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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 101–125 of 617 papers

Title	Date	Tasks	Status	Hype
Background Activation Suppression for Weakly Supervised Object Localization	Dec 1, 2021	ObjectObject Localization	CodeCode Available	1
Group-Wise Learning for Weakly Supervised Semantic Segmentation	Dec 1, 2021	Graph Neural NetworkObject Localization	CodeCode Available	1
DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion	Nov 29, 2021	Multi-Object TrackingObject	CodeCode Available	1
TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs	Nov 26, 2021	feature selectionImage Classification	CodeCode Available	1
UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling	Nov 23, 2021	Image CaptioningImage Description	CodeCode Available	1
Rethinking Drone-Based Search and Rescue with Aerial Person Detection	Nov 17, 2021	Data AugmentationHuman Detection	CodeCode Available	1
Recognizing Vector Graphics without Rasterization	Nov 5, 2021	Graph Neural Networkobject-detection	CodeCode Available	1
Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization	Oct 12, 2021	ObjectObject Localization	CodeCode Available	1
Frustum-PointPillars: A Multi-Stage Approach for 3D Object Detection using RGB Camera and LiDAR	Oct 11, 2021	2D Object Detection3D Object Detection	CodeCode Available	1
F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling	Sep 15, 2021	Object LocalizationWeakly-Supervised Object Localization	CodeCode Available	1
DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection	Sep 13, 2021	object-detectionObject Detection	CodeCode Available	1
Learning Open-World Object Proposals without Learning to Classify	Aug 15, 2021	Objectobject-detection	CodeCode Available	1
Progressive Coordinate Transforms for Monocular 3D Object Detection	Aug 12, 2021	3D Object DetectionAI Agent	CodeCode Available	1
Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters	Aug 3, 2021	Objectobject-detection	CodeCode Available	1
Shallow Feature Matters for Weakly Supervised Object Localization	Aug 2, 2021	ObjectObject Localization	CodeCode Available	1
Normalization Matters in Weakly Supervised Object Localization	Jul 28, 2021	ObjectObject Localization	CodeCode Available	1
LayerCAM: Exploring Hierarchical Class Activation Maps for Localization	Jun 22, 2021	ObjectObject Localization	CodeCode Available	1
Keep CALM and Improve Visual Feature Attribution	Jun 15, 2021	Object LocalizationWeakly-Supervised Object Localization	CodeCode Available	1
Team RUC_AIM3 Technical Report at ActivityNet 2021: Entities Object Localization	Jun 11, 2021	Caption GenerationObject	CodeCode Available	1
DETReg: Unsupervised Pretraining with Region Priors for Object Detection	Jun 8, 2021	Few-Shot LearningFew-Shot Object Detection	CodeCode Available	1
Improving Weakly-supervised Object Localization via Causal Intervention	Apr 21, 2021	ObjectObject Localization	CodeCode Available	1
TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization	Mar 27, 2021	ObjectObject Localization	CodeCode Available	1
MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation	Mar 23, 2021	3D Object DetectionMonocular 3D Object Detection	CodeCode Available	1
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation	Mar 22, 2021	Few-Shot Object DetectionMeta-Learning	CodeCode Available	1
Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization	Mar 8, 2021	ClassificationGeneral Classification	CodeCode Available	1

Show:10 25 50

← PrevPage 5 of 25Next →

All datasets REVERIE KITTI Cars Easy KITTI Pedestrians Hard KITTI Pedestrians Moderate KITTI Cars Hard KITTI Cyclists Easy KITTI Cyclists Moderate KITTI Pedestrians Easy GRIT KITTI Cyclists Hard IllusionVQA KITTI Cars Moderate

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	OSMaN	RGSPL	32.99	—	Unverified
2	SUSA	RGSPL	27.31	—	Unverified
3	Shanks	RGSPL	22.85	—	Unverified
4	CVPR22	RGSPL	22.06	—	Unverified
5	damm1	RGSPL	15.96	—	Unverified
6	1637	RGSPL	14.03	—	Unverified
7	init. PREVALENT	RGSPL	13.51	—	Unverified
8	Airbert	RGSPL	13.28	—	Unverified
9	init. OSCAR	RGSPL	10	—	Unverified
10	SIA	RGSPL	9.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	VoxelNet	AP	89.35	—	Unverified
2	VoxelNet	AP	89.35	—	Unverified
3	Frustum PointNets	AP	88.7	—	Unverified
4	Frustum PointNets	AP	81.2	—	Unverified
5	VoxelNet	AP	77.47	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Frustrum-PointPillars	AP	48.3	—	Unverified
2	Frustum PointNets	AP	47.2	—	Unverified
3	Frustum PointNets	AP	40.23	—	Unverified
4	VoxelNet	AP	38.11	—	Unverified
5	VoxelNet	AP	31.51	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Frustrum-PointPillars	AP	52.23	—	Unverified
2	Frustum PointNets	AP	50.22	—	Unverified
3	Frustum PointNets	AP	42.15	—	Unverified
4	VoxelNet	AP	40.74	—	Unverified
5	VoxelNet	AP	33.69	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	VoxelNet	AP	77.39	—	Unverified
2	Frustum PointNets	AP	75.33	—	Unverified
3	Frustum PointNets	AP	62.19	—	Unverified
4	VoxelNet	AP	57.73	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Frustum PointNets	AP	75.38	—	Unverified
2	Frustum PointNets	AP	71.96	—	Unverified
3	VoxelNet	AP	66.7	—	Unverified
4	VoxelNet	AP	61.22	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Frustum PointNets	AP	61.96	—	Unverified
2	Frustum PointNets	AP	56.77	—	Unverified
3	VoxelNet	AP	54.76	—	Unverified
4	VoxelNet	AP	48.36	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Frustum PointNets	AP	58.09	—	Unverified
2	Frustum PointNets	AP	51.21	—	Unverified
3	VoxelNet	AP	46.13	—	Unverified
4	VoxelNet	AP	39.48	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Unified-IOXL	Localization (ablation)	67	—	Unverified
2	GPV-2	Localization (ablation)	53.6	—	Unverified
3	Mask R-CNN	Localization (ablation)	44.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Frustum PointNets	AP	54.68	—	Unverified
2	VoxelNe	AP	50.55	—	Unverified
3	Frustum PointNets	AP	50.39	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GPT4-Vision 4-shot+CoT	Accuracy	49.7	—	Unverified
2	Gemini-Pro 4-shot+CoT	Accuracy	33.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Frustum PointNets	AP	84	—	Unverified
2	VoxelNet	AP	79.26	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Frustrum-PointPillars	AP	60.98	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Hausdorff Loss	Precision	88.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ours	CorLoc	41.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ours	CorLoc	47.45	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Hausdorff Loss	F-Score	88.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Hausdorff Loss	Recall	89.2	—	Unverified