Search Results for author:
Found 96 papers, 38 papers with code
n-Reference Transfer Learning for Saliency Prediction
The proposed framework is gradient-based and model-agnostic.
Beyond Average: Individualized Visual Scanpath Prediction
Understanding how attention varies across individuals has significant scientific and societal impacts.
Heuristic Solution to Joint Deployment and Beamforming Design for STAR-RIS Aided Networks
This paper tackles the deployment challenges of Simultaneous Transmitting and Reflecting Reconfigurable Intelligent Surface (STAR-RIS) in communication systems.
PNeRV: Enhancing Spatial Consistency via Pyramidal Neural Representation for Videos
To address this issue, we introduce the Pyramidal Neural Representation for Videos (PNeRV), which is built on a multi-scale information connection and comprises a lightweight rescaling operator, Kronecker Fully-connected layer (KFc), and a Benign Selective Memory (BSM) mechanism.
Invisible Gas Detection: An RGB-Thermal Cross Attention Network and A New Benchmark
The widespread use of various chemical gases in industrial processes necessitates effective measures to prevent their leakage during transportation and storage, given their high toxicity.
SwitchTab: Switched Autoencoders Are Effective Tabular Learners
Self-supervised representation learning methods have achieved significant success in computer vision and natural language processing, where data samples exhibit explicit spatial or semantic dependencies.
Vamos: Versatile Action Models for Video Understanding
What makes good video representations for video understanding, such as anticipating future activities, or answering video-conditioned questions?
OV-VG: A Benchmark for Open-Vocabulary Visual Grounding
While current foundational models excel at various visual language tasks, there's a noticeable absence of models specifically tailored for open-vocabulary visual grounding.
What Do Deep Saliency Models Learn about Visual Attention?
In recent years, deep saliency models have made significant progress in predicting human visual attention.
Distributed Evolution Strategies with Multi-Level Learning for Large-Scale Black-Box Optimization
In the post-Moore era, main performance gains of black-box optimizers are increasingly depending on parallelism, especially for large-scale optimization (LSO).
Deep Reinforcement Learning Enabled Joint Deployment and Beamforming in STAR-RIS Assisted Networks
The paper constructs a STAR-RIS assisted multi-user multiple-input single-output (MU-MISO) mobile wireless network and jointly optimizes the dynamic deployment strategy of STAR-RIS and the hybrid beamforming strategy to maximize the long-term total communication rate of users.
AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
We propose to formulate the LTA task from two perspectives: a bottom-up approach that predicts the next actions autoregressively by modeling temporal dynamics; and a top-down approach that infers the goal of the actor and plans the needed procedure to accomplish the goal.
Iterative Robust Visual Grounding with Masked Reference based Centerpoint Supervision
The proposed framework is evaluated on five regular VG datasets and two newly constructed robust VG datasets.
Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review
We first introduce some preliminary knowledge for the change detection task, such as problem definition, datasets, evaluation metrics, and transformer basics, as well as provide a detailed taxonomy of existing algorithms from three different perspectives: algorithm granularity, supervision modes, and learning frameworks in the methodology section.
DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos
DNeRV achieves competitive results against the state-of-the-art neural compression approaches and outperforms existing implicit methods on downstream inpainting and interpolation for $960 \times 1920$ videos.
Cooperative Coevolution for Non-Separable Large-Scale Black-Box Optimization: Convergence Analyses and Distributed Accelerations
Given the ubiquity of non-separable optimization problems in real worlds, in this paper we analyze and extend the large-scale version of the well-known cooperative coevolution (CC), a divide-and-conquer black-box optimization framework, on non-separable functions.
Divide and Conquer: Answering Questions with Object Factorization and Compositional Reasoning
They have yet to develop the capability to address novel objects or spurious biases in real-world scenarios, and also fall short of interpreting the rationales behind their decisions.
Automated Design of Metaheuristic Algorithms: A Survey
Metaheuristics have gained great success in academia and practice because their search logic can be applied to any problem with available solution representation, solution quality evaluation, and certain notions of locality.
AutoOptLib: Tailoring Metaheuristic Optimizers via Automated Algorithm Design
In response, this paper proposes AutoOptLib, the first platform for accessible automated design of metaheuristic optimizers.
Self-Training Guided Disentangled Adaptation for Cross-Domain Remote Sensing Image Semantic Segmentation
We first propose source student backbone and target student backbone to respectively extract the source-style and target-style feature for both source and target images.
Toward Multi-Granularity Decision-Making: Explicit Visual Reasoning with Hierarchical Knowledge
Answering visual questions requires the ability to parse visual observations and correlate them with a variety of knowledge.
PyPop7: A Pure-Python Library for Population-Based Black-Box Optimization
In this paper, we present a pure-Python library called PyPop7 for black-box optimization (BBO).
Improved Pump Setpoint Selection Using a Calibrated Hydraulic Model of a High-Pressure Irrigation System
This paper presents a case study of the operational management of the Robinvale high-pressure piped irrigation water delivery system (RVHPS) in Australia.
Look in Different Views: Multi-Scheme Regression Guided Cell Instance Segmentation
On the DSB2018 and CA2. 5, our network surpasses previous methods by 1. 2% (AP50).
MMOTU: A Multi-Modality Ovarian Tumor Ultrasound Image Dataset for Unsupervised Cross-Domain Semantic Segmentation
To solve this problem, we propose a Multi-Modality Ovarian Tumor Ultrasound (MMOTU) image dataset containing 1469 2d ultrasound images and 170 contrast enhanced ultrasonography (CEUS) images with pixel-wise and global-wise annotations.
Attention in Reasoning: Dataset, Analysis, and Modeling
In this work, we propose an Attention with Reasoning capability (AiR) framework that uses attention to understand and improve the process leading to task outcomes.
Efficient and practical quantum compiler towards multi-qubit systems with deep reinforcement learning
We systematically evaluate the performance of our proposal in compiling quantum operators with both inverse-closed and inverse-free universal basis sets.
AutoOpt: A General Framework for Automatically Designing Metaheuristic Optimization Algorithms with Diverse Structures
However, the specific algorithm prototype and linear algorithm representation in the current automated design pipeline restrict the design within a fixed algorithm structure, which hinders discovering novelties and diversity across the metaheuristic family.
Artificial Intelligence Enables Real-Time and Intuitive Control of Prostheses via Nerve Interface
Objective: The next generation prosthetic hand that moves and feels like a real hand requires a robust neural interconnection between the human minds and machines.
REX: Reasoning-aware and Grounded Explanation
Finally, with our new data and method, we perform extensive analyses to study the effectiveness of our explanation under different settings, including multi-task learning and transfer learning.
Ranked #2 on
Explanatory Visual Question Answering
on GQA-REX
Speckle-based optical cryptosystem and its application for human face recognition via deep learning
A scattering ground glass is exploited to generate physical secret keys of gigabit length and encrypt face images via seemingly random optical speckles at light speed.
Learning to Predict Gradients for Semi-Supervised Continual Learning
To explore these issues, we formulate a new semi-supervised continual learning method, which can be generically applied to existing continual learning models.
Learning to Minimize the Remainder in Supervised Learning
To this end, we propose a new learning approach, namely gradient adjustment learning (GAL), to leverage the knowledge learned from the past training iterations to adjust vanilla gradients, such that the remainders are minimized and the approximations are improved.
VisualHow: Multimodal Problem Solving
With an overarching goal of developing intelligent systems to assist humans in various daily activities, we propose VisualHow, a free-form and open-ended research that focuses on understanding a real-life problem and deriving its solution by incorporating key components across multiple modalities.
Query and Attention Augmentation for Knowledge-Based Explainable Reasoning
Explainable visual question answering (VQA) models have been developed with neural modules and query-based knowledge incorporation to answer knowledge-requiring questions.
NN-Baker: A Neural-network Infused Algorithmic Framework for Optimization Problems on Geometric Intersection Graphs
This leads to a mixed algorithmic-ML framework, which we call NN-Baker that has the capacity to approximately solve a family of graph optimization problems (e. g, maximum independent set and minimum vertex cover) in time linear to input graph size, and only polynomial to approximation parameter.
Attention-based Feature Decomposition-Reconstruction Network for Scene Text Detection
In this paper, we propose attention-based feature decomposition-reconstruction network for scene text detection, which utilizes contextual information and low-level feature to enhance the performance of segmentation-based text detector.
ezcox: An R/CRAN Package for Cox Model Batch Processing and Visualization
Cox analysis is a common clinical data analysis technique to link valuable variables to clinical outcomes including dead and relapse.
A Feature Consistency Driven Attention Erasing Network for Fine-Grained Image Retrieval
To handle these two issues, we propose a feature consistency driven attention erasing network (FCAENet) for fine-grained image retrieval.
Learning to Predict Trustworthiness with Steep Slope Loss
Secondly, due to the data complexity, it is challenging to differentiate the incorrect predictions from the correct ones on real-world large-scale datasets.
Hybrid Beamforming for RIS-Aided Communications: Fitness Landscape Analysis and Niching Genetic Algorithm
To investigate the number and distribution of local optima, we conduct a fitness landscape analysis on the sum rate maximization problems.
Empirical Study of Named Entity Recognition Performance Using Distribution-aware Word Embedding
And the result shows that the performance of NER will be improved if the word specificity is incorporated into existing NER methods.
TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios
Object detection on drone-captured scenarios is a recent popular task.
Leveraging Human Attention in Novel Object Captioning
Image captioning models depend on training with paired image-text corpora, which poses various challenges in describing images containing novel objects absent from the training data.
A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation
To deal with the above two issues, we propose self-distillation embedded supervised affinity attention model to improve the performance of few-shot segmentation task.
Explicit Knowledge Incorporation for Visual Reasoning
Existing explainable and explicit visual reasoning methods only perform reasoning based on visual evidence but do not take into account knowledge beyond what is in the visual scene.
Predicting Human Scanpaths in Visual Question Answering
Conditioned on a task guidance map, the proposed model learns question-specific attention patterns to generate scanpaths.
Multiobjective Bilevel Evolutionary Approach for Off-Grid Direction-of-Arrival Estimation
We formulate a multiobjective off-grid DOA estimation model to realize this idea, by which the source number can be automatically identified together with DOA estimation.
Evolutionary Robust Clustering Over Time for Temporal Data
In many clustering scenes, data samples' attribute values change over time.
Gridless Evolutionary Approach for Line Spectral Estimation with Unknown Model Order
To overcome the above shortcomings of relaxation, we propose a novel idea of simultaneously estimating the frequencies and model order by means of the atomic $l_0$ norm.
Embedded Self-Distillation in Compact Multi-Branch Ensemble Network for Remote Sensing Scene Classification
On this issue, we embed self-distillation (SD) method to transfer knowledge from ensemble network to main-branch in it.
A Portable, Self-Contained Neuroprosthetic Hand with Deep Learning-Based Finger Control
This enables the implementation of the neuroprosthetic hand as a portable and self-contained unit with real-time control of individual finger movements.
BreakingBED -- Breaking Binary and Efficient Deep Neural Networks by Adversarial Attacks
The distilled models exhibit their strength against all white box attacks with an exception of C&W.
Embedded Knowledge Distillation in Depth-Level Dynamic Neural Network
In real applications, different computation-resource devices need different-depth networks (e. g., ResNet-18/34/50) with high-accuracy.
Self-Distillation for Few-Shot Image Captioning
We propose an ensemble-based self-distillation method that allows image captioning models to be trained with unpaired images and captions.
MM-FSOD: Meta and metric integrated few-shot object detection
In this paper, we present an effective object detection framework (MM-FSOD) that integrates metric learning and meta-learning to tackle the few-shot object detection task.
MGML: Multi-Granularity Multi-Level Feature Ensemble Network for Remote Sensing Scene Classification
To avoid the interference from confusing information, we propose Multi-granularity Multi-Level Feature Ensemble Module (MGML-FEM) which can provide diverse predictions by full-channel feature generator (FC-FG).
One-shot dynamical resource theory
Focusing on a general dynamical resource theory of quantum channels, here we consider tasks of one-shot resource distillation and dilution with a single copy of the resource.
Quantum Physics
A Deep Learning Framework for Predicting Digital Asset Price Movement from Trade-by-trade Data
Moreover, this study shows that the LSTM model could extract universal features from trade-by-trade data, as the learned parameters well maintain their high performance on other cryptocurrency instruments that were not included in training data.
Review of Machine-Learning Methods for RNA Secondary Structure Prediction
Recently, with the increasing availability of RNA structure data, new methods based on machine-learning technologies, especially deep learning, have alleviated the issue.
AiR: Attention with Reasoning Capability
In this work, we propose an Attention with Reasoning capability (AiR) framework that uses attention to understand and improve the process leading to task outcomes.
Saliency Prediction with External Knowledge
At the core of the method is a new Graph Semantic Saliency Network (GraSSNet) that constructs a graph that encodes semantic relationships learned from external knowledge.
Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detection
Few-shot object detection aims at detecting objects with few annotated examples, which remains a challenging research problem yet to be explored.
$n$-Reference Transfer Learning for Saliency Prediction
The proposed framework is gradient-based and model-agnostic.
Representation Learning for Information Extraction from Form-like Documents
We propose a novel approach using representation learning for tackling the problem of extracting structured information from form-like document images.
Active Learning for Skewed Data Sets
Furthermore, there is usually only a small amount of initial training data available when building machine-learned models to solve such problems.
GradMix: Multi-source Transfer across Domains and Tasks
Therefore, it is important to develop algorithms that can leverage off-the-shelf labeled dataset to learn useful knowledge for the target task.
Direction Concentration Learning: Enhancing Congruency in Machine Learning
We propose a Direction Concentration Learning (DCL) method to improve congruency in the learning process, where enhancing congruency influences the convergence path to be less circuitous.
Ranked #8 on
Image Classification
on Tiny ImageNet Classification
(using extra training data)
Human Annotations Improve GAN Performances
Unlike previous paradigms that directly ask annotators to distinguish between real and fake data in a straightforward way, we propose and annotate a set of carefully designed attributes that encode important image information at various levels, to understand the differences between fake and real images.
Designing metabolic division of labor in microbial communities
Specifically, we searched for communities able to survive under constraints (such as a limited number of reactions) that would not be sustainable by individual species.
Learning metrics for persistence-based summaries and applications for graph classification
However often in practice, the choice of the weight function should depend on the nature of the specific type of data one considers, and it is thus highly desirable to learn a best weight function (and thus metric for persistence diagrams) from labelled data.
Ranked #1 on
Graph Classification
on NCI109
Graph Classification
Computational Geometry
$\mathcal{G}$-softmax: Improving Intra-class Compactness and Inter-class Separability of Features
In addition, analysis of the intra-class compactness and inter-class separability demonstrates the advantages of the proposed function over the softmax function, which is consistent with the performance improvement.
Boosted Attention: Leveraging Human Attention for Image Captioning
Visual attention has shown usefulness in image captioning, with the goal of enabling a caption model to selectively focus on regions of interest.
Theory of variational quantum simulation
In this work, we introduce variational quantum simulation of mixed states under general stochastic evolution.
Quantum Physics
Learning to Learn from Noisy Labeled Data
Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect.
Ranked #26 on
Image Classification
on Clothing1M
(using extra training data)
Visual Social Relationship Recognition
Social relationships form the basis of social structure of humans.
A high threshold code for modular hardware with asymmetric noise
We consider an approach to fault tolerant quantum computing based on a simple error detecting code operating as the substrate for a conventional surface code.
Quantum Physics
Unsupervised Learning of View-invariant Action Representations
Different from previous works in video representation learning, our unsupervised learning task is to predict 3D motion in multiple target views using video representation from a source view.
Interact as You Intend: Intention-Driven Human-Object Interaction Detection
The recent advances in instance-level detection tasks lay strong foundation for genuine comprehension of the visual scenes.
Egocentric Spatial Memory
Egocentric spatial memory (ESM) defines a memory system with encoding, storing, recognizing and recalling the spatial information about the environment from an egocentric perspective.
Video Storytelling: Textual Summaries for Events
Video storytelling introduces new challenges, mainly due to the diversity of the story and the length and complexity of the video.
Emotional Attention: A Study of Image Sentiment and Visual Attention
In this paper, we present the first study to focus on the relation between emotional properties of an image and visual attention.
Advancing System Performance with Redundancy: From Biological to Artificial Designs
We envision that our theory would provide a framework for the future development of bio-inspired redundant artificial systems as well as assist the studies of the fundamental mechanisms governing various biological processes.
Egocentric Spatial Memory Network
During the exploration, our proposed ESM network model updates belief of the global map based on local observations using a recurrent neural network.
Learning Visual Attention to Identify People With Autism Spectrum Disorder
This paper presents a novel method for quantitative and objective diagnoses of Autism Spectrum Disorder (ASD) using eye tracking and deep neural networks.
Attention Transfer from Web Images for Video Recognition
However, due to the domain shift problem, the performance of Web images trained deep classifiers tend to degrade when directly deployed to videos.
Dual-Glance Model for Deciphering Social Relationships
Since the beginning of early civilizations, social relationships derived from each individual fundamentally form the basis of social structure in our daily life.
Ranked #3 on
Visual Social Relationship Recognition
on PIPA
Deep Future Gaze: Gaze Anticipation on Egocentric Videos Using Adversarial Networks
Through competition with discriminator, the generator progressively improves quality of the future frames and thus anticipates future gaze better.
Dex: Incremental Learning for Complex Environments in Deep Reinforcement Learning
This paper introduces Dex, a reinforcement learning environment toolkit specialized for training and evaluation of continual learning methods as well as general reinforcement learning problems.
A Paradigm for Building Generalized Models of Human Image Perception Through Data Fusion
(3) It can guide the design of a generalized computational algorithm for multi-dimensional visual perception.
SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks
Saliency in Context (SALICON) is an ongoing effort that aims at understanding and predicting visual attention.
Foveation-based Mechanisms Alleviate Adversarial Examples
To see this, first, we report results in ImageNet that lead to a revision of the hypothesis that adversarial perturbations are a consequence of CNNs acting as a linear classifier: CNNs act locally linearly to changes in the image regions with objects recognized by the CNN, and in other regions the CNN may act non-linearly.
SALICON: Saliency in Context
Saliency in Context (SALICON) is an ongoing effort that aims at understanding and predicting visual attention.
Label Consistent Quadratic Surrogate Model for Visual Saliency Prediction
In addition, since new datasets are built and shared in the community from time to time, it would be good not to retrain the entire model when new data are added.
Learning of Proto-object Representations via Fixations on Low Resolution
Visualizations also show that these features are selective to potential objects in the scene and the responses of these features work well in predicting eye fixations on the images when combined with learned weights.
Noise Characterization, Modeling, and Reduction for In Vivo Neural Recording
Multiple noise sources have been studied through analytical models as well as empirical measurements.
