Search Results for author:
Found 191 papers, 65 papers with code
GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement
Object pose refinement is essential for robust object pose estimation.
Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction
Large language models (LLMs) have been driving a new wave of interactive AI applications across numerous domains.
AirShot: Efficient Few-Shot Detection for Autonomous Exploration
Few-shot object detection has drawn increasing attention in the field of robotic exploration, where robots are required to find unseen objects with a few online provided examples.
Salient Sparse Visual Odometry With Pose-Only Supervision
Visual Odometry (VO) is vital for the navigation of autonomous systems, providing accurate position and orientation estimates at reasonable costs.
Towards Pareto Optimal Throughput in Small Language Model Serving
Large language models (LLMs) have revolutionized the state-of-the-art of many different natural language processing tasks.
PhysORD: A Neuro-Symbolic Approach for Physics-infused Motion Prediction in Off-road Driving
To bridge this gap, we present PhysORD, a neural-symbolic approach integrating the conservation law, i. e., the Euler-Lagrange equation, into data-driven neural models for motion prediction in off-road driving.
Instruction-based Hypergraph Pretraining
However, the gap between training objectives and the discrepancy between data distributions in pretraining and downstream tasks hinders the transfer of the pretrained knowledge.
A Survey on Large Language Models from Concept to Implementation
Recent advancements in Large Language Models (LLMs), particularly those built on Transformer architectures, have significantly broadened the scope of natural language processing (NLP) applications, transcending their initial use in chatbot technology.
Neural Markov Random Field for Stereo Matching
Stereo matching is a core task for many computer vision and robotics applications.
BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation
We present BEHAVIOR-1K, a comprehensive simulation benchmark for human-centered robotics.
DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation
Imitation learning from human hand motion data presents a promising avenue for imbuing robots with human-like dexterity in real-world manipulation tasks.
Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models
We propose a novel method that utilizes the extensive knowledge contained within a large corpus of scientific literature to deduce causal relationships in general causal graph recovery tasks.
Confidence-aware Fine-tuning of Sequential Recommendation Systems via Conformal Prediction
Recognizing the critical role of confidence in aligning training objectives with evaluation metrics, we propose CPFT, a versatile framework that enhances recommendation confidence by integrating Conformal Prediction (CP)-based losses with CE loss during fine-tuning.
Review-Incorporated Model-Agnostic Profile Injection Attacks on Recommender Systems
Recent studies have shown that recommender systems (RSs) are highly vulnerable to data poisoning attacks.
Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models
In this work, we find that the insertion of even a short prefix to the prompt leads to the generation of outputs far away from factually correct answers.
OIL-AD: An Anomaly Detection Framework for Sequential Decision Sequences
Our offline learning model is an adaptation of behavioural cloning with a transformer policy network, where we modify the training process to learn a Q function and a state value function from normal trajectories.
Zero-shot sketch-based remote sensing image retrieval based on multi-level and attention-guided tokenization
To address this gap, our study introduces a novel zero-shot, sketch-based retrieval method for remote sensing images, leveraging multi-level feature extraction, self-attention-guided tokenization and filtering, and cross-modality attention update.
$\widetilde{O}(T^{-1})$ Convergence to (Coarse) Correlated Equilibria in Full-Information General-Sum Markov Games
No-regret learning has a long history of being closely connected to game theory.
KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph
Large language model (LLM) has achieved outstanding performance on various downstream tasks with its powerful natural language understanding and zero-shot capability, but LLM still suffers from knowledge limitation.
Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis
Motivated by the impressive open-set performance and content generation capabilities of web-scale, large-capacity pre-trained models (i. e., foundation models) in research fields such as Natural Language Processing (NLP) and Computer Vision (CV), we devote this survey to exploring (i) how these existing foundation models from NLP and CV can be applied to the field of robotics, and also exploring (ii) what a robotics-specific foundation model would look like.
Fine-tuning vision foundation model for crack segmentation in civil infrastructures
Two parameter-efficient fine-tuning methods, adapter and low-rank adaptation, are adopted to fine-tune the foundation model in semantic segmentation: the Segment Anything Model (SAM).
Multimodality-guided Image Style Transfer using Cross-modal GAN Inversion
Compared to IIST, such approaches provide more flexibility with text-specified styles, which are useful in scenarios where the style is hard to define with reference images.
iMatching: Imperative Correspondence Learning
Learning feature correspondence is a foundational task in computer vision, holding immense importance for downstream applications such as visual odometry and 3D reconstruction.
Online Anomaly Detection over Live Social Video Streaming
After that, we propose a novel model update scheme that incrementally maintains CLSTM and decoder.
Multi-view Graph Convolution for Participant Recommendation
Participant recommendation, a fundamental problem emerging together with GB, aims to find the participants for a launched group buying process with an initiator and a target item to increase the GB success rate.
Group-Aware Interest Disentangled Dual-Training for Personalized Recommendation
The users' group participation on social platforms reveals their interests and can be utilized as side information to mitigate the data sparsity and cold-start problem in recommender systems.
NOIR: Neural Signal Operated Intelligent Robots for Everyday Activities
We present Neural Signal Operated Intelligent Robots (NOIR), a general-purpose, intelligent brain-robot interface system that enables humans to command robots to perform everyday activities through brain signals.
Unified Pretraining for Recommendation via Task Hypergraphs
On the other hand, pretraining and finetuning on the same dataset leads to a high risk of overfitting.
Knowledge Graph Context-Enhanced Diversified Recommendation
Collectively, our contributions signify a substantial stride towards augmenting the panorama of recommendation diversity within the realm of KG-informed RecSys paradigms.
Learning to Optimise Climate Sensor Placement using a Transformer
In this paper, we introduce a novel sensor placement approach focused on learning improvement heuristics using deep reinforcement learning (RL) methods.
Collaborative Semantic Alignment in Recommendation Systems
However, PLMs often overlook the vital collaborative filtering signals, leading to challenges in merging collaborative and semantic representation spaces and fine-tuning semantic representations for better alignment with warm-start conditions.
Valuation Duration of the Stock Market
In contrast, at the height of the global financial crisis, more than 2. 2% of market value is from dividends in the next year, implying a duration of 46 years.
Geometry-Guided Ray Augmentation for Neural Surface Reconstruction with Sparse Views
In this paper, we propose a novel method for 3D scene and object reconstruction from sparse multi-view images.
AirIMU: Learning Uncertainty Propagation for Inertial Odometry
Accurate uncertainty estimation for inertial odometry is the foundation to achieve optimal fusion in multi-sensor systems, such as visual or LiDAR inertial odometry.
The Best Arm Evades: Near-optimal Multi-pass Streaming Lower Bounds for Pure Exploration in Multi-armed Bandits
Here, $n$ is the number of arms and $\Delta$ is the reward gap between the best and the second-best arms.
BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing
One is a cascaded approach where outputs (tokens or states) of a separately trained speech recognition system are used as inputs for LLMs, which limits their potential in modeling alignment between speech and text.
Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation
However, the challenges arise due to the high-dimensional action space of dexterous hand and complex compositional dynamics of the long-horizon tasks.
Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape
Animal3D consists of 3379 images collected from 40 mammal species, high-quality annotations of 26 keypoints, and importantly the pose and shape parameters of the SMAL model.
Ranked #1 on
Animal Pose Estimation
on Animal3D
Graph-based Alignment and Uniformity for Recommendation
To address this issue, we propose a novel approach, graph-based alignment and uniformity (GraphAU), that explicitly considers high-order connectivities in the user-item bipartite graph.
Group Identification via Transitional Hypergraph Convolution with Cross-view Self-supervised Learning
With the proliferation of social media, a growing number of users search for and join group activities in their daily life.
Estimating Effects of Long-Term Treatments
We describe the identification assumptions, the estimation strategies, and the inference technique under this framework.
StairNetV3: Depth-aware Stair Modeling using Deep Learning
Experiments on our dataset show that our method has a significant improvement over the previous best monocular vision method, with an intersection over union (IOU) increase of 3. 4 %, and the lightweight version has a fast detection speed and can meet the requirements of most real-time applications.
Digging into Depth Priors for Outdoor Neural Radiance Fields
However, the shape-radiance ambiguity of radiance fields remains a challenge, especially in the sparse viewpoints setting.
Primitive Skill-based Robot Learning from Human Evaluative Feedback
By combining them, SEED reduces the human effort required in RLHF and increases safety in training robot manipulation with RL in real-world settings.
SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
To address this limitation, we present Masked Multi-view with Swin Transformers (SwinMM), a novel multi-view pipeline for enabling accurate and data-efficient self-supervised medical image analysis.
FDCT: Fast Depth Completion for Transparent Objects
To address these challenges, we propose a Fast Depth Completion framework for Transparent objects (FDCT), which also benefits downstream tasks like object pose estimation.
VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
The composed value maps are then used in a model-based planning framework to zero-shot synthesize closed-loop robot trajectories with robustness to dynamic perturbations.
Multi-task Item-attribute Graph Pre-training for Strict Cold-start Item Recommendation
We explore the role of the fine-grained item attributes in bridging the gaps between the existing and the SCS items and pre-train a knowledgeable item-attribute graph for SCS item recommendation.
DreamEditor: Text-Driven 3D Scene Editing with Neural Fields
Neural fields have achieved impressive advancements in view synthesis and scene reconstruction.
Image Harmonization with Diffusion Model
In this paper, we present a novel approach for image harmonization by leveraging diffusion models.
iSLAM: Imperative SLAM
Simultaneous Localization and Mapping (SLAM) stands as one of the critical challenges in robot navigation.
Tight Regret Bounds for Single-pass Streaming Multi-armed Bandits
We first improve the regret lower bound to $\Omega(K^{1/3}T^{2/3})$ for algorithms with $o(K)$ memory, which matches the uniform exploration regret up to a logarithm factor in $T$.
PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas
Unlike generalizable radiance fields trained on perspective images, PanoGRF avoids the information loss from panorama-to-perspective conversion and directly aggregates geometry and appearance features of 3D sample points from each panoramic view based on spherical projection.
Trustworthy Sensor Fusion against Inaudible Command Attacks in Advanced Driver-Assistance System
As deep learning has been applied to increasingly sensitive tasks, uncertainty measurement is crucial in helping improve model robustness, especially in mission-critical scenarios.
CUEING: a lightweight model to Capture hUman attEntion In driviNG
Discrepancies in decision-making between Autonomous Driving Systems (ADS) and human drivers underscore the need for intuitive human gaze predictors to bridge this gap, thereby improving user trust and experience.
A Rational Model of Dimension-reduced Human Categorization
Humans tend to categorize objects based on a few key features.
Revolutionizing Agrifood Systems with Artificial Intelligence: A Survey
With the world population rapidly increasing, transforming our agrifood systems to be more productive, efficient, safe, and sustainable is crucial to mitigate potential food shortages.
Learned Focused Plenoptic Image Compression with Microimage Preprocessing and Global Attention
Also, it achieves 18. 73% bitrate saving and generates perceptually pleasant reconstructions compared to the state-of-the-art end-to-end image compression methods, which benefits the applications of focused plenoptic cameras greatly.
AirLoc: Object-based Indoor Relocalization
This results in a robust, accurate, and portable indoor relocalization system, which outperforms the state-of-the-art methods in room-level relocalization by 9. 5% of PR-AUC and 7% of accuracy.
HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation
In this paper, we focus on the problem of category-level object pose estimation, which is challenging due to the large intra-category shape variation.
VMesh: Hybrid Volume-Mesh Representation for Efficient View Synthesis
With the emergence of neural radiance fields (NeRFs), view synthesis quality has reached an unprecedented level.
Boundary Unlearning
In this paper, we refocus our attention from the parameter space to the decision space of the DNN model, and propose Boundary Unlearning, a rapid yet effective way to unlearn an entire class from a trained DNN model.
Assessing the strength of many instruments with the first-stage F and Cragg-Donald statistics
As for the Cragg-Donald statistic, we obtain an asymptotically valid correction in the case of two endogenous variables.
A specification test for the strength of instrumental variables
This paper develops a new specification test for the instrument weakness when the number of instruments $K_n$ is large with a magnitude comparable to the sample size $n$.
Emerging Synergies in Causality and Deep Generative Models: A Survey
In the field of artificial intelligence (AI), the quest to understand and model data-generating processes (DGPs) is of paramount importance.
Benchmarking Robustness in Neural Radiance Fields
We find that NeRF-based models are significantly degraded in the presence of corruption, and are more sensitive to a different set of corruptions than image recognition models.
Boundary Unlearning: Rapid Forgetting of Deep Networks via Shifting the Decision Boundary
In this paper, we refocus our attention from the parameter space to the decision space of the DNN model, and propose Boundary Unlearning, a rapid yet effective way to unlearn an entire class from a trained DNN model.
NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modeling
This design shares computation within each group, in the spatial and temporal dimensions, resulting in reduced encoding time of the video.
RGB-D-based Stair Detection using Deep Learning for Autonomous Stair Climbing
Specifically, we design a selective module, which can make the network learn the complementary relationship between the RGB map and the depth map and effectively combine the information from the RGB map and the depth map in different scenes.
Ranking-based Group Identification via Factorized Attention on Social Tripartite Graph
PA layers efficiently learn the relatedness of non-neighbor nodes to improve the information propagation to users.
Sequential Recommendation with Auxiliary Item Relationships via Multi-Relational Transformer
However, it remains a significant challenge to model auxiliary item relationships in SR. To simultaneously model high-order item-item transitions in sequences and auxiliary item relationships, we propose a Multi-relational Transformer capable of modeling auxiliary item relationships for SR (MT4SR).
Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation
Existing zero-shot methods fail to align the two modalities of speech and text into a shared semantic space, resulting in much worse performance compared to the supervised ST methods.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Requirements Engineering for Machine Learning: A Review and Reflection
Today, many industrial processes are undergoing digital transformation, which often requires the integration of well-understood domain models and state-of-the-art machine learning technology in business processes.
NeRF-Loc: Transformer-Based Object Localization Within Neural Radiance Fields
Using current NeRF training tools, a robot can train a NeRF environment model in real-time and, using our algorithm, identify 3D bounding boxes of objects of interest within the NeRF for downstream navigation or manipulation tasks.
Multi-level Explanation of Deep Reinforcement Learning-based Scheduling
Dependency-aware job scheduling in the cluster is NP-hard.
StructNeRF: Neural Radiance Fields for Indoor Scenes with Structural Hints
Neural Radiance Fields (NeRF) achieve photo-realistic view synthesis with densely captured input images.
An Improved Ray Tracing Acceleration Algorithm Based on Bounding Volume Hierarchies
Ray tracing is an efficient channel modeling method.
Learning to Infer Counterfactuals: Meta-Learning for Estimating Multiple Imbalanced Treatment Effects
We regularly consider answering counterfactual questions in practice, such as "Would people with diabetes take a turn for the better had they choose another medication?".
Contrastive Counterfactual Learning for Causality-aware Interpretable Recommender Systems
Recognizing that confounders may be elusive, we propose a contrastive self-supervised learning to minimize exposure bias, employing inverse propensity scores and expanding the positive sample set.
GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning
Specifically, we outperform the state of the art by 7% on UCF and 4% on HMDB for video retrieval, and 5% on UCF and 6% on HMDB for video classification
AGENT: An Adaptive Grouping Entrapping Method of Flocking Systems
This study proposes a distributed algorithm that makes agents' adaptive grouping entrap multiple targets via automatic decision making, smooth flocking, and well-distributed entrapping.
DeepPortraitDrawing: Generating Human Body Images from Freehand Sketches
Researchers have explored various ways to generate realistic images from freehand sketches, e. g., for objects and human faces.
Prediction and Control of Focal Seizure Spread: Random Walk with Restart on Heterogeneous Brain Networks
In this study, we used a whole-brain model to show that heterogeneity in nodal excitability had a significant impact on seizure propagation in the networks, and compromised the prediction accuracy with structural connections.
Off-Policy Evaluation with Online Adaptation for Robot Exploration in Challenging Environments
To the best of our knowledge, this work for the first time demonstrates value function prediction on real-world dataset for robot exploration in challenging subterranean and urban environments.
Revisiting Neighborhood-based Link Prediction for Collaborative Filtering
While there is a rich literature of such works using advanced models for learning user and item representations separately, item recommendation is essentially a link prediction problem between users and items.
Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective
The stereo contrastive feature loss function explicitly constrains the consistency between learned features of matching pixel pairs which are observations of the same 3D points.
Pursuit-evasion differential games of players with different speeds in spaces of different dimensions
We study pursuit-evasion differential games between a faster pursuer moving in 3D space and an evader moving in a plane.
Identifying Oscillations Injected by Inverter-Based Solar Energy Sources
This new mode was recognized from the analysis of real-world ambient synchrophasor and point-of-wave data.
SADN: Learned Light Field Image Compression with Spatial-Angular Decorrelation
Light field image becomes one of the most promising media types for immersive video applications.
Large-scale Personalized Video Game Recommendation via Social-aware Contextualized Graph Neural Network
We conduct a comprehensive analysis of users' online game behaviors, which motivates the necessity of handling those three characteristics in the online game recommendation.
EVBattery: A Large-Scale Electric Vehicle Dataset for Battery Health and Capacity Estimation
In addition to demonstrating how existing deep learning algorithms can be applied to this task, we further develop an algorithm that exploits the data structure of battery systems.
Deep Leaning-Based Ultra-Fast Stair Detection
Staircases are some of the most common building structures in urban environments.
AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration
Few-shot object detection has attracted increasing attention and rapidly progressed in recent years.
NeRF-SR: High-Quality Neural Radiance Fields using Supersampling
We present NeRF-SR, a solution for high-resolution (HR) novel view synthesis with mostly low-resolution (LR) inputs.
AirObject: A Temporally Evolving Graph Embedding for Object Identification
In this context, we propose a novel temporal 3D object encoding approach, dubbed AirObject, to obtain global keypoint graph-based embeddings of objects.
Unsupervised Online Learning for Robotic Interestingness with Visual Memory
Instead, we propose to develop a method that automatically adapts online to the environment to report interesting scenes quickly.
Pre-training Graph Neural Network for Cross Domain Recommendation
Then, we transfer the pre-trained graph encoder to initialize the node embeddings on the target domain, which benefits the fine-tuning of the single domain recommender system on the target domain.
Cycle-Balanced Representation Learning For Counterfactual Inference
With the widespread accumulation of observational data, researchers obtain a new direction to learn counterfactual effects in many domains (e. g., health care and computational advertising) without Randomized Controlled Trials(RCTs).
Pseudo Supervised Monocular Depth Estimation with Teacher-Student Network
Despite recent improvement of supervised monocular depth estimation, the lack of high quality pixel-wise ground truth annotations has become a major hurdle for further progress.
Deep Fraud Detection on Non-attributed Graph
The successes of most previous methods heavily rely on rich node features and high-fidelity labels.
Sublinear Time and Space Algorithms for Correlation Clustering via Sparse-Dense Decompositions
We present a new approach for solving (minimum disagreement) correlation clustering that results in sublinear algorithms with highly efficient time and space complexity for this problem.
AirDOS: Dynamic SLAM benefits from Articulated Objects
To the best of our knowledge, AirDOS is the first dynamic object-aware SLAM system demonstrating that camera pose estimation can be improved by incorporating dynamic articulated objects.
Single Person Pose Estimation: A Survey
Human pose estimation in unconstrained images and videos is a fundamental computer vision task.
Low-resolution Human Pose Estimation
Human pose estimation has achieved significant progress on images with high imaging resolution.
AirLoop: Lifelong Loop Closure Detection
Nevertheless, simply finetuning the model on new data is infeasible since it may cause the model's performance on previously learned data to degrade over time, which is also known as the problem of catastrophic forgetting.
Blockchain-based Trustworthy Federated Learning Architecture
To enhance the accountability and fairness of federated learning systems, we present a blockchain-based trustworthy federated learning architecture.
Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration
Our method co-optimizes a human policy and a robot policy in an interactive learning process: the human policy learns to generate diverse and plausible collaborative behaviors from demonstrations while the robot policy learns to assist by estimating the unobserved latent strategy of its human collaborator.
What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
Based on the study, we derive a series of lessons including the sensitivity to different algorithmic design choices, the dependence on the quality of the demonstrations, and the variability based on the stopping criteria due to the different objectives in training and evaluation.
Interpreting Depression From Question-wise Long-term Video Recording of SDS Evaluation
To automatically interpret depression from the SDS evaluation and the paired video, we propose an end-to-end hierarchical framework for the long-term variable-length video, which is also conditioned on the questionnaire results and the answering time.
Learning Implicit Glyph Shape Representation
In this paper, we present a novel implicit glyph shape representation, which models glyphs as shape primitives enclosed by quadratic curves, and naturally enables generating glyph images at arbitrary high resolutions.
Spatial-temporal Conv-sequence Learning with Accident Encoding for Traffic Flow Prediction
In an intelligent transportation system, the key problem of traffic forecasting is how to extract periodic temporal dependencies and complex spatial correlations.
De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks
The results demonstrate that De-Pois is effective and efficient for detecting poisoned data against all the four types of poisoning attacks, with both the accuracy and F1-score over 0. 9 on average.
Robust Sensor Fusion Algorithms Against Voice Command Attacks in Autonomous Vehicles
This technology enables drivers to use voice commands to control the vehicle and will be soon available in Advanced Driver Assistance Systems (ADAS).
Few-Shot Meta-Learning on Point Cloud for Semantic Segmentation
With a good understanding of environmental information, construction robots can work better.
Leveraging a Joint of Phenotypic and Genetic Features on Cancer Patient Subgrouping
Cancer is responsible for millions of deaths worldwide every year.
Decentralized Circle Formation Control for Fish-like Robots in the Real-world via Reinforcement Learning
In this paper, the circle formation control problem is addressed for a group of cooperative underactuated fish-like robots involving unknown nonlinear dynamics and disturbances.
Human-Understandable Decision Making for Visual Recognition
The widespread use of deep neural networks has achieved substantial success in many tasks.
A parametric congruence motivated by Orr's identity
For any $m, n\in\mathbb{N}=\{0, 1, 2\ldots\}$, the truncated hypergeometric series ${}_{m+1}F_m$ is defined by $$ {}_{m+1}F_m\bigg[\begin{matrix}x_0&x_1&\ldots&x_m\\ &y_1&\ldots&y_m\end{matrix}\bigg|z\bigg]_n=\sum_{k=0}^n\frac{(x_0)_k(x_1)_k\cdots(x_m)_k}{(y_1)_k\cdots(y_m)_k}\cdot\frac{z^k}{k!
Number Theory Combinatorics 11A07, 33C20, 11B65, 05A10
Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control
Key to such capability is hand-eye coordination, a cognitive ability that enables humans to adaptively direct their movements at task-relevant objects and be invariant to the objects' absolute spatial location.
Learning Purified Feature Representations from Task-irrelevant Labels
Learning an empirically effective model with generalization using limited data is a challenging task for deep neural networks.
ScalingNet: extracting features from raw EEG data for emotion recognition
Convolutional Neural Networks(CNNs) has achieved remarkable performance breakthrough in a variety of tasks.
Lookup subnet based Spatial Graph Convolutional neural Network
Convolutional Neural Networks(CNNs) has achieved remarkable performance breakthrough in Euclidean structure data.
SwingBot: Learning Physical Features from In-hand Tactile Exploration for Dynamic Swing-up Manipulation
We present SwingBot, a robot that is able to learn the physical features of a held object through tactile exploration.
An Improved Level Set Method for Reachability Problems in Differential Games
The reachable tube is described as a sublevel set of a value function, which is the viscosity solution of a Hamilton-Jacobi equation with running cost.
Comparisons of Graph Neural Networks on Cancer Classification Leveraging a Joint of Phenotypic and Genetic Features
We applied and compared eight GNN models including AGNN, ChebNet, GAT, GCN, GIN, GraphSAGE, SGC, and TAGCN on the Mayo Clinic cancer disease dataset and assessedtheir performance as well as compared them with each other and with more conventional machinelearning models such as decision tree, gradient boosting, multi-layer perceptron, naive bayes, andrandom forest which we used as the baselines.
Architectural Patterns for the Design of Federated Learning Systems
Therefore, in this paper, we present a collection of architectural patterns to deal with the design challenges of federated learning systems.
FSV: Learning to Factorize Soft Value Function for Cooperative Multi-Agent Reinforcement Learning
We explore energy-based solutions for cooperative multi-agent reinforcement learning (MARL) using the idea of function factorization in centralized training with decentralized execution (CTDE).
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Bridging Graph Network to Lifelong Learning with Feature Interaction
In this paper, we aim to bridge GNN to lifelong learning, which is to overcome the effect of ``catastrophic forgetting" for continuously learning a sequence of graph-structured tasks.
Federated Unlearning
In this paper, we take the first step to fill this gap by presenting FedEraser, the first federated unlearning methodology that can eliminate the influence of a federated client's data on the global FL model while significantly reducing the time used for constructing the unlearned FL model. The basic idea of FedEraser is to trade the central server's storage for unlearned model's construction time, where FedEraser reconstructs the unlearned model by leveraging the historical parameter updates of federated clients that have been retained at the central server during the training process of FL.
Distances to molecular clouds in the second Galactic quadrant
We present distances to 76 medium-sized molecular clouds and an extra large-scale one in the second Galactic quadrant ($104. 75^\circ <l<150. 25^\circ $ and $|b|<5. 25^\circ$), 73 of which are accurately measured for the first time.
Astrophysics of Galaxies
Schema Extraction on Semi-structured Data
The schemas obtained by the structural methods are more interpretable, and the statistical methods have better applicability and generalization ability.
Congruences concerning generalized central trinomial coefficients
For any $n\in\mathbb{N}=\{0, 1, 2,\ldots\}$ and $b, c\in\mathbb{Z}$, the generalized central trinomial coefficient $T_n(b, c)$ denotes the coefficient of $x^n$ in the expansion of $(x^2+bx+c)^n$.
Number Theory Combinatorics 11A07, 11B75, 11B65, 05A10
Spin-Wave Doppler Shift by Magnon Drag in Magnetic Insulators
The Doppler shift of the quasiparticle dispersion by charge currents is responsible for the critical supercurrents in superconductors and instabilities of the magnetic ground state of metallic ferromagnets.
Mesoscale and Nanoscale Physics
Object-centered image stitching
Image stitching is typically decomposed into three phases: registration, which aligns the source images with a common target image; seam finding, which determines for each target pixel the source image it should come from; and blending, which smooths transitions over the seams.
Robust image stitching with multiple registrations
Here, we observe that the use of a single registration often leads to errors, especially in scenes with significant depth variation or object motion.
Time Series Data Imputation: A Survey on Deep Learning Approaches
Time series methods based on deep learning have made progress with the usage of models like RNN, since it captures time information from data.
HMFlow: Hybrid Matching Optical Flow Network for Small and Fast-Moving Objects
To address this problem, we introduce a lightweight but effective Global Matching Component (GMC) to grab global matching features.
On the Global Self-attention Mechanism for Graph Convolutional Networks
Applying Global Self-attention (GSA) mechanism over features has achieved remarkable success on Convolutional Neural Networks (CNNs).
Can Steering Wheel Detect Your Driving Fatigue?
In this paper, we propose a novel driver fatigue detection method by embedding surface electromyography (sEMG) sensors on a steering wheel.
Attn-HybridNet: Improving Discriminability of Hybrid Features with Attention Fusion
The principal component analysis network (PCANet) is an unsupervised parsimonious deep network, utilizing principal components as filters in its convolution layers.
Lifelong Graph Learning
In this paper, we bridge GNN and lifelong learning by converting a continual graph learning problem to a regular graph learning problem so GNN can inherit the lifelong learning techniques developed for convolutional neural networks (CNN).
The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)
This report summarizes the results of the first edition of the challenge together with the findings of the participants.
Online Visual Place Recognition via Saliency Re-identification
As an essential component of visual simultaneous localization and mapping (SLAM), place recognition is crucial for robot navigation and autonomous driving.
A Systematic Literature Review on Federated Machine Learning: From A Software Engineering Perspective
Federated learning is an emerging machine learning paradigm where clients train models locally and formulate a global model based on the local model updates.
MSA-MIL: A deep residual multiple instance learning model based on multi-scale annotation for classification and visualization of glomerular spikes
Therefore, the proposed model can provide a good foundation for assisting the clinical doctors to diagnose the glomerular membranous nephropathy.
Multi-Agent Reinforcement Learning in a Realistic Limit Order Book Market Simulation
Optimal order execution is widely studied by industry practitioners and academic researchers because it determines the profitability of investment decisions and high-level trading strategies, particularly those involving large volumes of orders.
Visual Memorability for Robotic Interestingness via Unsupervised Online Learning
In this paper, we explore the problem of interesting scene prediction for mobile robots.
Supervised Contrastive Learning
Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training of deep image models.
Ranked #2 on
Class Incremental Learning
on cifar100
Safe deep reinforcement learning-based constrained optimal control scheme for active distribution networks
In this scheme, the optimal voltage control problem is formulated as a constrained Markov decision process, in which both state and action spaces are continuous.
Exploration with Limited Memory: Streaming Algorithms for Coin Tossing, Noisy Comparisons, and Multi-Armed Bandits
In particular, algorithms with optimal sample complexity (number of coin tosses) have been known for this problem for quite some time.
TartanAir: A Dataset to Push the Limits of Visual SLAM
We present a challenging dataset, the TartanAir, for robot navigation task and more.
Robotics
Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection
Loop closure detection is an essential and challenging problem in simultaneous localization and mapping (SLAM).
Cooperative Pursuit with Multi-Pursuer and One Faster Free-moving Evader
When the faster evader is allowed to move freely without any constraint, the main issues are how to form an encirclement to trap the evader into the capture domain, how to balance between forming an encirclement and approaching the faster evader, and what conditions make the capture possible.
Systems and Control Systems and Control
Fully Dense Neural Network for the Automatic Modulation Recognition
Nowadays, we mainly use various convolution neural network (CNN) structures to extract features from radio data or spectrogram in AMR.
Kernel learning for visual perception
To this end, the novel kernel learning methods for several basic visual perceptual tasks, including object tracking, localization, mapping, and image recognition, are proposed and demonstrated both theoretically and practically.
Transferable Force-Torque Dynamics Model for Peg-in-hole Task
We present a learning-based force-torque dynamics to achieve model-based control for contact-rich peg-in-hole task using force-only inputs.
SAG-VAE: End-to-end Joint Inference of Data Representations and Feature Relations
Variational Autoencoders (VAEs) are powerful in data representation inference, but it cannot learn relations between features with its vanilla form and common variations.
Platoon trajectories generation: A unidirectional interconnected LSTM-based car following model
However, the traffic micro-simulation accuracy of car following models in a platoon level, especially during traffic oscillations, still needs to be enhanced.
6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
We present 6-PACK, a deep learning approach to category-level 6D object pose tracking on RGB-D data.
Ranked #1 on
6D Pose Estimation using RGBD
on REAL275
(Rerr metric)
Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
By shedding light on the promise and challenges, we hope our work can rekindle the conversation on workflows for data sharing.
A Radio Signal Modulation Recognition Algorithm Based on Residual Networks and Attention Mechanisms
To solve the problem of inaccurate recognition of types of communication signal modulation, a RNN neural network recognition algorithm combining residual block network with attention mechanism is proposed.
RAUNet: Residual Attention U-Net for Semantic Segmentation of Cataract Surgical Instruments
To the best of our knowledge, this is the first cataract surgical instrument dataset for semantic segmentation.
FfDL : A Flexible Multi-tenant Deep Learning Platform
This paper describes the design, implementation and our experiences with FfDL, a DL platform used at IBM.
Adaptive Ensemble of Classifiers with Regularization for Imbalanced Data Classification
In addition, the proposed method has other preferred properties such as special advantages in dealing with highly imbalanced data, and it pioneers the research on the regularization for dynamic ensemble methods.
Imbalance-XGBoost: Leveraging Weighted and Focal Losses for Binary Label-Imbalanced Classification with XGBoost
The paper presents Imbalance-XGBoost, a Python package that combines the powerful XGBoost software with weighted and focal losses to tackle binary label-imbalanced classification tasks.
Spearphone: A Speech Privacy Exploit via Accelerometer-Sensed Reverberations from Smartphone Loudspeakers
In this paper, we build a speech privacy attack that exploits speech reverberations generated from a smartphone's inbuilt loudspeaker captured via a zero-permission motion sensor (accelerometer).
Cryptography and Security
Multi-layer Attention Mechanism for Speech Keyword Recognition
The key idea is that, in addition to the conventional attention mechanism, information of layers prior to feature extraction and LSTM are introduced into attention weights calculations.
Ranked #4 on
Keyword Spotting
on Google Speech Commands
(Google Speech Commands V2 20 metric)
Memetic EDA-Based Approaches to Comprehensive Quality-Aware Automated Semantic Web Service Composition
The objective of this problem is to find a solution with optimized or near-optimized overall QoS and QoSM within polynomial time over a service request.
Kervolutional Neural Networks
Convolutional neural networks (CNNs) have enabled the state-of-the-art performance in many computer vision tasks.
Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
Based on this observation, we propose a defense approach which inspects the graph and recovers the potential adversarial perturbations.
Evolutionary Multitasking for Semantic Web Service Composition
We also found that the use of the proper neighborhood structure can enhance the effectiveness of our approach.
WaveletAE: A Wavelet-enhanced Autoencoder for Wind Turbine Blade Icing Detection
Quick detection of blade ice accretion is crucial for the maintenance of wind farms.
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
A key technical challenge in performing 6D object pose estimation from RGB-D image is to fully leverage the two complementary data sources.
Ranked #4 on
6D Pose Estimation
on LineMOD
Fast and Globally Optimal Rigid Registration of 3D Point Sets by Transformation Decomposition
However, the existing global methods are slow for two main reasons: the computational complexity of BnB is exponential to the problem dimensionality (which is six for 3D rigid registration), and the bound evaluation used in BnB is inefficient.
Model-free Approach for Sensor Network Localization with Noisy Distance Measurement
In addition, different from the traditional filter-based localization methods which need kinetic model for localization, our proposed method is model-free and converts the localization problem to graph optimization problem.
Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search
Three-dimensional rigid point cloud registration has many applications in computer vision and robotics.
Scalar Quantization as Sparse Least Square Optimization
Furthermore, to compute quantization results with a given amount of values/clusters, this paper designed an iterative method and a clustering-based method, and both of them are built on sparse least square.
Graph Optimization Approach to Range-based Localization
In this paper, we propose a general graph optimization based framework for localization, which can accommodate different types of measurements with varying measurement time intervals.
Robotics
Correlation Flow: Robust Optical Flow Using Kernel Cross-Correlators
Robust velocity and position estimation is crucial for autonomous robot navigation.
Robust Propensity Score Computation Method based on Machine Learning with Label-corrupted Data
The experimental results illustrate that xgboost propensity scores computing with the data processed by our method could outperform the same method with original data, and the advantages of our method increases as we add some artificial corruptions to the dataset.
TRL: Discriminative Hints for Scalable Reverse Curriculum Learning
However, tasks with sparse rewards remain challenging when the state space is large.
Fine-grained Pattern Matching Over Streaming Time Series
Hence, we formulate a new problem, called "fine-grained pattern matching", which allows users to specify varied granularities of matching deviation to different segments of a given pattern, and fuzzy regions for adaptive breakpoints determination between consecutive segments.
Non-iterative SLAM for Warehouse Robots Using Ground Textures
We present a novel visual SLAM method for the warehouse robot with a single downward-facing camera using ground textures.
Robotics
Ultra-Wideband Aided Fast Localization and Mapping System
This paper proposes an ultra-wideband (UWB) aided localization and mapping system that leverages on inertial sensor and depth camera.
Robotics
Interpreting Shared Deep Learning Models via Explicable Boundary Trees
In this paper, we propose a method to disclose a small set of training data that is just sufficient for users to get the insight of a complicated model.
Kernel Cross-Correlator
Cross-correlator plays a significant role in many visual perception tasks, such as object detection and tracking.
A discriminative view of MRF pre-processing algorithms
While Markov Random Fields (MRFs) are widely used in computer vision, they present a quite challenging inference problem.
Relaxation-Based Preprocessing Techniques for Markov Random Field Inference
Markov Random Fields (MRFs) are a widely used graphical model, but the inference problem is NP-hard.
Improving Raw Image Storage Efficiency by Exploiting Similarity
To improve the temporal and spatial storage efficiency, researchers have intensively studied various techniques, including compression and deduplication.
Semantic Object Segmentation via Detection in Weakly Labeled Video
Semantic object segmentation in video is an important step for large-scale multimedia analysis.
A Primal-Dual Algorithm for Higher-Order Multilabel Markov Random Fields
Graph cuts method such as a-expansion [4] and fusion moves [22] have been successful at solving many optimization problems in computer vision.
