SOTAVerified

Object Localization

Object Localization is the task of locating an instance of a particular object category in an image, typically by specifying a tightly cropped bounding box centered on the instance. An object proposal specifies a candidate bounding box, and an object proposal is said to be a correct localization if it sufficiently overlaps a human-labeled “ground-truth” bounding box for the given object. In the literature, the “Object Localization” task is to locate one instance of an object category, whereas “object detection” focuses on locating all instances of a category in a given image.

Source: Fast On-Line Kernel Density Estimation for Active Object Localization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 617 papers

TitleStatusHype
Group-Wise Learning for Weakly Supervised Semantic SegmentationCode1
Background Activation Suppression for Weakly Supervised Object LocalizationCode1
DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse MotionCode1
TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNsCode1
UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language ModelingCode1
Rethinking Drone-Based Search and Rescue with Aerial Person DetectionCode1
Recognizing Vector Graphics without RasterizationCode1
Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object LocalizationCode1
Frustum-PointPillars: A Multi-Stage Approach for 3D Object Detection using RGB Camera and LiDARCode1
F-CAM: Full Resolution Class Activation Maps via Guided Parametric UpscalingCode1
DAFNe: A One-Stage Anchor-Free Approach for Oriented Object DetectionCode1
Learning Open-World Object Proposals without Learning to ClassifyCode1
Progressive Coordinate Transforms for Monocular 3D Object DetectionCode1
Boosting Weakly Supervised Object Detection via Learning Bounding Box AdjustersCode1
Shallow Feature Matters for Weakly Supervised Object LocalizationCode1
Normalization Matters in Weakly Supervised Object LocalizationCode1
LayerCAM: Exploring Hierarchical Class Activation Maps for LocalizationCode1
Keep CALM and Improve Visual Feature AttributionCode1
Team RUC_AIM3 Technical Report at ActivityNet 2021: Entities Object LocalizationCode1
DETReg: Unsupervised Pretraining with Region Priors for Object DetectionCode1
Improving Weakly-supervised Object Localization via Causal InterventionCode1
TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object LocalizationCode1
MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty PropagationCode1
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation ExploitationCode1
Unveiling the Potential of Structure Preserving for Weakly Supervised Object LocalizationCode1
InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual ReferringCode1
Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based ScoringCode1
EDN: Salient Object Detection via Extremely-Downsampled NetworkCode1
Contrastive Learning of Relative Position Regression for One-Shot Object Localization in 3D Medical ImagesCode1
CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point CloudCode1
RfD-Net: Point Scene Understanding by Semantic Instance ReconstructionCode1
TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency LossCode1
Faraway-Frustum: Dealing with Lidar Sparsity for 3D Object Detection using FusionCode1
Discriminative Sounding Objects Localization via Self-supervised Audiovisual MatchingCode1
Anchor-free Small-scale Multispectral Pedestrian DetectionCode1
Sketch-Guided Object Localization in Natural ImagesCode1
Rethinking Class Activation Mapping for Weakly Supervised Object LocalizationCode1
Eigen-CAM: Class Activation Map using Principal ComponentsCode1
Geometry Constrained Weakly Supervised Object LocalizationCode1
A Generic Visualization Approach for Convolutional Neural NetworksCode1
RepPoints V2: Verification Meets Regression for Object DetectionCode1
Training Interpretable Convolutional Neural Networks by Differentiating Class-specific FiltersCode1
Cross-Modal Weighting Network for RGB-D Salient Object DetectionCode1
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and DatasetsCode1
Mining Cross-Image Semantics for Weakly Supervised Semantic SegmentationCode1
Learning to Segment from Scribbles using Multi-scale Adversarial Attention GatesCode1
MoNet3D: Towards Accurate Monocular 3D Object Localization in Real TimeCode1
Distilling Knowledge from Refinement in Multiple Instance Detection NetworksCode1
Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAICode1
Dual-attention Guided Dropblock Module for Weakly Supervised Object LocalizationCode1
Show:102550
← PrevPage 3 of 13Next →
All datasetsREVERIEKITTI Cars EasyKITTI Pedestrians HardKITTI Pedestrians ModerateKITTI Cars HardKITTI Cyclists EasyKITTI Cyclists ModerateKITTI Pedestrians EasyGRITKITTI Cyclists HardIllusionVQAKITTI Cars Moderate

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OSMaNRGSPL32.99—Unverified
2SUSARGSPL27.31—Unverified
3ShanksRGSPL22.85—Unverified
4CVPR22RGSPL22.06—Unverified
5damm1RGSPL15.96—Unverified
61637RGSPL14.03—Unverified
7init. PREVALENTRGSPL13.51—Unverified
8AirbertRGSPL13.28—Unverified
9init. OSCARRGSPL10—Unverified
10SIARGSPL9.2—Unverified
#ModelMetricClaimedVerifiedStatus
1VoxelNetAP89.35—Unverified
2VoxelNetAP89.35—Unverified
3Frustum PointNetsAP88.7—Unverified
4Frustum PointNetsAP81.2—Unverified
5VoxelNetAP77.47—Unverified
#ModelMetricClaimedVerifiedStatus
1Frustrum-PointPillarsAP48.3—Unverified
2Frustum PointNetsAP47.2—Unverified
3Frustum PointNetsAP40.23—Unverified
4VoxelNetAP38.11—Unverified
5VoxelNetAP31.51—Unverified
#ModelMetricClaimedVerifiedStatus
1Frustrum-PointPillarsAP52.23—Unverified
2Frustum PointNetsAP50.22—Unverified
3Frustum PointNetsAP42.15—Unverified
4VoxelNetAP40.74—Unverified
5VoxelNetAP33.69—Unverified
#ModelMetricClaimedVerifiedStatus
1VoxelNetAP77.39—Unverified
2Frustum PointNetsAP75.33—Unverified
3Frustum PointNetsAP62.19—Unverified
4VoxelNetAP57.73—Unverified
#ModelMetricClaimedVerifiedStatus
1Frustum PointNetsAP75.38—Unverified
2Frustum PointNetsAP71.96—Unverified
3VoxelNetAP66.7—Unverified
4VoxelNetAP61.22—Unverified
#ModelMetricClaimedVerifiedStatus
1Frustum PointNetsAP61.96—Unverified
2Frustum PointNetsAP56.77—Unverified
3VoxelNetAP54.76—Unverified
4VoxelNetAP48.36—Unverified
#ModelMetricClaimedVerifiedStatus
1Frustum PointNetsAP58.09—Unverified
2Frustum PointNetsAP51.21—Unverified
3VoxelNetAP46.13—Unverified
4VoxelNetAP39.48—Unverified
#ModelMetricClaimedVerifiedStatus
1Unified-IOXLLocalization (ablation)67—Unverified
2GPV-2Localization (ablation)53.6—Unverified
3Mask R-CNNLocalization (ablation)44.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Frustum PointNetsAP54.68—Unverified
2VoxelNeAP50.55—Unverified
3Frustum PointNetsAP50.39—Unverified
#ModelMetricClaimedVerifiedStatus
1GPT4-Vision 4-shot+CoTAccuracy49.7—Unverified
2Gemini-Pro 4-shot+CoTAccuracy33.9—Unverified
#ModelMetricClaimedVerifiedStatus
1Frustum PointNetsAP84—Unverified
2VoxelNetAP79.26—Unverified
#ModelMetricClaimedVerifiedStatus
1Frustrum-PointPillarsAP60.98—Unverified
#ModelMetricClaimedVerifiedStatus
1Hausdorff LossPrecision88.1—Unverified
#ModelMetricClaimedVerifiedStatus
1oursCorLoc41.2—Unverified
#ModelMetricClaimedVerifiedStatus
1oursCorLoc47.45—Unverified
#ModelMetricClaimedVerifiedStatus
1Hausdorff LossF-Score88.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Hausdorff LossRecall89.2—Unverified