No article text was recorded for this version.
unsupervised object discovery
Version 1 of 164 papers65 conceptsfrozen 2026-10-04
Papers in this version
- Blog: The Background Also Matters: Background-Aware Motion-Guided Objects Discovery
- Blog: Object Concepts Emerge from Motion
- Blog: Unsupervised Video Object Segmentation Using Motion Saliency-Guided Spatio-Temporal Propagation
- Blog: Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation
- Blog: Reciprocal Transformations for Unsupervised Video Object Segmentation
- Blog: RVOS: End-To-End Recurrent Network for Video Object Segmentation
- Blog: Learning Video Salient Object Detection Progressively From Unlabeled Videos
- Blog: Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
- Blog: Disentangling Video with Independent Prediction
- Blog: Object-Region Video Transformers
- Blog: UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking
- Blog: Learning 3D Object Categories by Looking Around Them
- Blog: Automatic Video Object Segmentation via Motion-Appearance-Stream Fusion and Instance-aware Segmentation
- Blog: Autonomous Development of a Grounded Object Ontology by a Learning Robot
- Blog: Towards Automatic Discovery of Object Categories
- Blog: Saliency-aware geodesic video object segmentation
- Blog: Anchor Diffusion for Unsupervised Video Object Segmentation
- Blog: Primary Object Segmentation in Videos via Alternate Convex Optimization of Foreground and Background Distributions
- Blog: Moving Off-the-Grid: Scene-Grounded Video Representations
- Blog: Auto-Vocabulary Semantic Segmentation
- Blog: Unsupervised Object Discovery and Tracking in Video Collections
- Blog: Discover and Learn New Objects from Documentaries
- Blog: Unsupervised Video Object Segmentation via Prototype Memory Network
- Blog: Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaboration
- Blog: Video Object Segmentation by Latent Outcome Regression
- Blog: RVAS: Referring Video Active Exploration and Segmentation
- Blog: COBE: Contextualized Object Embeddings from Narrated Instructional Video
- Blog: LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training
- Blog: Mask Selection and Propagation for Unsupervised Video Object Segmentation
- Blog: Unsupervised Deep Representation Learning for Real-Time Tracking
- Blog: Structured Object-Aware Physics Prediction for Video Modeling and Planning
- Blog: Guided Slot Attention for Unsupervised Video Object Segmentation
- Blog: Learning a Visual Tracker from a Single Movie without Annotation
- Blog: Look, Listen and Learn
- Blog: Deep Object Co-Segmentation via Spatial-Semantic Network Modulation
- Blog: Unsupervised Learning from Videos for Object Discovery in Single Images
- Blog: ObPose: Leveraging Pose for Object-Centric Scene Inference and Generation in 3D
- Blog: FreeSOLO: Learning to Segment Objects without Annotations
- Blog: Reducing the Annotation Effort for Video Object Segmentation Datasets
- Blog: Emergence of Object Segmentation in Perturbed Generative Models
- Blog: DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
- Blog: Associating Objects with Transformers for Video Object Segmentation
- Blog: Semantic Single Video Segmentation with Robust Graph Representation
- Blog: SAFFIRE: System for Autonomous Feature Filtering and Intelligent ROI Estimation
- Blog: See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks
- Blog: Video Segmentation by Tracking Many Figure-Ground Segments
- Blog: Intuitive physics learning in a deep-learning model inspired by developmental psychology
- Blog: Object Discovery and Representation Networks
- Blog: Unsupervised Video Object Segmentation via Prototype Memory Network
- Blog: Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation
- Blog: Object Discovery in Videos as Foreground Motion Clustering
- Blog: Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation
- Blog: Entity Abstraction in Visual Model-Based Reinforcement Learning
- Blog: Learning Unsupervised Video Object Segmentation Through Visual Attention
- Blog: An Efficient 3D CNN for Action/Object Segmentation in Video
- Blog: Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers
- Blog: Unsupervised Segmentation in Real-World Images via Spelke Object Inference
- Blog: Continual Learning of Conjugated Visual Representations through Higher-order Motion Flows
- Blog: Are We Done with Object-Centric Learning?
- Blog: Mask-Free Video Instance Segmentation
Showing 60 of 64 papers.
History & citation
Current · Permanent link
- This direction split from Autonomous Discovery and Segmentation of Objects in Video (56% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_unsupervised_object_discovery_5c774dc8,
title = {unsupervised object discovery},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/unsupervised-object-discovery/rdr_5c774dc888bd4d42905173aa1ccd5367},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_unsupervised_object_discovery_5c774dc8_v1,
title = {unsupervised object discovery},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/unsupervised-object-discovery/rdr_5c774dc888bd4d42905173aa1ccd5367/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}