← Back to all news
arXiv Computer Vision By Muxi Zha, Yang Shang, Wenlong Zhang, Qifeng Yu, Banglei Guan

Hierarchical Sparse Graph for Multi-dimensional Assignment in Event-based Tracking

Read the original on arXiv Computer Vision →

The paper introduces a Hierarchical Sparse Graph (HSG) for event‑based multi‑dimensional assignment, addressing the many‑to‑many tracklet association problem that arises when event detectors produce multiple spatially distinct tracklets per object. By modeling tracklet correlations with fuzzy logic and long‑range kinematic metrics, the authors avoid hard thresholds and integrate heterogeneous metrics into a unified graph partitioning framework. Experiments on eTram and Ev‑UAV datasets demonstrate that this training‑free method outperforms existing event‑based and most image‑based association models, achieving more than twice the performance of OC‑SORT in many‑to‑many scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

Hugging Face Trending Papers
Sep 28

VastMAT: A Large-Scale Multi-Category Benchmark for Multi-Animal Tracking

VastMAT is a large‑scale multi‑animal tracking benchmark featuring 2,947 videos, 337 animal categories, and over 3.6 million bounding boxes with 22,883 identity trajectories. It emphasizes high‑quality, expert‑reviewed annotations and introduces Seen‑category and Unseen‑category evaluation protocols, revealing significant challenges in tracking unseen animals. The authors also propose a lightweight Center‑Distance‑Augmented Association module that boosts HOTA scores for existing MOT methods without extra training.

benchmarks
More like this →
arXiv Computer Vision
Sep 22

Beyond the Survey: A Systematic Empirical Study of Detection and Association in Visual MOT

This paper conducts a systematic empirical study of multi‑object tracking (MOT) algorithms, focusing on how detection and association components affect overall performance. By evaluating state‑of‑the‑art methods on benchmarks such as MOT16/17/20, SportsMOT, DanceTrack, and CrowdTrack, the authors find that detection quality has a far greater impact than association strategies, and that transformer‑based end‑to‑end models are more robust to detection variations but computationally expensive. The study provides a unified pipeline diagram and practical guidance for researchers and practitioners in selecting and designing MOT systems.

By Linh Van Ma, Juhua Hu, Wei Cheng, Unse Fatima, Moongu Jeon
llmsragcomputer-visionbenchmarks
More like this →
arXiv Computer Vision
5d ago

MvT: Event-based Multi-view Projection for Multiple Object Tracking

The paper introduces MvT, a training‑free multi‑view pipeline for event‑camera based multiple object tracking. MvT preserves the 2‑D event format while generating three complementary spatio‑temporal views, then fuses them into a 3‑D coordinate system to resolve tracking ambiguities that arise in single‑view pseudo‑frames. Experiments on four datasets, including a new Small Objects Dataset, show that MvT outperforms both non‑learning and learning trackers and can be applied when ground‑truth annotations are unavailable.

By Muxi Zha, Banglei Guan, Minzu Liang, Zibin Liu, Yang Shang, Qifeng Yu, Laurent Kneip
More like this →
arXiv Computer Vision
Oct 26

GenTrack3: Hybrid Stochastic-Deterministic Online Multi-Object Tracking with Cluster-Aware Association

GenTrack3 is an online multi-object tracking framework that blends deterministic tracking-by-detection with stochastic particle-based uncertainty modeling. It introduces a cluster-aware track-to-detection matching strategy to improve scalability and support group tracking, while maintaining a systematic pipeline that tracks identifiers, states, velocities, penalties, and ages. The authors provide reference implementations on GitHub for reproducibility.

By Toan Van Nguyen, Rasmus G. K. Christiansen, Dirk Kraft, Leon Bodenhagen
More like this →