Overview

Visual object tracking estimates where a target moves over time, from a single object in a video to many objects across cameras, modalities, or 3D scenes. Common approaches match Siamese-network or Transformer features between frames, associate detections with track histories, and use motion models, geometric constraints, or memory to handle appearance changes, occlusion, and reappearance. Recent work also adapts video and segmentation foundation models, language guidance, event cameras, and learned memory control, with evaluations spanning benchmarks such as LaSOT, GOT-10k, MOT17, UAV tracking datasets, and specialized medical or 3D settings. A central challenge is making trackers reliable beyond standard benchmark conditions—especially over long absences, under severe occlusion or domain shifts—while keeping inference efficient and evaluation representative of real deployments.

Latest papers

CardsList

182 papers9 papers in the last four weeks, down 65% on the four weeks before. 0.1% of all new papers.

  1. SSP-GNN: Learning to Track via Bilevel Optimization

    Jul 5, 2024Griffin Golias, Masa Nakura-Fan, Vitaly AblavskyGraph Neural NetworksVisual Object Tracking

  2. Referring Multi-Object Tracking with Diverse Dynamic Expressions

    Jun 7, 2024Yani Zhang, Dongming Wu, Wencheng Han +3Referring MOTMulti-Object Tracking