Research map / Video / Video segmentation and tracking
The Emergence of Objectness: Learning Zero-shot Segmentation from Videos
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use AMD instead of traditional low-level saliency methods | Zero-shot salient object detection · DUTS test | Fβ: 55.2 -> 60.2 | Helped |
| Use AMD instead of CIS | Zero-shot video object segmentation · DAVIS 2016 | Jaccard: 59.2 -> 57.8 | Hurt |
| Use AMD instead of CIS | Zero-shot video object segmentation · SegTrackv2 | Jaccard: 45.6 -> 57.0 | Helped |
| Use AMD instead of CIS | Zero-shot video object segmentation · FBMS59 | Jaccard: 36.8 -> 47.5 | Helped |
| Add test-time adaptation using both appearance and motion pathways (ablation) | AMD · DAVIS 2016 | Jaccard: 45.7 -> 57.8 | Helped |
| Add test-time adaptation using both appearance and motion pathways (ablation) | AMD · SegTrackv2 | Jaccard: 28.7 -> 57.0 | Helped |
| Add test-time adaptation using both appearance and motion pathways (ablation) | AMD · FBMS59 | Jaccard: 42.9 -> 47.5 | Helped |
| Use AMD instead of TimeCycle pretraining | Semantic segmentation transfer · Pascal VOC 2012 val | mIoU: 52.8 -> 62.0 | Helped |
| Use AMD rather than MoCo-v2 with light augmentation | Semantic segmentation transfer · Pascal VOC 2012 val | mIoU: 61.5 -> 62.0 | Helped |
| Use AMD rather than MoCo-v2 with heavy augmentation | Semantic segmentation transfer · Pascal VOC 2012 val | mIoU: 62.8 -> 62.1 | Hurt |
| Increase segment channels from 5 to 8 (ablation) | AMD · DAVIS 2016 | Jaccard | Hurt |
Closest papers by meaning
- Segment Any Motion in Videos (CVPR 2025 · similarity 0.88)
- Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuli (NeurIPS 2024 · similarity 0.88)
- Learning Segmentation from Point Trajectories (NeurIPS 2024 · similarity 0.88)
- DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut (NeurIPS 2024 · similarity 0.87)
- UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model (CVPR 2024 · similarity 0.87)
- unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning (ICML 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.