Skip to main content
Search

# Multi-object Tracking

1 related articles

Subscribe to updates
  1. arXiv

    End-to-end tracking changes how detection queries are born: TAQ-MOTR reaches 72.0 HOTA on the DanceTrack test set

    In end-to-end multi-object tracking, detection queries have been formed before the decoder with little knowledge of existing track states, so occluded tracked objects lack complementary current-frame evidence. TAQ-MOTR forms them before decoding with a Hybrid Query Generator that fuses current-frame image features, track memory and learnable memory, plus a training-only auxiliary detection branch that adds detection supervision. On the DanceTrack test set it reaches 72.0 HOTA, 63.1 AssA and 76.6 IDF1, 3.5, 4.7 and 5.4 points above MeMOTR.

You’re all caught up