Toward Open-World Video Segmentation over Long Horizons

arXiv:2606.15632 · cs.CV · Submitted 2026-06-14 · Read on arXiv

cs.CV

Submitted: 2026-06-14

Updated: 2026-10-06

Code: https://github.com/QingSuML/savvy

Project page: https://qingsuml.github.io/savvy

Terminology

• Benchmark — 54× in this paper · explained in 2 episodes
• Consistency — 32× in this paper · explained in 3 episodes
• Deferred Admission — 31× in this paper
• Fidelity — 27× in this paper · explained in 2 episodes
• Track Consolidation — 26× in this paper
• Granularity Mismatch — 18× in this paper · explained in 2 episodes
• Self-consistency — 18× in this paper · explained in 2 episodes
• Ablation — 13× in this paper · explained in 1 episode
• Core — 13× in this paper · explained in 2 episodes
• Failure Modes — 13× in this paper · explained in 3 episodes
• Pruning — 12× in this paper · explained in 4 episodes
• Robustness — 6× in this paper · explained in 5 episodes
• Aggregation — 4× in this paper · explained in 1 episode
• Alignment — 4× in this paper · explained in 1 episode
• Redundancy — 4× in this paper · explained in 2 episodes
• Clustering — 3× in this paper · explained in 2 episodes
• Ontology — 3× in this paper · explained in 2 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Admissibility — 2× in this paper · explained in 2 episodes
• Credit assignment — 2× in this paper · explained in 3 episodes
• Embodied AI — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Appearance Gate — 1× in this paper · explained in 1 episode
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Exponential Moving Average (EMA) — 1× in this paper · explained in 2 episodes
• Instance Segmentation — 1× in this paper · explained in 3 episodes
• Mask Generation — 1× in this paper · explained in 2 episodes
• Savvy Hierarchical Mask Discovery — 1× in this paper
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Mask2Former for Video Instance Segmentation
• The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines
• Solving the Maximum-Weight Connected Subgraph Problem to Optimality
• DINOv2: Learning Robust Visual Features without Supervision
• Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI
• SAM 2: Segment Anything in Images and Videos
• STEP: Segmenting and Tracking Every Pixel

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models