Object Localization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 5
- 평가표
- 18
- 보존된 평가 기록
- 51
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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
O2V-Mapping: Online Open-Vocabulary Mapping with Neural Implicit Representation
MOSE: Boosting Vision-based Roadside 3D Object Detection with Scene Cues
FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery
Towards Two-Stream Foveation-based Active Vision Learning
Spatio-Temporal Bi-directional Cross-frame Memory for Distractor Filtering Point Cloud Single Object Tracking
IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models
Point-DETR3D: Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection
Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting
EcoSense: Energy-Efficient Intelligent Sensing for In-Shore Ship Detection through Edge-Cloud Collaboration
Few-shot Object Localization
Could We Generate Cytology Images from Histopathology Images? An Empirical Study
CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective
Weakly Supervised Monocular 3D Detection with a Single-View Image
The All-Seeing Project V2: Towards General Relation Comprehension of the Open World
Foveated Retinotopy Improves Classification and Localization in CNNs
Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
Toward Accurate Camera-based 3D Object Detection via Cascade Depth Estimation and Calibration
Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data
CPR++: Object Localization via Single Coarse Point Supervision
MsSVT++: Mixed-scale Sparse Voxel Transformer with Center Voting for 3D Object Detection
Spatial Structure Constraints for Weakly Supervised Semantic Segmentation
Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detection
Domain Adaptation for Large-Vocabulary Object Detectors
Bilateral Reference for High-Resolution Dichotomous Image Segmentation
GTA: Guided Transfer of Spatial Attention from Object-Centric Representations
LangSplat: 3D Language Gaussian Splatting
BEV-CV: Birds-Eye-View Transform for Cross-View Geo-Localisation
FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection
Dual Attention U-Net with Feature Infusion: Pushing the Boundaries of Multiclass Defect Segmentation
Object-Aware Domain Generalization for Object Detection
Weakly Supervised Open-Vocabulary Object Detection
Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance
Multiscale Vision Transformer With Deep Clustering-Guided Refinement for Weakly Supervised Object Localization
Mono3DVG: 3D Visual Grounding in Monocular Images
Boosting Segment Anything Model Towards Open-Vocabulary Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.