TrackFormer: Multi-Object Tracking with Transformers

TLDR

The challenging task of multi‑object tracking (MOT) requires simultaneous reasoning about track initialization, identity, and spatio‑temporal trajectories. The authors formulate MOT as a frame‑to‑frame set prediction problem and introduce TrackFormer, an end‑to‑end trainable Transformer‑based approach. TrackFormer uses an encoder‑decoder Transformer that associates tracks across frames via attention, initializing new tracks from static queries and autoregressively following existing tracks, with both query types leveraging self‑ and encoder‑decoder attention on global frame‑level features, thus avoiding separate graph optimization or motion/appearance modeling. TrackFormer introduces a new tracking‑by‑attention paradigm and achieves state‑of‑the‑art performance on MOT17 and MOTS20. The code is available at https://github.com/timmeinhardt/TrackFormer.

Abstract

The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about track initialization, identity, and spatio-temporal trajectories. We formulate this task as a frame-to-frame set prediction problem and introduce TrackFormer, an end-to-end trainable MOT approach based on an encoder-decoder Transformer architecture. Our model achieves data association between frames via attention by evolving a set of track predictions through a video sequence. The Transformer decoder initializes new tracks from static object queries and autoregressively follows existing tracks in space and time with the conceptually new and identity preserving track queries. Both query types benefit from self- and encoder-decoder attention on global frame-level features, thereby omitting any additional graph optimization or modeling of motion and/or appearance. TrackFormer introduces a new tracking-by-attention paradigm and while simple in its design is able to achieve state-of-the-art performance on the task of multi-object tracking (MOT17) and segmentation (MOTS20). The code is available at https://github.com/timmeinhardt/TrackFormer