Scalable approach for object pose estimation across domains.
problem Object pose estimation across different datasets and models.
method Multi-path learning: shared encoder, object-specific decoders.
result Generalizes well from synthetic to real data and across various instances.
We introduce SARR for symmetric object pose estimation, improving CNN performance.
problem Ambiguities in symmetric object orientations hinder deep learning pose estimation.
method Numeric rotation representation using symmetry-derived trigonometric identities.
result SARR enables standard CNNs to achieve state-of-the-art performance.
We show that 3D gravity, in its pure connection formulation, admits a natural 6D interpretation. The 3D field equations for the connection are equivalent to 6D Hitchin equations for the Chern-Simons 3-form in the total space of the principal bundle over the 3-dimensional base. Turning this construction around one gets …
Local supertwistors help study 6D conformal supergravity.
problem Understanding conformal supergravity in 6D.
method Local supertwistor formalism with a superconformal connection.
result Derived geometry of (1,0) and (2,0) supergravity multiplets.
The full 6d Hopf-Wess-Zumino term in the action functional for the M5-brane is anomalous as traditionally defined. What has been missing is a condition implying the higher analogue of level quantization familiar from the 2d Wess-Zumino term. We prove that the anomaly cancellation condition is implied by the hypothesis …
The abstract discusses fiber sum formulas for 4-manifolds using topological modular forms.
problem Understanding fiber sum formulas for 4-manifolds.
method Using the connection between 4-manifolds and topological modular forms from 6d (1,0) SCFTs.
result Even free theories exhibit nontrivial fiber sum formulas, sensitive to individual theories and parameters.
Generic low-entropy hypersurfaces in 4-6D flow with only generic singularities.
problem Analyzing mean curvature flow of low-entropy hypersurfaces.
method Proving flow encounters only generic singularities for specific entropy conditions.
result Proves flow encounters only generic singularities for low-entropy initial data.
Study 6D localized matter spectrum on singular Calabi-Yau 3-folds.
problem Determining 6D localized charged matter spectrum on singular spaces.
method Using string junctions and SL(2,Z) monodromy to compute massless string junctions. result Agreement with 6D anomaly cancellation in all cases considered.
The paper proves transversality for special Lagrangian submanifolds in a 6D manifold.
problem Counting special Lagrangian submanifolds in higher dimensions.
method Proving transversality for the moduli space of perturbed special Lagrangian submanifolds using a Lagrange multipliers problem.
result The moduli space is generically a set of isolated points.
The paper derives curvature identities for 5D and 6D Einstein manifolds.
problem Deriving curvature identities for specific dimensions of Einstein manifolds.
method Using Patterson's curvature identities and the Chern-Gauss-Bonnet Theorem, the paper provides explicit formulae for 5D and 6D Einstein manifolds.
result The curvature identities for 5D and 6D Einstein manifolds are confirmed to be consistent with previous work.
We correct an error in the second part of Theorem 3 of our original paper (arXiv:1512.07161).
Extended symmetries and anomalies in compactified 6d SCFTs on various internal manifolds.
problem Understanding symmetries and anomalies in compactified 6d SCFTs.
method Extended notion of polarizations, focusing on 2D, 3D, and 4D manifolds.
result Recurring themes in compactifications, including Kaluza-Klein modes and symmetries.
Criterion found for blowing down in 6D symplectic geometry.
problem Blowing down criterion in 6D symplectic geometry.
method Criterion for blowing down in 6D symplectic geometry.
result Criterion established for blowing down in 6D symplectic geometry.
We build a connection between topology of smooth 4-manifolds and the theory of topological modular forms by considering topologically twisted compactification of 6d (1,0) theories on 4-manifolds with flavor symmetry backgrounds. The effective 2d theory has (0,1) supersymmetry and, possibly, a residual flavor symmetry. …
In this note we find the metric of 6-dimensional h-space of the [33] type and then determine an important projective group characteristic of this h-space.
Detect objects from motion without annotations.
problem Weakly supervised object detection.
method Train model on videos of moving objects and negative scenes.
result Detects objects in single images without annotations.
Proposes class-agnostic object detection to handle all objects without class labels.
problem Difficulty and cost in creating annotated datasets limit conventional object detection models to specific object types.
method Proposes class-agnostic object detection as a new problem and proposes training and evaluation protocols. Uses adversarial learning to exclude class-specific information.
result Adversarial learning improves class-agnostic detection efficacy.
Paper uses machine learning to detect dark matter subhalos in simulated Gaia DR2 data.
problem Detecting dark matter subhalos in simulated Gaia DR2 data.
method Proposed anomaly detection and classification-based approaches.
result Anomaly detection algorithm is sensitive to DM subhalos, but classification-based approach is not.
Researchers found solutions to minimal surface equations in 6D.
problem Equations of minimal surface type in six dimensions.
method Constructed nonlinear entire solutions using parametric elliptic functionals.
result Found solutions to minimal surface equations in 6D.
End-to-end method learns geometry and appearance for multi-view object detection.
problem Challenges in multi-view object detection, including viewpoint, lighting, and scale variability.
method Jointly learns multi-view geometry and warping for robust cross-view object detection.
result Superior performance compared to baselines on a new street-level panorama data set.
Paper presents attacks on real-time object detection systems.
problem Adversarial attacks on real-time object detection systems.
method Three targeted adversarial Objectness Gradient attacks (TOG).
result Adversarial attacks can cause object-vanishing, object-fabrication, and object-mislabeling.
Constructing of molecular structural models from Cryo-Electron Microscopy (Cryo-EM) density volumes is the critical last step of structure determination by Cryo-EM technologies. Methods have evolved from manual construction by structural biologists to perform 6D translation-rotation searching, which is extremely comput…
In this paper, we demonstrate a physical adversarial patch attack against object detectors, notably the YOLOv3 detector. Unlike previous work on physical object detection attacks, which required the patch to overlap with the objects being misclassified or avoiding detection, we show that a properly designed patch can s…
Polarimetric images enhance object detection in adverse weather conditions.
problem Object detection in road scenes is challenging in adverse weather conditions.
method Combining polarimetric imaging and deep learning.
result Polarimetry improves object detection by 20% to 50% compared to conventional RGB images.
We study the six-dimensional pseudo-Riemannian spaces with two time-like coordinates that admit non-homothetic infinitesimal projective transformations. The metrics are manifestly obtained and the projective group properties are determined. We also find a generic defining of projective motion in the 6-dimensional rigid…
Robots detect and recognize objects in real-time for better manipulation.
problem Real-time object detection and recognition for humanoid robots.
method Modified YOLOv3 algorithm, quantization, and re-arrangement of layers for low-compute NAO robots.
result Robots can perform real-time detection, recognition, and localization of objects.
Flat stable minimal hypersurfaces found in 6D space.
problem Existence of stable minimal hypersurfaces in R6. method Adapted Chodosh-Li-Minter-Stryker strategy with volume estimates.
result Complete, two-sided stable minimal hypersurfaces in R6 are flat. We propose UOLO, a novel framework for the simultaneous detection and segmentation of structures of interest in medical images. UOLO consists of an object segmentation module which intermediate abstract representations are processed and used as input for object detection. The resulting system is optimized simultaneousl…
New method calibrates confidence for object detection and segmentation models.
problem Intrinsically miscalibrated confidence estimates in object detection and segmentation models.
method Introduces multivariate confidence calibration for object detection and segmentation, extending ECE.
result Improves calibration, positively impacts segmentation quality.
Deep object detection improves mitotic nucleus detection in breast cancer biopsies.
problem Challenges in automated mitotic nucleus detection in breast cancer histopathological images.
method Adapted Mask R-CNN for deep object detection, initially selects candidate regions with maximum recall, refines them with multi-object loss function.
result Improved discrimination ability (F-score of 0.86) and significant precision (0.86) for mitotic nuclei compared to two-stage models.
Novel framework for unbiased confidence estimates in object detection.
problem Unbiased confidence estimates for safety-critical object detection.
method Combines regression output with additional information for calibration.
result Calibrated confidence estimates for image location and scale.
The Familiarity Hypothesis explains deep open set methods' success in detecting novel objects.
problem Detecting novel objects in open set recognition problems.
method Logits-based detection of absence of familiar features.
result Familiarity-based detection fails in scenarios with both novel and familiar objects.
Object detection models shipped with camera-equipped edge devices cannot cover the objects of interest for every user. Therefore, the incremental learning capability is a critical feature for a robust and personalized object detection system that many applications would rely on. In this paper, we present an efficient y…
A method detects vehicles far from tunnel CCTV using AI.
problem Tunnel CCTV's height limits detection of far-away vehicles.
method Object detection algorithm with inverse perspective transform.
result Deep learning model trained on warped images detects vehicles more accurately.
New methods detect objects in industrial settings with little training data.
problem Lack of training data limits object detection in industrial settings.
method Adapted Faster R-CNN and Scaled Yolov4-p5 architectures for small training data.
result Both models can distinguish unknown objects from homogeneous backgrounds.
Abstract M5 branes on ADE singularities yields BPS spectrum and partition functions.
problem Determine the BPS spectrum and partition functions for M5 branes on ADE singularities.
method Analyze 6d N=(1,0) SCFTs on geometric backgrounds, using contributions from BPS strings and particles. result Explicit expressions for BPS string and particle contributions to partition functions.
CST-YOLO improves blood cell detection with YOLOv7 and CNN-Swin Transformer.
problem Small-scale object detection in blood cells.
method YOLOv7 architecture enhanced with CNN-Swin Transformer, W-ELAN, MCS, CatConv.
result CST-YOLO achieves 92.7%, 95.6%, and 91.1% mAP@0.5 on three blood cell datasets.
The paper examines uncertainty calibration for object detection models in autonomous driving.
problem Uncertainty in object detection predictions and its calibration.
method Definition and evaluation of semantic and spatial uncertainty, calibration methods for uncertainty distributions.
result Calibrated uncertainty improves the overall performance of object detection models in real-world scenarios.
Graph neural networks detect anomalies in object-centric business processes.
problem Detecting anomalies in graph-like business processes.
method Graph convolutional autoencoder architecture for anomaly detection.
result Promising performance in detecting anomalies at the activity type and attributes level.
Study of ants' movement rules on a 6D space, revealing distribution structures and singular trajectories.
problem Understanding the movement patterns of ants in a 6D space.
method Analyzing mechanical system rules to derive distribution structures and singular trajectories.
result Distributions and singular trajectories of ants' movement rules in a 6D space.
New method improves object detection models for long-tailed datasets.
problem Classifier imbalance in long-tail object detection datasets.
method Balanced Group Softmax (BAGS) module for balanced training of classifiers.
result Significantly improves performance of object detection models.
xYOLO speeds up object detection on low-end hardware for humanoid soccer robots.
problem Real-time object detection on resource-constrained devices like Raspberry Pi.
method Adaptation of YOLO CNN model to achieve faster inference speed.
result Achieved 9.66 FPS on Raspberry Pi 3 B, 70x faster than Tiny-YOLO.
Cooperative perception improves 3D object detection in autonomous vehicles.
problem Limited field-of-view and occlusion in single sensor data.
method Early fusion of point clouds from multiple sensors, late fusion of independently detected bounding boxes, and hybrid combination.
result Early fusion approach outperforms late fusion by significantly higher recall (95%) compared to single-point sensing (30%).
The ability to detect objects regardless of image distortions or weather conditions is crucial for real-world applications of deep learning like autonomous driving. We here provide an easy-to-use benchmark to assess how object detection models perform when image quality degrades. The three resulting benchmark datasets,…
This paper proposes a technique for the unsupervised detection and tracking of arbitrary objects in videos. It is intended to reduce the need for detection and localization methods tailored to specific object types and serve as a general framework applicable to videos with varied objects, backgrounds, and image qualiti…
Study simplifies homotopy groups of 6D manifolds.
problem Homotopy groups of 6D manifolds.
method Double suspension homotopy decomposition.
result Easily determines K- and KO-groups. For many automated driving functions, a highly accurate perception of the vehicle environment is a crucial prerequisite. Modern high-resolution radar sensors generate multiple radar targets per object, which makes these sensors particularly suitable for the 2D object detection task. This work presents an approach to de…
A novel UNet detector detects sheep in UAV imagery.
problem Detecting small objects (sheep) in UAV imagery.
method Developed a novel dataset, used various object detectors, and evaluated their performance.
result UNet detector with weighted Hausdorff distance is best for sheep detection.