---
title: "HyperSSM Lets Objects Share Motion Clues to Beat Tracking Blindspots"
subtitle: "HyperSSM fuses hypergraph reasoning with state space models to let correlated objects share motion cues, delivering state-of-the-art results across four MOT benchmarks."
url: "https://alphasignal.ai/news/hyperssm-lets-objects-share-motion-clues-to-beat-tracking-blindspots"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-04-14T00:00:00.000Z"
updated: "2026-08-23T21:59:32.677Z"
type: "Paper"
topics:
  - "Video"
  - "Benchmarks"
subtopics:
  - "Video Understanding"
upvotes: 2278
source_url: "https://arxiv.org/abs/2604.12665"
comments: 0
truncated: true
---

# HyperSSM Lets Objects Share Motion Clues to Beat Tracking Blindspots

> HyperSSM fuses hypergraph reasoning with state space models to let correlated objects share motion cues, delivering state-of-the-art results across four MOT benchmarks.

Multi-object tracking has spent years wrestling with two stubborn failure modes: motion predictors that jitter under noise, and trajectories that fall apart the moment a target gets occluded. A new paper from Huazhong University of Science and Technology and the National University of Singapore proposes a different way of thinking about the problem. Rather than predicting each object's motion in isolation, [HyperSSM](https://arxiv.org/abs/2604.12665) lets objects with similar movement patterns reason together, using a hypergraph to share information and a state space model to keep trajectories temporally smooth.

The result is a tracker that posts state-of-the-art numbers on four different benchmarks, and the code is already [on GitHub](https://github.com/SkyeSong38/HyperMOT).

## Why motion estimation keeps breaking

Motion prediction is the glue that holds identity together across frames in tracking-by-detection systems, and the field has been stuck between two imperfect options. Traditional trackers use hand-crafted Kalman filters that assume constant-velocity linear motion. They perform well in linear scenarios like surveillance video but deteriorate sharply in nonlinear cases such as dancing or sports. Learnable motion networks replace the Kalman filter with data-driven predictors that better capture complex nonlinear dynamics and substantially improve robustness, but their probabilistic outputs introduce fluctuations.

The authors frame this as two challenges. Learned predictors are noisy in easy linear scenes where a Kalman filter would be rock solid. And both approaches collapse when a target disappears behind another object, because there is simply no visual signal to work with.

## Borrowing motion from the neighbors

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [Hypergraph-State Collaborative Reasoning for Multi-Object Tracking](https://arxiv.org/abs/2604.12665)
- [HyperMOT GitHub Repository](https://github.com/SkyeSong38/HyperMOT)
- [HyperSSM paper HTML version](https://arxiv.org/html/2604.12665v1)
- [Semantic Scholar entry](https://www.semanticscholar.org/paper/49037f85e4a0f02718c4084d4199ae4090e987e0)