SOTAVerified

Object Proposal Generation

Object proposal generation is a preprocessing technique that has been widely used in current object detection pipelines to guide the search of objects and avoid exhaustive sliding window search across images.

( Image credit: Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 54 papers

TitleStatusHype
Adapting Pre-Trained Vision Models for Novel Instance Detection and SegmentationCode2
Towards Addressing the Misalignment of Object Proposal Evaluation for Vision-Language Tasks via Semantic GroundingCode0
Small, but important: Traffic light proposals for detecting small traffic lights and beyond—0
Fast Segment AnythingCode0
SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous DrivingCode0
4D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and AggregationCode1
Segmenting Medical Instruments in Minimally Invasive Surgeries using AttentionMask—0
Localizing Small Apples in Complex Apple Orchard Environments—0
ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues—0
Class-agnostic Object Detection with Multi-modal TransformerCode1
DeepFH Segmentations for Superpixel-based Object Proposal Refinement—0
Superpixel-based Refinement for Object Proposal GenerationCode1
You Don't Only Look Once: Constructing Spatial-Temporal Memory for Integrated 3D Object Detection and Tracking—0
3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds—0
3D Object Detection with PointformerCode1
UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object DetectionCode1
Improving Point Cloud Semantic Segmentation by Learning 3D Object Detection—0
What leads to generalization of object proposals?—0
Real-time 3D object proposal generation and classification under limited processing resources—0
Relation Graph Network for 3D Object Detection in Point Clouds—0
PointRCNN: 3D Object Proposal Generation and Detection from Point CloudCode1
AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small ObjectsCode0
Deep Learning for Generic Object Detection: A Survey—0
Semantic Edge Detection with Diverse Deep SupervisionCode0
A New Target-specific Object Proposal Generation Method for Visual Tracking—0
Object cosegmentation using deep Siamese network—0
Deep Crisp Boundaries: From Boundaries to Higher-level Tasks—0
Recurrent Pixel Embedding for Instance GroupingCode0
SalProp: Salient object proposals via aggregated edge cues—0
CASENet: Deep Category-Aware Semantic Edge DetectionCode0
Object Discovery via Cohesion Measurement—0
ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond—0
Object proposal generation applying the distance dependent Chinese restaurant processCode0
Semantic Instance Segmentation via Deep Metric LearningCode0
Boundary-aware Instance Segmentation—0
Learning to Segment Object Candidates via Recursive Neural Networks—0
Multi-View 3D Object Detection Network for Autonomous DrivingCode0
Multi-stage Object Detection with Group Recursive Learning—0
Multi-Scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation—0
Monocular 3D Object Detection for Autonomous Driving—0
Selective Convolutional Descriptor Aggregation for Fine-Grained Image RetrievalCode1
Seq-NMS for Video Object DetectionCode0
Generating Discriminative Object Proposals via Submodular Ranking—0
Learning to Combine Mid-Level Cues for Object Proposal Generation—0
SubmodBoxes: Near-Optimal Search for a Set of Diverse Object Proposals—0
Sequential Optimization for Efficient High-Quality Object Proposal Generation—0
Manipulated Object Proposal: A Discriminative Object Extraction and Feature Fusion Framework for First-Person Daily Activity Recognition—0
Object Detection by Labeling Superpixels—0
Traditional Saliency Reloaded: A Good Old Model in New Shape—0
Convolutional Channel FeaturesCode0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.