Search Results for author:
Found 98 papers, 24 papers with code
Evolutionary Multitasking for Multiobjective Continuous Optimization: Benchmark Problems, Performance Metrics and Baseline Results
In this report, we suggest nine test problems for multi-task multi-objective optimization (MTMOO), each of which consists of two multiobjective optimization tasks that need to be solved simultaneously.
Temporal Dynamic Graph LSTM for Action-driven Video Object Detection
A common issue, however, is that objects of interest that are not involved in human actions are often absent in global action descriptions known as "missing label".
Ranked #3 on
Weakly Supervised Object Detection
on Charades
Robustness Analysis of Pedestrian Detectors for Surveillance
In this study, we conduct the research on the robustness of pedestrian detection algorithms to video quality degradation.
Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks
We consider the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable.
Dynamic Hierarchical Empirical Bayes: A Predictive Model Applied to Online Advertising
Predicting keywords performance, such as number of impressions, click-through rate (CTR), conversion rate (CVR), revenue per click (RPC), and cost per click (CPC), is critical for sponsored search in the online advertising industry.
Learning from Synthetic Data for Crowd Counting in the Wild
Secondly, we propose two schemes that exploit the synthetic data to boost the performance of crowd counting in the wild: 1) pretrain a crowd counter on the synthetic data, then finetune it using the real data, which significantly prompts the model's performance on real data; 2) propose a crowd counting method via domain adaptation, which can free humans from heavy data annotations.
Forward Vehicle Collision Warning Based on Quick Camera Calibration
Forward Vehicle Collision Warning (FCW) is one of the most important functions for autonomous vehicles.
Tracking as A Whole: Multi-Target Tracking by Modeling Group Behavior with Sequential Detection
In the detection stage, we present a sequential detection model to deal with serious occlusions.
Cross-Modal Message Passing for Two-stream Fusion
The classification object ensures that each modal network predicts the true action category while the competing objective encourages each modal network to outperform the other one.
Early Action Prediction with Generative Adversarial Networks
Action Prediction is aimed to determine what action is occurring in a video as early as possible, which is crucial to many online applications, such as predicting a traffic accident before it happens and detecting malicious actions in the monitoring system.
Memory-Augmented Temporal Dynamic Learning for Action Recognition
Human actions captured in video sequences contain two crucial factors for action recognition, i. e., visual appearance and motion dynamics.
Anomaly Detection in Traffic Scenes via Spatial-aware Motion Reconstruction
3) Results of motion orientation and magnitude are adaptively weighted and fused by a Bayesian model, which makes the proposed method more robust and handle more kinds of abnormal events.
Learning by Inertia: Self-supervised Monocular Visual Odometry for Road Vehicles
In this paper, we present iDVO (inertia-embedded deep visual odometry), a self-supervised learning based monocular visual odometry (VO) for road vehicles.
Embedding Structured Contour and Location Prior in Siamesed Fully Convolutional Networks for Road Detection
Road detection from the perspective of moving vehicles is a challenging issue in autonomous driving.
VSSA-NET: Vertical Spatial Sequence Attention Network for Traffic Sign Detection
Our contributions are as follows: 1) We propose a multi-resolution feature fusion network architecture which exploits densely connected deconvolution layers with skip connections, and can learn more effective features for the small size object; 2) We frame the traffic sign detection as a spatial sequence classification and regression task, and propose a vertical spatial sequence attention (VSSA) module to gain more context information for better detection performance.
A Joint Convolutional Neural Networks and Context Transfer for Street Scenes Labeling
Our contributions are threefold: (1) A priori s-CNNs model that learns priori location information at superpixel level is proposed to describe various objects discriminatingly; (2) A hierarchical data augmentation method is presented to alleviate dataset bias in the priori s-CNNs training stage, which improves foreground objects labeling significantly; (3) A soft restricted MRF energy function is defined to improve the priori s-CNNs model's labeling performance and reduce the over smoothness at the same time.
Marginalized Average Attentional Network for Weakly-Supervised Learning
The MAAN employs a novel marginalized average aggregation (MAA) module and learns a set of latent discriminative probabilities in an end-to-end fashion.
Ranked #11 on
Weakly Supervised Action Localization
on ActivityNet-1.3
(mAP@0.5 metric)
Weakly Supervised Action Localization
Weakly-supervised Learning
+2
Efficient Batch Black-box Optimization with Deterministic Regret Bounds
In this work, we investigate black-box optimization from the perspective of frequentist kernel methods.
Gift Contagion in Online Groups: Evidence From Virtual Red Packets
Using data on 36 million online red packet gifts on a large social site in East Asia, we leverage a natural experimental design to identify the social contagion of gift giving in online groups.
SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting
The latter attempts to extract more discriminative features among different channels, which aids model to pay attention to the head region, the core of crowd scenes.
Towards a Proactive MWE Terminological Platform for Cross-Lingual Mediation in the Age of Big Data
It has broader economic implication in the Age of Big Data (Tsou et al, 2015) and Trade War, as the workload, if not, the challenges, increasingly cannot be met by currently available front-line translators.
Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction
Recently, crowd counting using supervised learning achieves a remarkable improvement.
Feature-aware Adaptation and Density Alignment for Crowd Counting in Video Surveillance
To reduce the gap, in this paper, we propose a domain-adaptation-style crowd counting method, which can effectively adapt the model from synthetic data to the specific real-world scenes.
Focus on Semantic Consistency for Cross-domain Crowd Understanding
According to the semantic consistency, a similar distribution in deep layer's features of the synthetic and real-world crowd area, we first introduce a semantic extractor to effectively distinguish crowd and background in high-level semantic information.
Learning Longterm Representations for Person Re-Identification Using Radio Signals
RF signals traverse clothes and reflect off the human body; thus they can be used to extract more persistent human-identifying features like body size and shape.
Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting
Specifically, for a specific neuron of a source model, NLT exploits few labeled target data to learn domain shift parameters.
Video Frame Interpolation via Residue Refinement
Video frame interpolation achieves temporal super-resolution by generating smooth transitions between frames.
Ranked #14 on
Video Frame Interpolation
on Vimeo90K
Efficient Dynamic Scene Deblurring Using Spatially Variant Deconvolution Network With Optical Flow Guided Training
In order to remove the non-uniform blur of images captured from dynamic scenes, many deep learning based methods design deep networks for large receptive fields and strong fitting capabilities, or use multi-scale strategy to deblur image on different scales gradually.
Pixel-wise Crowd Understanding via Synthetic Data
To be specific, 1) supervised crowd understanding: pre-train a crowd analysis model on the synthetic data, then fine-tune it using the real data and labels, which makes the model perform better on the real world; 2) crowd understanding via domain adaptation: translate the synthetic data to photo-realistic images, then train the model on translated data and labels.
In-Home Daily-Life Captioning Using Radio Signals
This paper aims to caption daily life --i. e., to create a textual description of people's activities and interactions with objects in their homes.
Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning
In this paper, we combine both to propose an Unsupervised Semantic Aggregation and Deformable Template Matching (USADTM) framework for SSL, which strives to improve the classification performance with few labeled data and then reduce the cost in data annotating.
Causal Network Motifs: Identifying Heterogeneous Spillover Effects in A/B Tests
Our study provides an approach that accounts for both the local structure in a user's social network via motifs as well as the assignment conditions of neighbors.
Social and Information Networks Applications
Subgroup-based Rank-1 Lattice Quasi-Monte Carlo
We theoretically prove a lower and an upper bound of the minimum pairwise distance of any non-degenerate rank-1 lattice.
CM-Net: Concentric Mask based Arbitrary-Shaped Text Detection
Extensive experiments demonstrate the proposed CM is efficient and robust to fit arbitrary-shaped text instances, and also validate the effectiveness of MPF and constraints loss for discriminative text features recognition.
Learning Independent Instance Maps for Crowd Localization
Furthermore, to improve the segmentation quality for different density regions, we present a differentiable Binarization Module (BM) to output structured instance maps.
Addressing Feature Suppression in Unsupervised Visual Representations
However, contrastive learning is susceptible to feature suppression, i. e., it may discard important information relevant to the task of interest, and learn irrelevant features.
Learning Blood Oxygen from Respiration Signals
Further, since breathing can be monitored without body contact by analyzing the radio signal in the environment, we show that oxygen too can be monitored without any wearable devices.
Bio-Inspired Representation Learning for Visual Attention Prediction
In this paper, a novel VAP method is proposed to generate visual attention map via bio-inspired representation learning.
BiP-Net: Bidirectional Perspective Strategy based Arbitrary-Shaped Text Detection Network
Specifically, a new text representation strategy is proposed to represent text contours from a top-down perspective, which can fit highly curved text contours effectively.
Deep feature selection-and-fusion for RGB-D semantic segmentation
Scene depth information can help visual information for more accurate semantic segmentation.
Ranked #9 on
Semantic Segmentation
on SUN-RGBD
(using extra training data)
Self-supervised spectral matching network for hyperspectral target detection
In order to learn more discriminative features, a pair-based loss is adopted to minimize the distance between target pixels while maximizing the distances between target and background.
Open Set Domain Recognition via Attention-Based GCN and Semantic Matching Optimization
Open set domain recognition has got the attention in recent years.
Weighted Hierarchical Sparse Representation for Hyperspectral Target Detection
However, background dictionary building issue and the correlation analysis of target and background dictionary issue have not been well studied.
Instance-aware Remote Sensing Image Captioning with Cross-hierarchy Attention
The spatial attention is a straightforward approach to enhance the performance for remote sensing image captioning.
Task-Related Self-Supervised Learning for Remote Sensing Image Change Detection
(3) a smooth mechanism is utilized to remove some of pseudo-changes and noise.
Change Detection
Change detection for remote sensing images
+1
MT: Multi-Perspective Feature Learning Network for Scene Text Detection
Text detection, the key technology for understanding scene text, has become an attractive research topic.
Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification
In addition, due to domain gaps between different datasets, the performance is dramatically decreased when re-ID models pre-trained on label-rich datasets (source domain) are directly applied to other unlabeled datasets (target domain).
MESSFN : a Multi-level and Enhanced Spectral-Spatial Fusion Network for Pan-sharpening
A novel Spectral-Spatial (SS) stream is established to hierarchically derive and fuse the multi-level prior spectral and spatial expertise from the MS stream and the PAN stream.
Investigating and Modeling the Dynamics of Long Ties
Long ties, the social ties that bridge different communities, are widely believed to play crucial roles in spreading novel information in social networks.
LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds
The rapid development in visual crowd analysis shows a trend to count people by positioning or even detecting, rather than simply summing a density map.
ASK: Adaptively Selecting Key Local Features for RGB-D Scene Recognition
Discriminative local theme-level and object-level representations can be selected with the DLFS module from the spatially-correlated multi-modal RGB-D features.
Adaptive Shrink-Mask for Text Detection
It weakens the coupling of texts to shrink-masks, which improves the robustness of detection results.
Targeted Supervised Contrastive Learning for Long-Tailed Recognition
This forces all classes, including minority classes, to maintain a uniform distribution in the feature space, improves class boundaries, and provides better generalization even in the presence of long-tail data.
Ranked #22 on
Long-tail Learning
on CIFAR-10-LT (ρ=100)
Optimizing LLVM Pass Sequences with Shackleton: A Linear Genetic Programming Framework
In this paper we introduce Shackleton as a generalized framework enabling the application of linear genetic programming -- a technique under the umbrella of evolutionary algorithms -- to a variety of use cases.
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
For unsupervised saliency detection, we improve IoU for 4. 9%, 5. 2%, 12. 9% on ECSSD, DUTS, DUT-OMRON respectively compared to previous state of the art.
Ranked #1 on
Weakly-Supervised Object Localization
on CUB
Iterative Genetic Improvement: Scaling Stochastic Program Synthesis
In cases where large programs are required for a solution, it is generally believed that {\it stochastic} search has advantages over other classes of search techniques.
Dual-Stage Approach Toward Hyperspectral Image Super-Resolution
Hyperspectral image produces high spectral resolution at the sacrifice of spatial resolution.
Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher
The core reason of intrinsic scale shift being one of the most essential issues in crowd localization is that it is ubiquitous in crowd scenes and makes scale distribution chaotic.
Unsupervised Learning for Human Sensing Using Radio Signals
Thus, in this paper, we explore the feasibility of adapting RGB-based unsupervised representation learning to RF signals.
MAFNet: A Multi-Attention Fusion Network for RGB-T Crowd Counting
RGB-Thermal (RGB-T) crowd counting is a challenging task, which uses thermal images as complementary information to RGB images to deal with the decreased performance of unimodal RGB-based methods in scenes with low-illumination or similar backgrounds.
TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut
This method also achieves competitive results for unsupervised video object segmentation tasks with the DAVIS, SegTV2, and FBMS datasets.
Ranked #4 on
Unsupervised Instance Segmentation
on COCO val2017
Smiles in Profiles: Improving Fairness and Efficiency Using Estimates of User Preferences in Online Marketplaces
Online platforms often face challenges being both fair (i. e., non-discriminatory) and efficient (i. e., maximizing revenue).
RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data
However, the object-level visual grounding on RS images is still under-explored.
DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity
Most existing methods rely on binary shadow masks, without considering the ambiguous boundaries of soft and self shadows.
Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation
In our DA framework, we retain the depth and background information during the domain feature alignment.
Counting Like Human: Anthropoid Crowd Counting on Modeling the Similarity of Objects
The mainstream crowd counting methods regress density map and integrate it to obtain counting results.
Contactless Oxygen Monitoring with Gated Transformer
With the increasing popularity of telehealth, it becomes critical to ensure that basic physiological signals can be monitored accurately at home, with minimal patient overhead.
Z-SSMNet: A Zonal-aware Self-Supervised Mesh Network for Prostate Cancer Detection and Diagnosis in bpMRI
However, existing state of the art AI algorithms which are based on deep learning technology are often limited to 2D images that fails to capture inter-slice correlations in 3D volumetric images.
Learning to Simulate Daily Activities via Modeling Dynamic Human Needs
To enhance the fidelity and utility of the generated activity data, our core idea is to model the evolution of human needs as the underlying mechanism that drives activity generation in the simulation model.
Near-Optimal Experimental Design Under the Budget Constraint in Online Platforms
A/B testing, or controlled experiments, is the gold standard approach to causally compare the performance of algorithms on online platforms.
Imbalanced Aircraft Data Anomaly Detection
Anomaly detection in temporal data from sensors under aviation scenarios is a practical but challenging task: 1) long temporal data is difficult to extract contextual information with temporal correlation; 2) the anomalous data are rare in time series, causing normal/abnormal imbalance in anomaly detection, making the detector classification degenerate or even fail.
Spatio-temporal Diffusion Point Processes
To enhance the learning of each step, an elaborated spatio-temporal co-attention module is proposed to capture the interdependence between the event time and space adaptively.
Multi-Scale Simulation of Complex Systems: A Perspective of Integrating Knowledge and Data
In this survey, we will systematically review the literature on multi-scale simulation of complex systems from the perspective of knowledge and data.
Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution
In this paper, we enhance the visibility from a single nighttime haze image by suppressing glow and enhancing low-light regions.
Estimating Effects of Long-Term Treatments
We describe the identification assumptions, the estimation strategies, and the inference technique under this framework.
A Two-Part Machine Learning Approach to Characterizing Network Interference in A/B Testing
The reliability of controlled experiments, or "A/B tests," can often be compromised due to the phenomenon of network interference, wherein the outcome for one unit is influenced by other units.
Resource-Adaptive Newton's Method for Distributed Learning
Distributed stochastic optimization methods based on Newton's method offer significant advantages over first-order methods by leveraging curvature information for improved performance.
Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval
To address this issue, in this work, we investigate the parameter-efficient transfer learning (PETL) method to effectively and efficiently transfer visual-language knowledge from the natural domain to the RS domain on the image-text retrieval task.
Ranked #3 on
Cross-Modal Retrieval
on RSICD
Continuous Invariance Learning
To address this challenge, we then propose Continuous Invariance Learning (CIL), which extracts invariant features across continuously indexed domains.
Cross-modal Generative Model for Visual-Guided Binaural Stereo Generation
To this end, a metric to measure the spatial perception of audio is proposed for the first time.
Improving Factual Error Correction by Learning to Inject Factual Errors
Given the lack of paired data (i. e., false claims and their corresponding correct claims), existing methods typically adopt the mask-then-correct paradigm.
Mono3DVG: 3D Visual Grounding in Monocular Images
To foster this task, we propose Mono3DVG-TR, an end-to-end transformer-based network, which takes advantage of both the appearance and geometry information in text embeddings for multi-modal learning and 3D object localization.
Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives
Finally, since this area is new and quickly evolving, we discuss the open problems and promising future directions.
Do LLM Agents Exhibit Social Behavior?
Recent social science research has explored the use of these ``black-box'' LLM agents for simulating complex social systems and potentially substituting human subjects in experiments.
HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping
Further, to ensure the distinguishability among various regions, we introduce a region-level contrastive clustering loss to pull closer similar regions across images.
NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction
However, the intricacies of the real world, particularly with the presence of light effects and low-light regions affected by noise, create significant domain gaps, hampering synthetic-trained models in removing rain streaks properly and leading to over-saturation and color shifts.
SamLP: A Customized Segment Anything Model for License Plate Detection
Meanwhile, the proposed SamLP has great few-shot and zero-shot learning ability, which shows the potential of transferring vision foundation model.
Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention
They struggle to acquire new knowledge while also retaining previously learned knowledge. To address these problems, we propose a semantic segmentation method for multiple adverse weather conditions that incorporates adaptive knowledge acquisition, pseudolabel blending, and weather composition replay.
SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model
Specifically, after projecting RS visual features to the language domain via an alignment layer, they are fed jointly with task-specific instructions into an LLM-based RS decoder to predict answers for RS open-ended tasks.
Intelligent Diagnosis of Alzheimer's Disease Based on Machine Learning
Overall, this study successfully overcomes the challenge of missing data and provides valuable insights into early detection of Alzheimer's disease, demonstrating its unique research value and practical significance.
Beyond Imitation: Generating Human Mobility from Context-aware Reasoning with Large Language Models
In this paper, we design a novel Mobility Generation as Reasoning (MobiGeaR) framework that prompts LLM to recursively generate mobility behaviour.
Network Formation and Dynamics Among Multi-LLMs
Social networks shape opinions, behaviors, and information dissemination in human societies.
Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generation
Spatio-temporal modeling is foundational for smart city applications, yet it is often hindered by data scarcity in many cities and regions.
UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction
Urban spatio-temporal prediction is crucial for informed decision-making, such as transportation management, resource optimization, and urban planning.
Channel Measurements and Modeling for Dynamic Vehicular ISAC Scenarios at 28 GHz
Integrated sensing and communication (ISAC) is a promising technology for 6G, with the goal of providing end-to-end information processing and inherent perception capabilities for future communication systems.
Characterization of Wireless Channel Semantics: A New Paradigm
Recently, deep learning enabled semantic communications have been developed to understand transmission content from semantic level, which realize effective and accurate information transfer.
NightHaze: Nighttime Image Dehazing via Self-Prior Learning
By increasing the noise values to approach as high as the pixel intensity values of the glow and light effect blended images, our augmentation becomes severe, resulting in stronger priors.
Large Language Models as Test Case Generators: Performance Evaluation and Enhancement
As a complementary aspect to code generation, test case generation is of crucial importance in ensuring the quality and reliability of code.
