Papers › Short-term anchor linking and long-term self-guided attention for video object detection

Short-term anchor linking and long-term self-guided attention for video object detection

18 Apr 2021archive 2025-07-28

Daniel Cores, Víctor M Brea, Manuel Mucientes

We present a new network architecture able to take advantage of spatio-temporal information available in videos to boost object detection precision. First, box features are associated and aggregated by linking proposals that come from the same anchor box in the nearby frames. Then, we design a new attention module that aggregates short-term enhanced box features to exploit long-term spatio-temporal information. This module takes advantage of geometrical features in the long-term for the first time in the video object detection domain. Finally, a spatio-temporal double head is fed with both spatial information from the reference frame and the aggregated information that takes into account the short- and long-term temporal context. We have tested our proposal in five video object detection datasets with very different characteristics, in order to prove its robustness in a wide number of scenarios. Non-parametric statistical tests show that our approach outperforms the state-of-the-art. Our code is available at https://github.com/daniel-cores/SLTnet.

PaperPDFCode

Code

daniel-cores/SLTnet mentioned in paperpytorch 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.

Code Syntology ran Syntology

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

Tasks

ObjectObject DetectionVideo Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Object Detection ImageNet VID SLTnet FPN-X101 MAP 82.4 #24 of 33 Archive leaderboard report
Video Object Detection USC-GRAD-STDdb SLTnet FPN-X101 AP 16.6 #1 of 1 Archive leaderboard report
Video Object Detection USC-GRAD-STDdb SLTnet FPN-X101 AP 0.5 44.9 #1 of 1 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.

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