Presents the first multispectral dataset for fine-grained small-UAV detection and a dual-stream MFDNet baseline that gains 6.2% AP50 over RGB-only detectors by using spectral material cues.
hub
Objects as Points
30 Pith papers cite this work. Polarity classification is still indexing.
30
Pith papers citing it
abstract
Detection identifies objects as axis-aligned boxes in an image. Most successful object detectors enumerate a nearly exhaustive list of potential object locations and classify each. This is wasteful, inefficient, and requires additional post-processing. In this paper, we take a different approach. We model an object as a single point --- the center point of its bounding box. Our detector uses keypoint estimation to find center points and regresses to all other object properties, such as size, 3D location, orientation, and even pose. Our center point based approach, CenterNet, is end-to-end differentiable, simpler, faster, and more accurate than corresponding bounding box based detectors. CenterNet achieves the best speed-accuracy trade-off on the MS COCO dataset, with 28.1% AP at 142 FPS, 37.4% AP at 52 FPS, and 45.1% AP with multi-scale testing at 1.4 FPS. We use the same approach to estimate 3D bounding box in the KITTI benchmark and human pose on the COCO keypoint dataset. Our method performs competitively with sophisticated multi-stage methods and runs in real-time.
hub tools
citation-role summary
background 1
baseline 1
dataset 1
method 1
citation-polarity summary
representative citing papers
MoCA3D formulates monocular 3D box prediction as dense pixel-space tasks using corner heatmaps and depth maps, with a new PAG metric for image-plane evaluation.
Grayscale diffusion model generates two-layer RF passives with sub-pixel resolution from partial S-parameters, achieving low error in surrogate predictions and validated on fabricated filters.
SARR modifies trigonometric rotation encodings with object symmetry orders to produce unique continuous poses, enabling standard CNNs to outperform existing methods on symmetry-aware 6D pose estimation without custom losses or 3D models.
FishRoPE reparameterizes attention mechanisms in fisheye images to use angular separation in spherical coordinates, enabling frozen vision foundation models to achieve state-of-the-art results on 2D detection and BEV segmentation benchmarks.
DinoRADE reports a radar-centered multi-class detection pipeline that fuses dense radar tensors with DINOv3 features via deformable attention and outperforms prior radar-camera methods by 12.1% on the K-Radar dataset across weather conditions.
WUTDet is a 100K-image ship detection dataset with benchmarks indicating Transformer models outperform CNN and Mamba architectures in accuracy and small-object detection for complex maritime environments.
L2G-Det detects and segments novel object instances in open scenes by using local template patch matches to generate points that prompt an augmented SAM for global masks.
PEPR reframes learning with privileged event data as predicting latent event features from RGB to improve domain generalization in object detection and segmentation without direct cross-modal alignment.
ThinkDeeper introduces a world-model-based reasoning step that predicts future spatial states to improve multimodal visual grounding for autonomous vehicles, achieving top results on Talk2Car and other benchmarks.
A tip-handle detection network based on HRNet combined with greedy matching outperforms nnUNet segmentation for multi-needle localization in pelvic brachytherapy CT images on a 100-patient dataset.
BEVDet achieves 39.3% mAP and 47.2% NDS on nuScenes val set with a fast BEV-based multi-camera 3D detector that outperforms FCOS3D while using far less compute in its tiny variant.
FS-FSD regresses frequency-supervised Fourier contours for bridge defects, yielding higher polygon accuracy and better geometric quality than box, mask, or contour baselines on 3,767 UAV images with 42,346 instances.
RefCD enables unsupervised category-aware object detection by using feature similarity between predicted objects and unlabeled reference images to guide category learning.
Telescope uses learnable hyperbolic foveation to deliver a 76% relative mAP gain (0.185 to 0.326) for objects beyond 250 meters while keeping overhead low.
SFFNet uses multi-scale dynamic dual-domain coupling and a synergistic feature pyramid network to reach 36.8 AP on VisDrone and 20.6 AP on UAVDT for UAV object detection.
Grounding DINO fuses language and vision via feature enhancer, language-guided query selection, and cross-modality decoder in a DINO backbone, achieving 52.5 AP zero-shot on COCO and a new record of 26.1 AP mean on ODinW.
YOLOX exceeds prior YOLO models by adopting anchor-free detection, decoupled heads, and SimOTA assignment to reach 50.0% AP on COCO for the large variant.
OCD SLAM adds cross-disparity inconsistency checks and object-level motion classification to ORB-SLAM2, reporting better trajectory accuracy than prior dynamic SLAM methods on KITTI sequences.
A vision-language model outputs dual heatmaps for navigation affordance and facing to ground semantic instructions into executable free space, achieving higher affordance rates than waypoint regression across simulated robot embodiments.
TCMP achieves SOTA MOT metrics (HOTA 63.4%, IDF1 65.0%, AssA 49.1%) with 0.014x parameters and 0.05x FLOPs of the previous best method by using a simple dilated TCN regressor.
Caries-DETR adds tooth-structure query initialization and lesion-aware loss reweighting to DETR, reaching state-of-the-art caries detection on AlphaDent and DentalAI datasets.
A new class-adaptive fusion architecture improves multi-class LiDAR 3D object detection in V2X cooperative perception by routing small and large objects through attentive pathways and balancing training objectives.
A multi-task JEPA-pretrained Vision Transformer achieves 0.949 AUC for cancer triage and 0.953 AUC for binary density classification after training on 71k studies from 14 sites.
citing papers explorer
-
Contour-Native Bridge Defect Detection and Compact Digital Archiving with Frequency-Supervised Fourier Contours
FS-FSD regresses frequency-supervised Fourier contours for bridge defects, yielding higher polygon accuracy and better geometric quality than box, mask, or contour baselines on 3,767 UAV images with 42,346 instances.