AI Paper Atlas

Research map / Video / Video segmentation and tracking

DIMOS: Disentangling Instance-level Moving Object Segmentation

Hongxiang Huang, Hongwei Ren, Xiaopeng Lin, Yulong Huang, Zeke Xie, Bojun Cheng

CVPR 2026 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 changedWhereMeasuredEffect
add unsupervised optical flow loss (ablation)DIMOS baseline · MouseSISmIoU_ins (%): 60.47 -> 62.54Improved
add bounding box regression loss (ablation)DIMOS + flow · MouseSISmIoU_ins (%): 62.54 -> 63.46Improved
add dual-disentangling mechanism with intra-modal contrastive learning (ablation)DIMOS + flow + bbox · MouseSISmIoU_ins (%): 63.46 -> 68.11Improved
add semantic-level alignment (modality translation) (ablation)DIMOS + dual · MouseSISmIoU_ins (%): 68.11 -> 69.23Improved
add distribution-level alignment (adversarial) (ablation)DIMOS + sem. align · MouseSISmIoU_ins (%): 69.23 -> 70.25Improved
use ResNet-50 instead of MobileNetV2 backbone (ablation)DIMOS · MouseSISmIoU_ins (%): 68.62 -> 70.25Improved
use ResNet-50 instead of ResNet18 backbone (ablation)DIMOS · MouseSISmIoU_ins (%): 69.32 -> 70.25Improved
stack 3 fusion blocks instead of 1 (ablation)DIMOS · MouseSISmIoU_ins (%): 70.25 -> 70.23No clear effect
deepen domain discriminator to 3 blocks (ablation)DIMOS · MouseSISmIoU_ins (%): 70.25 -> 69.52Hurt
use 3 modality translator blocks instead of 1 (ablation)DIMOS · MouseSISmIoU_ins (%): 70.25 -> 70.11No clear effect
use DIMOS instead of EvInsMOSDIMOS · SEVD-FixedmIoU_ins (%): 56.50 -> 62.05Improved
use DIMOS instead of EvInsMOSDIMOS · MouseSISmAP (%): 30.94 -> 45.18Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy