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

Showing 125 of 617 papers

TitleStatusHype
Qwen2.5-VL Technical ReportCode11
Bilateral Reference for High-Resolution Dichotomous Image SegmentationCode7
VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language TasksCode5
The All-Seeing Project V2: Towards General Relation Comprehension of the Open WorldCode4
Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language ModelsCode4
Mamba-FETrack: Frame-Event Tracking via State Space ModelCode4
CrossOver: 3D Scene Cross-Modal AlignmentCode3
LangSplat: 3D Language Gaussian SplattingCode3
DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile ManipulationCode3
Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3DCode3
Roboflow 100: A Rich, Multi-Domain Object Detection BenchmarkCode2
Omnidirectional Multi-Object TrackingCode2
Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object DetectionCode2
Point Segment and Count: A Generalized Framework for Object CountingCode2
BOP Challenge 2020 on 6D Object LocalizationCode2
C2AM: Contrastive Learning of Class-Agnostic Activation Map for Weakly Supervised Object Localization and Semantic SegmentationCode2
Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene GraphsCode2
Crafting Better Contrastive Views for Siamese Representation LearningCode2
Deep Snake for Real-Time Instance SegmentationCode2
A Novel Unified Architecture for Low-Shot Counting by Detection and SegmentationCode2
CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object DetectionCode2
Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic SegmentationCode2
Many-Shot In-Context Learning in Multimodal Foundation ModelsCode2
Background Activation Suppression for Weakly Supervised Object Localization and Semantic SegmentationCode1
CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point CloudCode1
Show:102550
← PrevPage 1 of 25Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OSMaNRGSPL32.99Unverified
2SUSARGSPL27.31Unverified
3ShanksRGSPL22.85Unverified
4CVPR22RGSPL22.06Unverified
5damm1RGSPL15.96Unverified
61637RGSPL14.03Unverified
7init. PREVALENTRGSPL13.51Unverified
8AirbertRGSPL13.28Unverified
9init. OSCARRGSPL10Unverified
10SIARGSPL9.2Unverified
#ModelMetricClaimedVerifiedStatus
1VoxelNetAP89.35Unverified
2VoxelNetAP89.35Unverified
3Frustum PointNetsAP88.7Unverified
4Frustum PointNetsAP81.2Unverified
5VoxelNetAP77.47Unverified
#ModelMetricClaimedVerifiedStatus
1Frustrum-PointPillarsAP48.3Unverified
2Frustum PointNetsAP47.2Unverified
3Frustum PointNetsAP40.23Unverified
4VoxelNetAP38.11Unverified
5VoxelNetAP31.51Unverified
#ModelMetricClaimedVerifiedStatus
1Frustrum-PointPillarsAP52.23Unverified
2Frustum PointNetsAP50.22Unverified
3Frustum PointNetsAP42.15Unverified
4VoxelNetAP40.74Unverified
5VoxelNetAP33.69Unverified
#ModelMetricClaimedVerifiedStatus
1VoxelNetAP77.39Unverified
2Frustum PointNetsAP75.33Unverified
3Frustum PointNetsAP62.19Unverified
4VoxelNetAP57.73Unverified
#ModelMetricClaimedVerifiedStatus
1Frustum PointNetsAP75.38Unverified
2Frustum PointNetsAP71.96Unverified
3VoxelNetAP66.7Unverified
4VoxelNetAP61.22Unverified
#ModelMetricClaimedVerifiedStatus
1Frustum PointNetsAP61.96Unverified
2Frustum PointNetsAP56.77Unverified
3VoxelNetAP54.76Unverified
4VoxelNetAP48.36Unverified
#ModelMetricClaimedVerifiedStatus
1Frustum PointNetsAP58.09Unverified
2Frustum PointNetsAP51.21Unverified
3VoxelNetAP46.13Unverified
4VoxelNetAP39.48Unverified
#ModelMetricClaimedVerifiedStatus
1Unified-IOXLLocalization (ablation)67Unverified
2GPV-2Localization (ablation)53.6Unverified
3Mask R-CNNLocalization (ablation)44.7Unverified
#ModelMetricClaimedVerifiedStatus
1Frustum PointNetsAP54.68Unverified
2VoxelNeAP50.55Unverified
3Frustum PointNetsAP50.39Unverified
#ModelMetricClaimedVerifiedStatus
1GPT4-Vision 4-shot+CoTAccuracy49.7Unverified
2Gemini-Pro 4-shot+CoTAccuracy33.9Unverified
#ModelMetricClaimedVerifiedStatus
1Frustum PointNetsAP84Unverified
2VoxelNetAP79.26Unverified
#ModelMetricClaimedVerifiedStatus
1Frustrum-PointPillarsAP60.98Unverified
#ModelMetricClaimedVerifiedStatus
1Hausdorff LossPrecision88.1Unverified
#ModelMetricClaimedVerifiedStatus
1oursCorLoc41.2Unverified
#ModelMetricClaimedVerifiedStatus
1oursCorLoc47.45Unverified
#ModelMetricClaimedVerifiedStatus
1Hausdorff LossF-Score88.6Unverified
#ModelMetricClaimedVerifiedStatus
1Hausdorff LossRecall89.2Unverified