energy functions, enabling us to represent both global concepts as well as objects under a unified framework.
Efficient Learning and Decoding of the Continuous-Time Hidden Markov Model for Disease Progression Modeling
We solve the first challenge by reformulating the estimation problem as an equivalent discrete time-inhomogeneous hidden Markov model.
Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions
Our task poses unique challenges as a system does not know what types of human-object interactions are present in a video or the actual spatiotemporal location of the human and the object.
Explaining Point Processes by Learning Interpretable Temporal Logic Rules
We propose a principled method to learn a set of human-readable logic rules to explain temporal point processes.
Neural Temporal Logic Programming
Events across a timeline are a common data representation, seen in different temporal modalities.
Language Model Pre-training Improves Generalization in Policy Learning
Additional experiments explore the role of language-based encodings in these results; we find that it is possible to train a simple adapter layer that maps from observations and action histories to LM embeddings, and thus that language modeling provides an effective initializer even for tasks with no language as input or output.
Semantic Concentration for Domain Adaptation
To tackle this issue, we propose Semantic Concentration for Domain Adaptation (SCDA), which encourages the model to concentrate on the most principal features via the pair-wise adversarial alignment of prediction distributions.
ZiGAN: Fine-grained Chinese Calligraphy Font Generation via a Few-shot Style Transfer Approach
Chinese character style transfer is a very challenging problem because of the complexity of the glyph shapes or underlying structures and large numbers of existed characters, when comparing with English letters.
I2V-GAN: Unpaired Infrared-to-Visible Video Translation
Human vision is often adversely affected by complex environmental factors, especially in night vision scenarios.
3D Neural Scene Representations for Visuomotor Control
Humans have a strong intuitive understanding of the 3D environment around us.
Understanding the Spread of COVID-19 Epidemic: A Spatio-Temporal Point Process View
In this paper, we model the propagation of the COVID-19 as spatio-temporal point processes and propose a generative and intensity-free model to track the spread of the disease.
Quotient Space-Based Keyword Retrieval in Sponsored Search
Since the synonymous relations between queries and keywords are quite scarce, the traditional information retrieval framework is inefficient in this scenario.
TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning
Secondly, on top of the proposed graph transformer, we introduce a two-stream encoder that separately extracts representations from temporal neighborhoods associated with the two interaction nodes and then utilizes a co-attentional transformer to model inter-dependencies at a semantic level.
Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation
Specifically, we first design a pixel-wise contrastive loss by considering the correspondences between semantic distributions and pixel-wise representations from both domains.
Dynamic Domain Adaptation for Efficient Inference
Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy.
MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
Real-world training data usually exhibits long-tailed distribution, where several majority classes have a significantly larger number of samples than the remaining minority classes.
Ranked #2 on
Long-tail Learning
on CIFAR-100-LT (ρ=200)
Transferable Semantic Augmentation for Domain Adaptation
To remedy this, we propose a Transferable Semantic Augmentation (TSA) approach to enhance the classifier adaptation ability through implicitly generating source features towards target semantics.
Generalized Domain Conditioned Adaptation Network
Domain Adaptation (DA) attempts to transfer knowledge learned in the labeled source domain to the unlabeled but related target domain without requiring large amounts of target supervision.
Digital Beamforming Robust to Time-Varying Carrier Frequency Offset
We present novel beamforming algorithms that are robust to signal corruptions arising from this time-variant carrier frequency offset.
One-shot Face Reenactment Using Appearance Adaptive Normalization
The paper proposes a novel generative adversarial network for one-shot face reenactment, which can animate a single face image to a different pose-and-expression (provided by a driving image) while keeping its original appearance.
Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation
Motivated by the observation that target samples cannot always be separated distinctly by the decision boundary, here in the proposed BCDM, we design a novel classifier determinacy disparity (CDD) metric, which formulates classifier discrepancy as the class relevance of distinct target predictions and implicitly introduces constraint on the target feature discriminability.
Improved Contrastive Divergence Training of Energy Based Models
Contrastive divergence is a popular method of training energy-based models, but is known to have difficulties with training stability.
Compositional Visual Generation with Energy Based Models
A vital aspect of human intelligence is the ability to compose increasingly complex concepts out of simpler ideas, enabling both rapid learning and adaptation of knowledge.
Energy-Based Models for Continual Learning
We motivate Energy-Based Models (EBMs) as a promising model class for continual learning problems.
SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition
We tackle the problem of place recognition from point cloud data and introduce a self-attention and orientation encoding network (SOE-Net) that fully explores the relationship between points and incorporates long-range context into point-wise local descriptors.
Ranked #5 on
3D Place Recognition
on Oxford RobotCar Dataset
(AR@1% metric)
Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
In this paper, we introduce Watch-And-Help (WAH), a challenge for testing social intelligence in agents.
Domain Agnostic Learning for Unbiased Authentication
We further extend our method to a meta-learning framework to pursue more thorough domain-difference elimination.
Optimizing AD Pruning of Sponsored Search with Reinforcement Learning
Industrial sponsored search system (SSS) can be logically divided into three modules: keywords matching, ad retrieving, and ranking.
Simultaneous Semantic Alignment Network for Heterogeneous Domain Adaptation
In this paper, we propose a Simultaneous Semantic Alignment Network (SSAN) to simultaneously exploit correlations among categories and align the centroids for each category across domains.
Domain Conditioned Adaptation Network
Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while integrating a totally shared convolutional architecture for source and target.
Compositional Visual Generation and Inference with Energy Based Models
A vital aspect of human intelligence is the ability to compose increasingly complex concepts out of simpler ideas, enabling both rapid learning and adaptation of knowledge.
Deep Residual Correction Network for Partial Domain Adaptation
Deep domain adaptation methods have achieved appealing performance by learning transferable representations from a well-labeled source domain to a different but related unlabeled target domain.
A Mobile Robot Hand-Arm Teleoperation System by Vision and IMU
In this paper, we present a multimodal mobile teleoperation system that consists of a novel vision-based hand pose regression network (Transteleop) and an IMU-based arm tracking method.
Robust Robotic Pouring using Audition and Haptics
Both network training results and robot experiments demonstrate that MP-Net is robust against noise and changes to the task and environment.
Iterative Hard Thresholding for Low CP-rank Tensor Models
In this paper, we utilize the same tensor version of the Restricted Isometry Property (RIP) to extend these results for tensors with low CANDECOMP/PARAFAC (CP) rank.
The Landscape of Non-convex Empirical Risk with Degenerate Population Risk
We also apply the theory to matrix sensing and phase retrieval to demonstrate how to infer the landscape of empirical risk from that of the corresponding population risk.
Imitation Learning of Neural Spatio-Temporal Point Processes
We present a novel Neural Embedding Spatio-Temporal (NEST) point process model for spatio-temporal discrete event data and develop an efficient imitation learning (a type of reinforcement learning) based approach for model fitting.
An Approach for Process Model Extraction By Multi-Grained Text Classification
Process model extraction (PME) is a recently emerged interdiscipline between natural language processing (NLP) and business process management (BPM), which aims to extract process models from textual descriptions.
Making Sense of Audio Vibration for Liquid Height Estimation in Robotic Pouring
PouringNet is trained on our collected real-world pouring dataset with multimodal sensing data, which contains more than 3000 recordings of audio, force feedback, video and trajectory data of the human hand that performs the pouring task.
Robotics Sound Audio and Speech Processing
Progressively Growing Generative Adversarial Networks for High Resolution Semantic Segmentation of Satellite Images
Machine learning has proven to be useful in classification and segmentation of images.
Generative Adversarial User Model for Reinforcement Learning Based Recommendation System
There are great interests as well as many challenges in applying reinforcement learning (RL) to recommendation systems.
Generative Adversarial Network
Model-based Reinforcement Learning
+3
Learning Temporal Point Processes via Reinforcement Learning
Social goods, such as healthcare, smart city, and information networks, often produce ordered event data in continuous time.
PointNetGPD: Detecting Grasp Configurations from Point Sets
In this paper, we propose an end-to-end grasp evaluation model to address the challenging problem of localizing robot grasp configurations directly from the point cloud.
Robotics
Vision-based Teleoperation of Shadow Dexterous Hand using End-to-End Deep Neural Network
In this paper, we present TeachNet, a novel neural network architecture for intuitive and markerless vision-based teleoperation of dexterous robotic hands.
Robotics
Question-Guided Hybrid Convolution for Visual Question Answering
Most state-of-the-art VQA methods fuse the high-level textual and visual features from the neural network and abandon the visual spatial information when learning multi-modal features. To address these problems, question-guided kernels generated from the input question are designed to convolute with visual features for capturing the textual and visual relationship in the early stage.
Ranked #14 on
Visual Question Answering (VQA)
on CLEVR
Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification
As a result, the network learns latent representations of the face, torso and other body parts using the best available image patches from the entire video sequence.
Can Image Retrieval help Visual Saliency Detection?
We propose a novel image retrieval framework for visual saliency detection using information about salient objects contained within bounding box annotations for similar images.
Identity-Aware Textual-Visual Matching with Latent Co-attention
The stage-2 CNN-LSTM network refines the matching results with a latent co-attention mechanism.
Learning Feature Pyramids for Human Pose Estimation
We investigate our method on two standard benchmarks for human pose estimation.
Ranked #6 on
Pose Estimation
on Leeds Sports Poses
Fake News Mitigation via Point Process Based Intervention
We propose the first multistage intervention framework that tackles fake news in social networks by combining reinforcement learning with a point process network activity model.
Person Search with Natural Language Description
Searching persons in large-scale image databases with the query of natural language description has important applications in video surveillance.
Data-Driven Threshold Machine: Scan Statistics, Change-Point Detection, and Extreme Bandits
We present a novel distribution-free approach, the data-driven threshold machine (DTM), for a fundamental problem at the core of many learning tasks: choose a threshold for a given pre-specified level that bounds the tail probability of the maximum of a (possibly dependent but stationary) random sequence.
Joint Detection and Identification Feature Learning for Person Search
Existing person re-identification benchmarks and methods mainly focus on matching cropped pedestrian images between queries and candidates.
Ranked #9 on
Person Re-Identification
on CUHK03
Detecting weak changes in dynamic events over networks
Large volume of networked streaming event data are becoming increasingly available in a wide variety of applications, such as social network analysis, Internet traffic monitoring and healthcare analytics.
M-Statistic for Kernel Change-Point Detection
Detecting the emergence of an abrupt change-point is a classic problem in statistics and machine learning.
Efficient Learning of Continuous-Time Hidden Markov Models for Disease Progression
The Continuous-Time Hidden Markov Model (CT-HMM) is an attractive approach to modeling disease progression due to its ability to describe noisy observations arriving irregularly in time.
COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution
Information diffusion in online social networks is affected by the underlying network topology, but it also has the power to change it.
Scan $B$-Statistic for Kernel Change-Point Detection
A novel theoretical result of the paper is the characterization of the tail probability of these statistics using the change-of-measure technique, which focuses on characterizing the tail of the detection statistics rather than obtaining its asymptotic distribution under the null distribution.
