Dr. Ming-Ching Chang
I am an Associate Professor with tenure in the Department of Computer Science at the University at Albany, State University of New York. My research interests include video analytics, computer vision, image processing, and artificial intelligence.
Before joining UAlbany, I was a Computer Scientist at GE Global Research Center and an Assistant Researcher at the Industrial Technology Research Institute in Taiwan. I received my Ph.D. from Brown University, and my M.S. and B.S. degrees from National Taiwan University.
I lead research spanning intelligent video understanding, visual perception, and practical AI systems, with projects supported by government, industry, and academic partners.
Video Analytics
Computer Vision
Image Processing
Artificial Intelligence
đź“ť Recent Publications with PDFs
Medical AI & Healthcare Analytics 3 selected papers
MICCAI 2026
RatSeizure: A Benchmark and Saliency-Context Transformer for Rat Seizure Localization
AIME 2026
PreClaim-GCT: Self-Supervised Graph-Transformer Pretraining for Incident Outcome Prediction from Healthcare Claims
GC-CARE 2025
A Latent-Guided Hybrid Architecture for Liver Segmentation in Contrast-Enhanced MRI
Multimodal Video Understanding 6 selected papers
IEEE TMM 2026
SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM
ICPR 2026
LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval
ECCV Workshop 2026
TRACE-TAR: Reusable Video Evidence and Shared Event Memory for Transportation Anomaly Reasoning
AVSS 2026
Detecting ATM Money Mule Activities via LVLM-Guided Forensic Analysis
CVPR 2026
FAVE: A Structured Benchmark for Fine-Grained Audio-Visual Temporal Evaluation in Multimodal LLMs
IEEE Internet of Things Journal 2026
FE-DETRAC: An Infrastructure Fisheye Video Benchmark with Distortion-Aware Hybrid Data Association for Multi-Object Tracking
Learning Systems & Industrial AI 3 selected papers
MIPR 2026
Bridging Design and Quality: A Technical Overview of IFMs in Manufacturing
HiLD Workshop at ICML 2026
Causal Volterra Dynamics of Mamba
ICML 2026
FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU
Trustworthy & Generative AI 3 selected papers
TrustNLP Workshop at ACL 2026
Uncertainty-Aware Proxy Attribute Reasoning for Reliable Media Bias Detection
AAAI 2026
How Bias Binds: Measuring Hidden Associations for Bias Control in Text-to-Image Compositions
ICCV Workshop 2025
LSSGen: Leveraging Latent Space Scaling in Flow and Diffusion for Efficient Text-to-Image Generation
Vision, Image Analysis & Forensics 3 selected papers
CVPR Workshop 2026
SoREL: Soft-Label Refurbishment with Ensemble Learning for Noisy Long-Tailed Classification
IEEE ISM 2025
Physics-Guided Exposure Parameter Estimation for Image Metadata Verification
WACV 2026
PatchEAD: Unifying Industrial Visual Prompting Frameworks for Patch-Exclusive Anomaly Detection
đź“š All Publications
Browse by research topic
Computer Vision & Machine Learning 68 publications
- Weight Group-wise Post-Training Quantization for Medical Foundation Model
- SILVA-Mamba: Spatial Integrity for Landslide Segmentation via Vectorized Hilbert Scanning and Adaptive Mamba
- ReDiPrune: Relevance-Diversity Pre-Projection Token Pruning for Efficient Multimodal LLMs
- Partial Ring Scan: Revisiting Scan Order in Vision State Space Models
- Optimization-Diverse Transformer Adaptation with Gated Heterogeneous Fusion for Robust Thermal Object Detection
- 4th Workshop on Maritime Computer Vision (MaCVi): Challenge Overview
- Unsupervised domain adaptation for cross-style, cross-year land use understanding from historical maps
- Sharpness-Aware Geometric Defense for Robust Out-Of-Distribution Detection
- Scale-aware crowd counting network with annotation error modeling
- Robust defense against adversarial attacks with defensive preprocessing and adversarial training
- Rlministyler: Light-weight rl style agent for arbitrary sequential neural style generation
- Open-set occluded person identification with mmWave radar
- Latent Orthogonal Perturbation: A Data Poisoning Approach to Prevent Unauthorized LoRA Fine-Tuning
- Integrating manual preprocessing with automated feature extraction for improved rodent seizure classification
- Enhancing LLM Question Answering with RAG through Dense Vector Search and Re-Ranking
- Continual learning with synthetic boundary experience blending
- Continual Learning with Support Boundary Experience Blending
- A comprehensive evaluation of encrypted DNN inference methods
- Uu-mamba: Uncertainty-aware u-mamba for cardiovascular segmentation
- Set-Nas: Sample-Efficient Training For Neural Architecture Search With Strong Predictor And Stratified Sampling
- Pushing the limit of fine-tuning for few-shot learning: where feature reusing meets cross-scale attention
- NAS-based Recursive Stage Partial Network (RSPNet) for Light-Weight Semantic Segmentation
- MOTE-NAS: Multi-objective training-based estimate for efficient neural architecture search
- Learning multi-manifold embedding for out-of-distribution detection
- Improving limited supervised foot ulcer segmentation using cross-domain augmentation
- An Uncertainty-Aware Generalization Framework for Cardiovascular Image Segmentation
- Addressing long-tail noisy label learning problems: a two-stage solution with label refurbishment considering label rarity
- A comprehensive review of machine learning advances on data change: A cross-field perspective
- Scale-Aware Crowd Count Network with Annotation Error Correction
- Region-aware photo assurance system for image authentication
- Mean-Shift Based Differentiable Architecture Search
- Fisheye8k: A benchmark and dataset for fisheye camera object detection
- Towards multimodal semantic consistency analysis of long form articles
- Semi-supervised Learning for Topographic Map Analysis Over Time: a Study of Bridge Segmentation
- Scale-Aware Crowd Counting Using a Joint Likelihood Density Map and Synthetic Fusion Pyramid Network
- Pseudoprop: Robust pseudo-label generation for semi-supervised object detection in autonomous driving systems
- On multimodal semantic consistency detection of news articles with image caption pairs
- Mitigating Data Absence in Federated Learning Using Privacy-Controllable Data Digests
- Instance contour adjustment via structure-driven CNN
- FedTrust: Towards Building Secure Robust and Trustworthy Moderators for Federated Learning
- FedDig: Robust Federated Learning Using Data Digest to Represent Absent Clients.
- Class-Specific Channel Attention for Few-Shot Learning
- A Robust Collaborative Learning Framework Using Data Digests and Synonyms to Represent Absent Clients
- Transrpn: Towards the transferable adversarial perturbations using region proposal networks and beyond
- The 2020 Low-Power Computer Vision Challenge
- Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection
- MS-DARTS: Mean-shift based differentiable architecture search
- Learnable discrete wavelet pooling (LDW-Pooling) for convolutional networks
- MULTI-PASS YOLOV3 FOR SCOOTER LICENSE PLATE DETECTION AND RECOGNITION (Best paper candidate)
- Robust adversarial perturbation on deep proposal-based models
- Exploring the Vulnerability of Single Shot Module in Object Detectors via Imperceptible Background Patches
- Explain Black-box Image Classifications Using Superpixel-based Interpretation
- Adaptive RNN Tree for Large-Scale Human Action Recognition
- Crowd Analytics via One Shot Learning and Agent Based Inference
- Co-regularized PLSA For Multi-Modal Learning
- Bridging Computer Vision and Social Science: A Multi-Camera Vision System for Social Interaction Training Analysis
- Probabilistic Group-Level Motion Analysis and Scenario Recognition
- Fast Search Algorithms for IC Printed Mark Quality Inspection
- IC Printed Mark Quality Inspection Algorithms
- UAlbany3D
- PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems–Appendix
- MIPR 2022
- Cross-scale Patch-Attention with Prototype-guided Siamese Network for Effective Anomaly Detection
- Counting Very Small Vehicles and Crowds in Uav Images Using Mdamdl Framework
- Andre Kaup, Friedrich-Alexander University Erlangen-NĂĽrnberg Changick Kim, Korea Advanced Institute of Science and Technology Serkan Kiranyaz, Qatar University
- 2025 IEEE 8th International Conference on Multimedia Information Processing and Retrieval (MIPR)| 979-8-3315-9465-7/25/$31.00© 2025 IEEE| DOI: 10.1109/MIPR67560. 2025.00099
- 2024 IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR)| 979-8-3503-5142-2/24/$31.00© 2024 IEEE| DOI: 10.1109/MIPR62202. 2024.00119
- 2023 IEEE 6th International Conference on Multimedia Information Processing and Retrieval (MIPR)| 979-8-3503-0781-8/23/$31.00© 2023 IEEE| DOI: 10.1109/MIPR59079. 2023.00007
Patents & Technology Transfer 27 publications
- Training method for continual learning model and non-transitory computer-readable medium
- Method and system for reducing hallucinations generated by a large vision-language model
- Inference and conversion method for encrypted deep neural network model
- Accelerated bootstrapping fully homomorphic encryption calculator, computing system, and operating method thereof
- System for verifying edited image
- Segmentation model training method, device, and non-transitory computer readable storage medium
- Robust out-of-distribution detection system and method
- Operating system and method of a fully homomorphic encryption neural network model
- Multi-manifold embedding learning method and system
- Method of training a model using data essence
- Method for verifying model update
- Method for machine learning model verification and transaction
- Machine learning training device, method, and non-transitory computer readable storage medium
- Federated learning system using synonym
- Device for executing machine learning model inference
- Privacy computing method based on homomorphic encryption
- Federated learning system and method of protecting data digest
- Fedrated learning system and method using data digest
- Federated learning method using synonym
- Three-dimensional modeling of an object
- Image and video capture architecture for three-dimensional reconstruction
- Systems and methods for analyzing time series data based on event transitions
- Apparatus and method for spatially relating views of sky images acquired at spaced apart locations
- Apparatus and method for predicting solar irradiance variation
- Usage measurent techniques and systems for interactive advertising
- Person tracking and interactive advertising
- Analytics-to-content interface for interactive advertising
Video Analytics, Tracking & Transportation 62 publications
- The 10th AI city challenge
- Flashsinkhorn: Io-aware entropic optimal transport
- E4: Energy-efficient DNN inference for edge video analytics via early exiting and DVFS
- BF-YOLOv7: Enhancing Helmet Rule Violation Detection
- The 8th ai city challenge
- Text-driven synchronized diffusion video and audio talking head generation
- Smiletrack: Similarity learning for occlusion-aware multiple object tracking
- Image classification for historical documents: a study on Chinese local gazetteers
- Dual-Phase Msqnet for Species-Specific Animal Activity Recognition
- Video analytics for detecting motorcyclist helmet rule violations
- The 7th AI City Challenge
- Prb-fpn+: Video analytics for enforcing motorcycle helmet laws
- Fisheye multiple object tracking by learning distortions without dewarping
- Simultaneous Multi-Person Tracking and Activity Recognition based on Cohesive Cluster Search
- DetPoseNet: Improving multi-person pose estimation via coarse-pose filtering
- Multi-Camera Tracking by Candidate Intersection Ratio Tracklet Matching
- FlagDetSeg: Multi-nation flag detection and segmentation in the wild
- A video analytic system for rail crossing point protection
- UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking
- Railcar Detection, Identification and Tracking for Rail Yard Management
- Explainable and Efficient Sequential Correlation Network for 3D Single Person Concurrent Activity Detection
- Drone-Based Vehicle Flow Estimation and its Application to Traffic Conflict Hotspot Detection at Intersections
- AI City Challenge 2020 - Computer Vision for Smart Transportation Applications
- 3D Single-Person Concurrent Activity Detection Using Stacked Relation Network
- WIP abstract: Deep intelligent network for device-free people tracking
- The 2019 AI City Challenge
- Occupancy sensing and activity recognition with cameras and wireless sensors
- Graph-to-Graph Energy Minimization for Video Object Segmentation
- Fast Online Video Pose Estimation by Dynamic Bayesian Modeling of Mode Transitions
- Deep intelligent network for device-free people tracking: WIP abstract
- Deep Intelligent Network for Device-free People Tracking
- AI City Challenge 2019 -- City-Scale Video Analytics for Smart Transportation
- Who did what at where and when: simultaneous multi-person tracking and activity recognition
- Video Analytics in Smart Transportation for the AIC'18 Challenge
- The 2018 nvidia ai city challenge
- Pixel offset regression (por) for single-shot instance segmentation
- Multi-Scale Structure-Aware Network for Human Pose Estimation
- In ictu oculi: Exposing AI generated fake face videos by detecting eye blinking. 2018
- In ictu oculi: Exposing ai created fake videos by detecting eye blinking
- UA-DETRAC 2017: Report of AVSS2017 \& IWT4S Challenge on Advanced Traffic Monitoring
- The NVIDIA AI City Challenge
- Street Object Detection / Tracking for AI City Traffic Analysis
- Multi-Camera Multi-Target Tracking with Space-Time-View Hyper-graph
- Hybrid Structure Hypergraph for Online Deformable Object Tracking
- Cloud Tracking for Solar Irradiance Prediction
- Efficient large-scale photometric reconstruction using Divide-Recon-Fuse 3D Structure from Motion
- AVSS 2016 Message from the chairs
- The visual object tracking vot2015 challenge results
- The thermal infrared visual object tracking VOT-TIR2015 challenge results
- Shot Segmentation and Grouping for PTZ Camera Videos
- Seeing as it Happens: Real time 3D Video Event Visualization
- Fast Online Upper Body Pose Estimation from Video
- DETRAC: A new benchmark and protocol for multi-object tracking
- A live video analytic system for affect analysis in public space
- Spatio-Temporal Phrases for Activity Recognition
- Tracking Gaze Direction from Far-Field Surveillance Cameras
- Gaze and Body Pose Estimation from a Distance
- Group Level Activity Recognition in Crowded Environments across Multiple Cameras
- TRAFFIC ANALYSIS USING VISUAL OBJECT DETECTION AND TRACKING
- Multi-Scale Structure Learning for Human Pose Estimation
- Diffusion Model for Text to Synchronized Joint Talking Head Video and Audio Generation
- CARTS: Cooperative Reinforcement Learning for Traffic Signal Control and Carbon Emission Reduction
Trustworthy AI & Media Forensics 21 publications
- Who brings the frisbee: Probing hidden hallucination factors in large vision-language model via causality analysis
- Training-free image manipulation localization using diffusion models
- Spotting the fakes: A deep dive into GAN-generated face detection
- A semantically impactful image manipulation dataset: Characterizing image manipulations using semantic significance
- Unveiling mesoscopic structures in distorted lamellar phases through deep learning-based small angle neutron scattering analysis
- TextSleuth: a new dataset and baseline for scene text manipulation detection
- Leveraging Semantic Segmentation for Image Manipulation Detection and Localization
- Learning With Instance-Dependent Noisy Labels By Anchor Hallucination And Hard Sample Label Correction
- Image manipulation detection with implicit neural representation and limited supervision
- A New Benchmark and Model for Challenging Image Manipulation Detection
- Using vocoder artifacts for audio deepfakes detection
- Gan-generated faces detection: A survey and new perspectives
- Welcome Message from MIPR 2022 Organization Committee
- Robust attentive deep neural network for detecting gan-generated faces
- Open-eye: An open platform to study human performance on identifying ai-synthesized faces
- Observation of attention mechanism baseline for pcb surface inspection system
- Lightning YOLOv4 for a surface defect detection system for sawn lumber
- Exposing AI-Synthesized Human Voices Using Neural Vocoder Artifacts
- Multi-Teacher Single-Student Visual Transformer with Multi-Level Attention for Face Spoofing Detection.
- MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network
- Modeling transition patterns between events for temporal human action segmentation and classification
Industrial AI & Scientific Computing 19 publications
- Scattering-based structural inversion of soft materials via Kolmogorov–Arnold networks
- Optimizing Encrypted Neural Networks: Model Design, Quantization and Fine-Tuning Using FHEW/TFHE
- Generative Kolmogorov-Arnold Network Architecture for Enhanced Quantative Small Angle Neutron Scattering Data Analysis
- PreAugNet: improve data augmentation for industrial defect classification with small-scale training data
- Inferring effective electrostatic interaction of charge-stabilized colloids from scattering using deep learning
- Gpu acceleration for fhew/tfhe bootstrapping
- Efficient design of FHEW/TFHE bootstrapping implementation with scalable parameters
- Inferring Colloidal Interaction from Scattering by Machine Learning
- An efficient ckks-fhew/tfhe hybrid encrypted inference framework
- A machine learning inversion scheme for determining interaction from scattering
- A machine learning inversion scheme for determining effective interaction of charged colloidal suspensions using scattering
- Driver License Field Detection Using Real-Time Deep Networks
- Deep Learning Based Super-Resolution for Small-Angle Neutron Scattering Data: Attempt to Accelerate Experimental Workflow
- Accelerating neutron scattering data collection and experiments using AI deep super-resolution learning
- Cross-cultural training analysis via social science and computer vision methods
- Fast Search Algorithms for Industrial Inspection
- Supplementary Material: Instance Contour Adjustment via Structure-driven CNN
- Inferring Structure Factors of Charge Stabilized Colloids from Scattering Using Deep Learning
- Deeppvmap: Deep Photovoltaic Map for Efficient Segmentation of Solar Panels from Low-Resolution Aerial Imagery
Medical AI & Healthcare 15 publications
- IntelliCardiac: An Intelligent Platform for Cardiac Image Segmentation and Classification
- Uu-mamba: uncertainty-aware u-mamba for cardiac image segmentation
- Modeling Latent Comorbidity for Health Risk Prediction Using Graph Convolutional Network.
- Multi-Modal Sensor System for Pressure Ulcer Wound Assessment and Care
- In-Bed Patient Motion and Pose Analysis Using Depth Videos for Pressure Ulcer Prevention
- Quantitative pharmacokinetic analysis of prostate cancer DCE-MRI at 3 T: comparison of two arterial input functions on cancer detection with digitized whole mount …
- Variations of Dynamic Contrast-Enhanced Magnetic Resonance Imaging in Evaluation of Breast Cancer Therapy Response: A Multicenter Data Analysis Challenge
- Variations in DCE-MRI Assessment of Breast Cancer Therapy Response: A Multicenter Data Analysis Challenge
- Spatial Information Based DCE-MRI Data Reconstruction and Analysis using PCA
- Improved T1 mapping and DCE-MRI quantification for prostate at 3T by Incorporating B1 inhomogeneity correction
- Automatic Arterial Input Function Detection for Prostate Dynamic Contrast Enhanced MRI
- Automated Determination of Arterial Input Function for DCE-MRI of the Prostate
- Subvoxel Segmentation and Representation of Brain Cortex using Fuzzy Clustering and Gradient Vector Diffusion
- Reliable Fusion of Knee Bone Laser Scans to Establish Ground Truth for Cartilage Thickness Measurement
- A Skull Stripping Method Using Deformable Surface and Tissue Classification
Generative AI & Multimodal Learning 9 publications
- Improving limited supervised foot ulcer segmentation using cross-domain augmentation strategies
- Two-stage dual augmentation with clip for improved text-to-sketch synthesis
- Transformer Based Image-Text Consistency Analysis for Infographic Articles
- Mixnet: toward accurate detection of challenging scene text in the wild
- Vocbench: A neural vocoder benchmark for speech synthesis
- Text-image de-contextualization detection using vision-language models
- Improving class activation map for weakly supervised object localization
- Efficient algorithms for graph regularized PLSA for probabilistic topic modeling
- Group context learning for event recognition
3D Vision & Geometry 10 publications
- Eyes tell all: Irregular pupil shapes reveal gan-generated faces
- Measuring 3D Shape Similarity by Graph-Based Matching of the Medial Scaffolds
- A General Approach to Model Biomedical Data from 3D Unorganised Point Clouds with Medial Scaffolds
- The medial scaffold for three-dimensional shape modeling and recognition
- Surface Reconstruction from Point Clouds by Transforming the Medial Scaffold
- Measuring 3D Shape Similarity by Matching the Medial Scaffolds
- The Medial Scaffold for 3D Shape Modeling and Recognition
- Regularizing 3D Medial Axis Using Medial Scaffold Transforms
- Shape Registration using Regularized Medial Scaffolds
- 3D Shape Registration using Regularized Medial Scaffolds
Browse by year
The complete publication record is generated from the canonical chang.bib database. Search by title, author, venue, or year; for example, Siwei, Jun-Wei, inspect, or AVSS.
2026 8 papers
- Weight Group-wise Post-Training Quantization for Medical Foundation Model
- The 10th AI city challenge
- SILVA-Mamba: Spatial Integrity for Landslide Segmentation via Vectorized Hilbert Scanning and Adaptive Mamba
- ReDiPrune: Relevance-Diversity Pre-Projection Token Pruning for Efficient Multimodal LLMs
- Partial Ring Scan: Revisiting Scan Order in Vision State Space Models
- Optimization-Diverse Transformer Adaptation with Gated Heterogeneous Fusion for Robust Thermal Object Detection
- Flashsinkhorn: Io-aware entropic optimal transport
- 4th Workshop on Maritime Computer Vision (MaCVi): Challenge Overview
2025 22 papers
- Who brings the frisbee: Probing hidden hallucination factors in large vision-language model via causality analysis
- Unsupervised domain adaptation for cross-style, cross-year land use understanding from historical maps
- Training-free image manipulation localization using diffusion models
- Spotting the fakes: A deep dive into GAN-generated face detection
- Sharpness-Aware Geometric Defense for Robust Out-Of-Distribution Detection
- Scattering-based structural inversion of soft materials via Kolmogorov–Arnold networks
- Scale-aware crowd counting network with annotation error modeling
- Robust defense against adversarial attacks with defensive preprocessing and adversarial training
- Rlministyler: Light-weight rl style agent for arbitrary sequential neural style generation
- Optimizing Encrypted Neural Networks: Model Design, Quantization and Fine-Tuning Using FHEW/TFHE
- Open-set occluded person identification with mmWave radar
- Latent Orthogonal Perturbation: A Data Poisoning Approach to Prevent Unauthorized LoRA Fine-Tuning
- IntelliCardiac: An Intelligent Platform for Cardiac Image Segmentation and Classification
- Integrating manual preprocessing with automated feature extraction for improved rodent seizure classification
- Generative Kolmogorov-Arnold Network Architecture for Enhanced Quantative Small Angle Neutron Scattering Data Analysis
- Enhancing LLM Question Answering with RAG through Dense Vector Search and Re-Ranking
- E4: Energy-efficient DNN inference for edge video analytics via early exiting and DVFS
- Continual learning with synthetic boundary experience blending
- Continual Learning with Support Boundary Experience Blending
- BF-YOLOv7: Enhancing Helmet Rule Violation Detection
- A semantically impactful image manipulation dataset: Characterizing image manipulations using semantic significance
- A comprehensive evaluation of encrypted DNN inference methods
2024 27 papers
- Uu-mamba: Uncertainty-aware u-mamba for cardiovascular segmentation
- Uu-mamba: uncertainty-aware u-mamba for cardiac image segmentation
- Unveiling mesoscopic structures in distorted lamellar phases through deep learning-based small angle neutron scattering analysis
- The 8th ai city challenge
- TextSleuth: a new dataset and baseline for scene text manipulation detection
- Text-driven synchronized diffusion video and audio talking head generation
- Smiletrack: Similarity learning for occlusion-aware multiple object tracking
- Set-Nas: Sample-Efficient Training For Neural Architecture Search With Strong Predictor And Stratified Sampling
- Pushing the limit of fine-tuning for few-shot learning: where feature reusing meets cross-scale attention
- PreAugNet: improve data augmentation for industrial defect classification with small-scale training data
- NAS-based Recursive Stage Partial Network (RSPNet) for Light-Weight Semantic Segmentation
- MOTE-NAS: Multi-objective training-based estimate for efficient neural architecture search
- Leveraging Semantic Segmentation for Image Manipulation Detection and Localization
- Learning With Instance-Dependent Noisy Labels By Anchor Hallucination And Hard Sample Label Correction
- Learning multi-manifold embedding for out-of-distribution detection
- Inferring effective electrostatic interaction of charge-stabilized colloids from scattering using deep learning
- Improving limited supervised foot ulcer segmentation using cross-domain augmentation strategies
- Improving limited supervised foot ulcer segmentation using cross-domain augmentation
- Image manipulation detection with implicit neural representation and limited supervision
- Image classification for historical documents: a study on Chinese local gazetteers
- Gpu acceleration for fhew/tfhe bootstrapping
- Efficient design of FHEW/TFHE bootstrapping implementation with scalable parameters
- Dual-Phase Msqnet for Species-Specific Animal Activity Recognition
- An Uncertainty-Aware Generalization Framework for Cardiovascular Image Segmentation
- Addressing long-tail noisy label learning problems: a two-stage solution with label refurbishment considering label rarity
- A New Benchmark and Model for Challenging Image Manipulation Detection
- A comprehensive review of machine learning advances on data change: A cross-field perspective
2023 15 papers
- Video analytics for detecting motorcyclist helmet rule violations
- Using vocoder artifacts for audio deepfakes detection
- Two-stage dual augmentation with clip for improved text-to-sketch synthesis
- Transformer Based Image-Text Consistency Analysis for Infographic Articles
- The 7th AI City Challenge
- Scale-Aware Crowd Count Network with Annotation Error Correction
- Region-aware photo assurance system for image authentication
- Prb-fpn+: Video analytics for enforcing motorcycle helmet laws
- Mixnet: toward accurate detection of challenging scene text in the wild
- Mean-Shift Based Differentiable Architecture Search
- Inferring Colloidal Interaction from Scattering by Machine Learning
- Gan-generated faces detection: A survey and new perspectives
- Fisheye8k: A benchmark and dataset for fisheye camera object detection
- Fisheye multiple object tracking by learning distortions without dewarping
- An efficient ckks-fhew/tfhe hybrid encrypted inference framework
2022 25 papers
- Welcome Message from MIPR 2022 Organization Committee
- Vocbench: A neural vocoder benchmark for speech synthesis
- Towards multimodal semantic consistency analysis of long form articles
- Text-image de-contextualization detection using vision-language models
- Simultaneous Multi-Person Tracking and Activity Recognition based on Cohesive Cluster Search
- Semi-supervised Learning for Topographic Map Analysis Over Time: a Study of Bridge Segmentation
- Scale-Aware Crowd Counting Using a Joint Likelihood Density Map and Synthetic Fusion Pyramid Network
- Robust attentive deep neural network for detecting gan-generated faces
- Pseudoprop: Robust pseudo-label generation for semi-supervised object detection in autonomous driving systems
- Open-eye: An open platform to study human performance on identifying ai-synthesized faces
- On multimodal semantic consistency detection of news articles with image caption pairs
- Observation of attention mechanism baseline for pcb surface inspection system
- Mitigating Data Absence in Federated Learning Using Privacy-Controllable Data Digests
- Lightning YOLOv4 for a surface defect detection system for sawn lumber
- Instance contour adjustment via structure-driven CNN
- Improving class activation map for weakly supervised object localization
- FedTrust: Towards Building Secure Robust and Trustworthy Moderators for Federated Learning
- FedDig: Robust Federated Learning Using Data Digest to Represent Absent Clients.
- Eyes tell all: Irregular pupil shapes reveal gan-generated faces
- Exposing AI-Synthesized Human Voices Using Neural Vocoder Artifacts
- DetPoseNet: Improving multi-person pose estimation via coarse-pose filtering
- Class-Specific Channel Attention for Few-Shot Learning
- A Robust Collaborative Learning Framework Using Data Digests and Synonyms to Represent Absent Clients
- A machine learning inversion scheme for determining interaction from scattering
- A machine learning inversion scheme for determining effective interaction of charged colloidal suspensions using scattering
2021 9 papers
- Transrpn: Towards the transferable adversarial perturbations using region proposal networks and beyond
- The 2020 Low-Power Computer Vision Challenge
- Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection
- Multi-Teacher Single-Student Visual Transformer with Multi-Level Attention for Face Spoofing Detection.
- Multi-Camera Tracking by Candidate Intersection Ratio Tracklet Matching
- MS-DARTS: Mean-shift based differentiable architecture search
- Learnable discrete wavelet pooling (LDW-Pooling) for convolutional networks
- FlagDetSeg: Multi-nation flag detection and segmentation in the wild
- A video analytic system for rail crossing point protection
2020 11 papers
- UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking
- Railcar Detection, Identification and Tracking for Rail Yard Management
- MULTI-PASS YOLOV3 FOR SCOOTER LICENSE PLATE DETECTION AND RECOGNITION (Best paper candidate)
- Modeling Latent Comorbidity for Health Risk Prediction Using Graph Convolutional Network.
- MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network
- Explainable and Efficient Sequential Correlation Network for 3D Single Person Concurrent Activity Detection
- Drone-Based Vehicle Flow Estimation and its Application to Traffic Conflict Hotspot Detection at Intersections
- Driver License Field Detection Using Real-Time Deep Networks
- Deep Learning Based Super-Resolution for Small-Angle Neutron Scattering Data: Attempt to Accelerate Experimental Workflow
- AI City Challenge 2020 - Computer Vision for Smart Transportation Applications
- 3D Single-Person Concurrent Activity Detection Using Stacked Relation Network
2019 10 papers
- WIP abstract: Deep intelligent network for device-free people tracking
- The 2019 AI City Challenge
- Occupancy sensing and activity recognition with cameras and wireless sensors
- Graph-to-Graph Energy Minimization for Video Object Segmentation
- Fast Online Video Pose Estimation by Dynamic Bayesian Modeling of Mode Transitions
- Efficient algorithms for graph regularized PLSA for probabilistic topic modeling
- Deep intelligent network for device-free people tracking: WIP abstract
- Deep Intelligent Network for Device-free People Tracking
- AI City Challenge 2019 -- City-Scale Video Analytics for Smart Transportation
- Accelerating neutron scattering data collection and experiments using AI deep super-resolution learning
2018 10 papers
- Who did what at where and when: simultaneous multi-person tracking and activity recognition
- Video Analytics in Smart Transportation for the AIC'18 Challenge
- The 2018 nvidia ai city challenge
- Robust adversarial perturbation on deep proposal-based models
- Pixel offset regression (por) for single-shot instance segmentation
- Multi-Scale Structure-Aware Network for Human Pose Estimation
- In ictu oculi: Exposing AI generated fake face videos by detecting eye blinking. 2018
- In ictu oculi: Exposing ai created fake videos by detecting eye blinking
- Exploring the Vulnerability of Single Shot Module in Object Detectors via Imperceptible Background Patches
- Explain Black-box Image Classifications Using Superpixel-based Interpretation
2017 9 papers
- UA-DETRAC 2017: Report of AVSS2017 \& IWT4S Challenge on Advanced Traffic Monitoring
- The NVIDIA AI City Challenge
- Street Object Detection / Tracking for AI City Traffic Analysis
- Multi-Modal Sensor System for Pressure Ulcer Wound Assessment and Care
- Multi-Camera Multi-Target Tracking with Space-Time-View Hyper-graph
- In-Bed Patient Motion and Pose Analysis Using Depth Videos for Pressure Ulcer Prevention
- Hybrid Structure Hypergraph for Online Deformable Object Tracking
- Cloud Tracking for Solar Irradiance Prediction
- Adaptive RNN Tree for Large-Scale Human Action Recognition
2016 4 papers
2015 11 papers
- The visual object tracking vot2015 challenge results
- The thermal infrared visual object tracking VOT-TIR2015 challenge results
- Shot Segmentation and Grouping for PTZ Camera Videos
- Seeing as it Happens: Real time 3D Video Event Visualization
- Quantitative pharmacokinetic analysis of prostate cancer DCE-MRI at 3 T: comparison of two arterial input functions on cancer detection with digitized whole mount …
- Modeling transition patterns between events for temporal human action segmentation and classification
- Fast Online Upper Body Pose Estimation from Video
- DETRAC: A new benchmark and protocol for multi-object tracking
- Cross-cultural training analysis via social science and computer vision methods
- Bridging Computer Vision and Social Science: A Multi-Camera Vision System for Social Interaction Training Analysis
- A live video analytic system for affect analysis in public space
2014 2 papers
2013 2 papers
2012 2 papers
2011 6 papers
- Tracking Gaze Direction from Far-Field Surveillance Cameras
- Probabilistic Group-Level Motion Analysis and Scenario Recognition
- Measuring 3D Shape Similarity by Graph-Based Matching of the Medial Scaffolds
- Gaze and Body Pose Estimation from a Distance
- Automatic Arterial Input Function Detection for Prostate Dynamic Contrast Enhanced MRI
- Automated Determination of Arterial Input Function for DCE-MRI of the Prostate
2010 5 papers
- Subvoxel Segmentation and Representation of Brain Cortex using Fuzzy Clustering and Gradient Vector Diffusion
- Reliable Fusion of Knee Bone Laser Scans to Establish Ground Truth for Cartilage Thickness Measurement
- Group Level Activity Recognition in Crowded Environments across Multiple Cameras
- A Skull Stripping Method Using Deformable Surface and Tissue Classification
- A General Approach to Model Biomedical Data from 3D Unorganised Point Clouds with Medial Scaffolds