Search Results for author:
Found 32 papers, 4 papers with code
UAV-Sim: NeRF-based Synthetic Data Generation for UAV-based Perception
Using various synthetic renderers in conjunction with perception models is prevalent to create synthetic data to augment the learning in the ground-based imaging domain.
Novel Categories Discovery Via Constraints on Empirical Prediction Statistics
As an alternative to the traditional pseudo-labeling-based approaches, we leverage the connection between the data sampling and the provided multinoulli (categorical) distribution of novel classes.
NEV-NCD: Negative Learning, Entropy, and Variance regularization based novel action categories discovery
During our experiments with UCF101 and multi-view action dataset, NEV-NCD achieves ~ 83% classification accuracy in test instances of labeled data.
Progressive Transformation Learning for Leveraging Virtual Images in Training
To effectively interrogate UAV-based images for detecting objects of interest, such as humans, it is essential to acquire large-scale UAV-based datasets that include human instances with various poses captured from widely varying viewing angles.
Archangel: A Hybrid UAV-based Human Detection Benchmark with Position and Pose Metadata
Learning to detect objects, such as humans, in imagery captured by an unmanned aerial vehicle (UAV) usually suffers from tremendous variations caused by the UAV's position towards the objects.
Negative Samples are at Large: Leveraging Hard-distance Elastic Loss for Re-identification
We present a Momentum Re-identification (MoReID) framework that can leverage a very large number of negative samples in training for general re-identification task.
A Multi-purpose Realistic Haze Benchmark with Quantifiable Haze Levels and Ground Truth
The full dataset presented in this paper, including the ground truth object classification bounding boxes and haze density measurements, is provided for the community to evaluate their algorithms at: https://a2i2-archangel. vision.
Exploring Cross-Domain Pretrained Model for Hyperspectral Image Classification
In addition, we have verified that our approach effectively reduces the overfitting issue, enabling us to deepen the model up to 13 layers (from 9) without compromising the accuracy.
DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors
In this paper, we propose a novel and highly practical score-level fusion approach called dynamic belief fusion (DBF) that directly integrates inference scores of individual detections from multiple object detection methods.
Self-supervised Contrastive Learning for Cross-domain Hyperspectral Image Representation
Recently, self-supervised learning has attracted attention due to its remarkable ability to acquire meaningful representations for classification tasks without using semantic labels.
Validation of object detection in UAV-based images using synthetic data
Using the synthetic datasets, we analyze detection accuracy in different imaging conditions as a function of the above parameters.
SENSE: Semantically Enhanced Node Sequence Embedding
Effectively capturing graph node sequences in the form of vector embeddings is critical to many applications.
Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach
Object detection from images captured by Unmanned Aerial Vehicles (UAVs) is becoming increasingly useful.
Semantics to Space(S2S): Embedding semantics into spatial space for zero-shot verb-object query inferencing
Our approach is powered by Semantics-to-Space (S2S) architecture where semantics derived from the residing objects are embedded into a spatial space of the visual stream.
Integrating Propositional and Relational Label Side Information for Hierarchical Zero-Shot Image Classification
Zero-shot learning (ZSL) is one of the most extreme forms of learning from scarce labeled data.
S-DOD-CNN: Doubly Injecting Spatially-Preserved Object Information for Event Recognition
We present a novel event recognition approach called Spatially-preserved Doubly-injected Object Detection CNN (S-DOD-CNN), which incorporates the spatially preserved object detection information in both a direct and an indirect way.
Is Pretraining Necessary for Hyperspectral Image Classification?
To answer the first question, we have devised an approach that pre-trains a network on multiple source datasets that differ in their hyperspectral characteristics and fine-tunes on a target dataset.
Generating Hard Examples for Pixel-wise Classification
To overcome the problem of the data scarcity and lack of hard examples in training, we introduce a two-step hard example generation (HEG) approach that first generates hard example candidates and then mines actual hard examples.
DOD-CNN: Doubly-injecting Object Information for Event Recognition
Recognizing an event in an image can be enhanced by detecting relevant objects in two ways: 1) indirectly utilizing object detection information within the unified architecture or 2) directly making use of the object detection output results.
Can You Spot the Semantic Predicate in this Video?
We propose a method to improve human activity recognition in video by leveraging semantic information about the target activities from an expert-defined linguistic resource, VerbNet.
Object and Text-guided Semantics for CNN-based Activity Recognition
We further improve upon the multitask learning approach by exploiting a text-guided semantic space to select the most relevant objects with respect to the target activities.
Cross-domain CNN for Hyperspectral Image Classification
To cope with this problem, we propose a novel cross-domain CNN containing the shared parameters which can co-learn across multiple hyperspectral datasets.
ME R-CNN: Multi-Expert R-CNN for Object Detection
To address this problem, we introduce a practical training strategy which is tailored to optimize ME, EAN, and the shared network in an end-to-end fashion.
IOD-CNN: Integrating Object Detection Networks for Event Recognition
Many previous methods have showed the importance of considering semantically relevant objects for performing event recognition, yet none of the methods have exploited the power of deep convolutional neural networks to directly integrate relevant object information into a unified network.
Enhanced Object Detection via Fusion With Prior Beliefs from Image Classification
The prior knowledge is then fused with the decisions of object detection to improve detection accuracy by mitigating false positives of an object detector that are strongly contradicted with the prior knowledge.
Exploitation of Semantic Keywords for Malicious Event Classification
Learning an event classifier is challenging when the scenes are semantically different but visually similar.
DTM: Deformable Template Matching
A novel template matching algorithm that can incorporate the concept of deformable parts, is presented in this paper.
Fast Object Localization Using a CNN Feature Map Based Multi-Scale Search
Object localization is an important task in computer vision but requires a large amount of computational power due mainly to an exhaustive multiscale search on the input image.
Going Deeper with Contextual CNN for Hyperspectral Image Classification
The initial spatial and spectral feature maps obtained from the multi-scale filter bank are then combined together to form a joint spatio-spectral feature map.
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
Dynamic Belief Fusion for Object Detection
A novel approach for the fusion of heterogeneous object detection methods is proposed.
Optimal Sparse Kernel Learning for Hyperspectral Anomaly Detection
In this paper, a novel framework of sparse kernel learning for Support Vector Data Description (SVDD) based anomaly detection is presented.
