Papers › Efficient Visual Tracking with Exemplar Transformers

Efficient Visual Tracking with Exemplar Transformers

17 Dec 2021arXiv:2112.09686archive 2025-07-28

Philippe Blatter, Menelaos Kanakis, Martin Danelljan, Luc van Gool

The design of more complex and powerful neural network models has significantly advanced the state-of-the-art in visual object tracking. These advances can be attributed to deeper networks, or the introduction of new building blocks, such as transformers. However, in the pursuit of increased tracking performance, runtime is often hindered. Furthermore, efficient tracking architectures have received surprisingly little attention. In this paper, we introduce the Exemplar Transformer, a transformer module utilizing a single instance level attention layer for realtime visual object tracking. E.T.Track, our visual tracker that incorporates Exemplar Transformer modules, runs at 47 FPS on a CPU. This is up to 8x faster than other transformer-based models. When compared to lightweight trackers that can operate in realtime on standard CPUs, E.T.Track consistently outperforms all other methods on the LaSOT, OTB-100, NFS, TrackingNet, and VOT-ST2020 datasets. Code and models are available at https://github.com/pblatter/ettrack.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

pblatter/ettrack officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
visionml/pytracking officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Generating Masks from Boxes by Mining Spatio-Temporal Consistencies in Videos (arXiv:2101.02196; that paper's own run record: 6 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Object TrackingVideo Object TrackingVisual Object TrackingVisual Tracking

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Object Tracking NT-VOT211 E.T.Tracker AUC 34.38 #24 of 43 Archive leaderboard report
Video Object Tracking NT-VOT211 E.T.Tracker Precision 46.98 #24 of 43 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections