Paper Detail

SAM-MT: Real-Time Interactive Multi-Target Video Segmentation

Ruiqi Shen, Chang Liu, Henghui Ding

huggingface Score 5.0

Published 2026-07-09 · First seen 2026-07-11

General AI

Abstract

Modern Video Object Segmentation (VOS) involves tracking and segmenting user-specified targets. While recent approaches have achieved remarkable performance in single-target scenarios, extending them to multi-target settings typically involves replicating the single-target processing for each individual object, resulting in reduced frame rates (FPS) with unbounded latency as target count increases. Built upon Segment Anything 2 (SAM2), we propose SAM-MT, which addresses this by transforming the model into an interactive framework for real-time Multi-Target video segmentation. SAM-MT uses explicit queries to represent different individual targets, in parallel with a shared representation for global context. It employs decoupled masked attention to keep individual identities distinct from cross-target interference, and sparse memory for stable temporal evolution, along with specialized strategies for occlusion handling and overlap prevention. SAM-MT successfully decouples latency from the number of targets, achieving real-time speed on par with single-target baselines (>36 FPS for 10 targets) while maintaining SAM2's robust video segmentation performance.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{shen2026sam,
  title = {SAM-MT: Real-Time Interactive Multi-Target Video Segmentation},
  author = {Ruiqi Shen and Chang Liu and Henghui Ding},
  year = {2026},
  abstract = {Modern Video Object Segmentation (VOS) involves tracking and segmenting user-specified targets. While recent approaches have achieved remarkable performance in single-target scenarios, extending them to multi-target settings typically involves replicating the single-target processing for each individual object, resulting in reduced frame rates (FPS) with unbounded latency as target count increases. Built upon Segment Anything 2 (SAM2), we propose SAM-MT, which addresses this by transforming the },
  url = {https://huggingface.co/papers/2607.08688},
  keywords = {code available, huggingface daily},
  eprint = {2607.08688},
  archiveprefix = {arXiv},
}

Metadata

{}