Search Results for author:
Found 56 papers, 21 papers with code
CIMGEN: Controlled Image Manipulation by Finetuning Pretrained Generative Models on Limited Data
Content creation and image editing can benefit from flexible user controls.
BLoad: Enhancing Neural Network Training with Efficient Sequential Data Handling
The increasing complexity of modern deep neural network models and the expanding sizes of datasets necessitate the development of optimized and scalable training methods.
Q-RBSA: High-Resolution 3D EBSD Map Generation Using An Efficient Quaternion Transformer Network
Our framework uses a quaternion residual block self-attention network (QRBSA) to generate high-resolution 3D EBSD maps from sparsely sectioned EBSD maps.
DDS: Decoupled Dynamic Scene-Graph Generation Network
Scene-graph generation involves creating a structural representation of the relationships between objects in a scene by predicting subject-object-relation triplets from input data.
3D Neuron Morphology Analysis
A skeleton graph is then obtained from skeleton mesh and is used to extract sub-cellular features.
Generalizable Deepfake Detection with Phase-Based Motion Analysis
Overall, with PhaseForensics, we show improved distortion and adversarial robustness, and state-of-the-art cross-dataset generalization, with 91. 2% video-level AUC on the challenging CelebDFv2 (a recent state-of-the-art compares at 86. 9%).
Context-Matched Collage Generation for Underwater Invertebrate Detection
However, in many scenarios, it can be difficult to collect images for training, not to mention the costs associated with collecting annotations suitable for training these object detectors.
MalGrid: Visualization Of Binary Features In Large Malware Corpora
The number of malware is constantly on the rise.
LOCL: Learning Object-Attribute Composition using Localization
This paper describes LOCL (Learning Object Attribute Composition using Localization) that generalizes composition zero shot learning to objects in cluttered and more realistic settings.
Ranked #1 on
Zero-Shot Learning
on MIT-States
Deep Learning Enabled Time-Lapse 3D Cell Analysis
This paper presents a method for time-lapse 3D cell analysis.
Context-Driven Detection of Invertebrate Species in Deep-Sea Video
Each video includes annotations indicating the start and end times of substrates across the video in addition to counts of species of interest.
Automated Segmentation and Connectivity Analysis for Normal Pressure Hydrocephalus
The segmentation and network features are used to train a model for NPH prediction.
HAPSSA: Holistic Approach to PDF Malware Detection Using Signal and Statistical Analysis
Malicious PDF documents present a serious threat to various security organizations that require modern threat intelligence platforms to effectively analyze and characterize the identity and behavior of PDF malware.
OMD: Orthogonal Malware Detection Using Audio, Image, and Static Features
In this paper, we propose a novel and orthogonal malware detection (OMD) approach to identify malware using a combination of audio descriptors, image similarity descriptors and other static/statistical features.
Seam Carving Detection and Localization using Two-Stage Deep Neural Networks
In this paper, we propose a two-step method to detect and localize seam carved images.
SeeTheSeams: Localized Detection of Seam Carving based Image Forgery in Satellite Imagery
Seam carving is a popular technique for content aware image retargeting.
A computational geometry approach for modeling neuronal fiber pathways
We develop a computational geometry-based tractography representation that aims to simplify the connectivity of white matter fibers.
GTNet:Guided Transformer Network for Detecting Human-Object Interactions
For detecting HOI, it is important to utilize relative spatial configurations and object semantics to find salient spatial regions of images that highlight the interactions between human object pairs.
FoveaTer: Foveated Transformer for Image Classification
We propose Foveated Transformer (FoveaTer) model, which uses pooling regions and eye movements to perform object classification tasks using a Vision Transformer architecture.
Holistic Image Manipulation Detection using Pixel Co-occurrence Matrices
While most detection methods in literature focus on detecting a particular type of manipulation, it is challenging to identify doctored images that involve a host of manipulations.
Adversarially Optimized Mixup for Robust Classification
Mixup is a procedure for data augmentation that trains networks to make smoothly interpolated predictions between datapoints.
Attribution of Gradient Based Adversarial Attacks for Reverse Engineering of Deceptions
Machine Learning (ML) algorithms are susceptible to adversarial attacks and deception both during training and deployment.
Malware Detection Using Frequency Domain-Based Image Visualization and Deep Learning
Motivated by the visual similarity of these images for different malware families, we compare our deep neural network models with standard image features like GIST descriptors to evaluate the performance.
StressNet: Detecting Stress in Thermal Videos
Precise measurement of physiological signals is critical for the effective monitoring of human vital signs.
Semi supervised segmentation and graph-based tracking of 3D nuclei in time-lapse microscopy
We propose a novel weakly supervised method to improve the boundary of the 3D segmented nuclei utilizing an over-segmented image.
Exploiting Context for Robustness to Label Noise in Active Learning
Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available.
3DMaterialGAN: Learning 3D Shape Representation from Latent Space for Materials Science Applications
In the field of computer vision, unsupervised learning for 2D object generation has advanced rapidly in the past few years.
Detection, Attribution and Localization of GAN Generated Images
Recent advances in Generative Adversarial Networks (GANs) have led to the creation of realistic-looking digital images that pose a major challenge to their detection by humans or computers.
PCAMs: Weakly Supervised Semantic Segmentation Using Point Supervision
Current state of the art methods for generating semantic segmentation rely heavily on a large set of images that have each pixel labeled with a class of interest label or background.
VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions
Comprehensive visual understanding requires detection frameworks that can effectively learn and utilize object interactions while analyzing objects individually.
Ranked #24 on
Human-Object Interaction Detection
on V-COCO
Predicting Clinical Outcome of Stroke Patients with Tractographic Feature
However, the presence of stroke lesion may cause neural disruptions to other brain regions, and these potentially damaged regions may affect the clinical outcome of stroke patients.
Improving 3D U-Net for Brain Tumor Segmentation by Utilizing Lesion Prior
We propose a novel, simple and effective method to integrate lesion prior and a 3D U-Net for improving brain tumor segmentation.
Predicting Fluid Intelligence of Children using T1-weighted MR Images and a StackNet
In this work, we utilize T1-weighted MR images and StackNet to predict fluid intelligence in adolescents.
Detecting GAN generated Fake Images using Co-occurrence Matrices
The advent of Generative Adversarial Networks (GANs) has brought about completely novel ways of transforming and manipulating pixels in digital images.
Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeries
This paper proposes a high-confidence manipulation localization architecture which utilizes resampling features, Long-Short Term Memory (LSTM) cells, and encoder-decoder network to segment out manipulated regions from non-manipulated ones.
Accurate 3D Cell Segmentation using Deep Feature and CRF Refinement
We consider the problem of accurately identifying cell boundaries and labeling individual cells in confocal microscopy images, specifically, 3D image stacks of cells with tagged cell membranes.
Deep Learning Methods for Event Verification and Image Repurposing Detection
The first method uses the features from the last convolutional layer of a pre-trained network as input to a classifier.
Automated Segmentation of CT Scans for Normal Pressure Hydrocephalus
The Evan's ratio, an approximation of the ratio of ventricle to brain volume using only one 2D slice of the scan, has been proposed but is not robust.
Actor Conditioned Attention Maps for Video Action Detection
While observing complex events with multiple actors, humans do not assess each actor separately, but infer from the context.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Brain Tumor Segmentation and Tractographic Feature Extraction from Structural MR Images for Overall Survival Prediction
For segmentation, we utilize an existing brain parcellation atlas in the MNI152 1mm space and map this parcellation to each individual subject data.
Resampling Forgery Detection Using Deep Learning and A-Contrario Analysis
A deep learning classifier is then used to generate a heatmap that indicates if the image block has been resampled.
Boosting Image Forgery Detection using Resampling Features and Copy-move analysis
Realistic image forgeries involve a combination of splicing, resampling, cloning, region removal and other methods.
An Order Preserving Bilinear Model for Person Detection in Multi-Modal Data
We propose a new order preserving bilinear framework that exploits low-resolution video for person detection in a multi-modal setting using deep neural networks.
Exploiting Spatial Structure for Localizing Manipulated Image Regions
In order to formulate the framework, we employ a hybrid CNN-LSTM model to capture discriminative features between manipulated and non-manipulated regions.
Weakly Supervised Manifold Learning for Dense Semantic Object Correspondence
We also leverage a key correspondence problem insight that the geometric structure between object parts is consistent across multiple object instances.
Optimizing Region Selection for Weakly Supervised Object Detection
This region selection procedure is further integrated into a CNN-based weakly supervised detection (WSD) framework, and can be performed in each stochastic gradient descent mini-batch during training.
Detection and Localization of Image Forgeries using Resampling Features and Deep Learning
In this paper, we propose two methods to detect and localize image manipulations based on a combination of resampling features and deep learning.
Summarization of ICU Patient Motion from Multimodal Multiview Videos
There is a small number of clinical studies, which use manual analysis of sleep poses and motion recordings to support medical benefits of patient positioning and motion monitoring.
Beyond Spatial Auto-Regressive Models: Predicting Housing Prices with Satellite Imagery
Spatial Auto-Regression (SAR) is a common tool used to model such data, where the spatial contiguity matrix (W) encodes the spatial correlations.
UAV Sensor Fusion With Latent-Dynamic Conditional Random Fields in Coronal Plane Estimation
We present a real-time body orientation estimation in a micro-Unmanned Air Vehicle video stream.
Weakly Supervised Localization using Deep Feature Maps
Object localization is an important computer vision problem with a variety of applications.
Ranked #4 on
Weakly Supervised Object Detection
on MS COCO
Eye-CU: Sleep Pose Classification for Healthcare using Multimodal Multiview Data
This work addresses these issues by introducing a new method and a new system for robust automated classification of sleep poses in an Intensive Care Unit (ICU) environment.
Search Tracker: Human-derived object tracking in-the-wild through large-scale search and retrieval
In this paper, we present a method to leverage human knowledge in the form of annotated video libraries in a novel search and retrieval based setting to track objects in unseen video sequences.
Weakly Supervised Graph Based Semantic Segmentation by Learning Communities of Image-Parts
We present a weakly-supervised approach to semantic segmentation.
Eye Tracking Assisted Extraction of Attentionally Important Objects From Videos
The proposed algorithm extracts dominant visual tracks using eye tracking data from multiple subjects on a video sequence by a combination of mean-shift clustering and Hungarian algorithm.
