SOTAVerified

Object Discovery

Object Discovery is the task of identifying previously unseen objects.

Source: Unsupervised Object Discovery and Segmentation of RGBD-images

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–175 of 210 papers

TitleStatusHype
XS-VID: An Extremely Small Video Object Detection Dataset—0
3D Object Discovery and Modeling Using Single RGB-D Images Containing Multiple Object Instances—0
Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset—0
Multi-Label Self-Supervised Learning with Scene Images—0
Multi-Object Discovery by Low-Dimensional Object Motion—0
Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations—0
Object-Category Aware Reinforcement Learning—0
Object Discovery in Videos as Foreground Motion Clustering—0
Object Discovery via Cohesion Measurement—0
Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory—0
Out of Sight, Still in Mind: Reasoning and Planning about Unobserved Objects with Video Tracking Enabled Memory Models—0
OV-SCAN: Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection—0
Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries—0
PatchCut: Data-Driven Object Segmentation via Local Shape Transfer—0
PatchNet: Unsupervised Object Discovery based on Patch Embedding—0
Pixel Objectness—0
POD: Discovering Primary Objects in Videos Based on Evolutionary Refinement of Object Recurrence, Background, and Primary Object Models—0
Pushing the envelope in deep visual recognition for mobile platforms—0
MONet: Unsupervised Scene Decomposition and RepresentationCode0
Entity Abstraction in Visual Model-Based Reinforcement LearningCode0
Box-based Refinement for Weakly Supervised and Unsupervised Localization TasksCode0
Efficient Dialog Policy Learning via Positive Memory RetentionCode0
Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in VideosCode0
Boosting Object Representation Learning via Motion and Object ContinuityCode0
MoDA: Leveraging Motion Priors from Videos for Advancing Unsupervised Domain Adaptation in Semantic SegmentationCode0
Show:102550
← PrevPage 7 of 9Next →

No leaderboard results yet.