AI Paper Atlas

Research map / Detection and segmentation / Tracking

Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy

Zikai Zhang, Bineng Zhong, Shengping Zhang, Zhenjun Tang, Xin Liu, Zhaoxiang Zhang

CVPR 2021 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 35 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace cross-correlation, depthwise cross-correlation, or Hadamard product with dynamic convolutions (ablation)DMTrack detection correlation · LaSOTSuccess: 49.8, 51.4, 51.1 -> 53.0Improved
integrate dynamic convolutions across layers 1 through 6 rather than only layer 6 (ablation)DMTrack detection head · LaSOTSuccess: 48.7 -> 53.2Improved
use dense dynamic-convolution integration across layers 1 through 6 instead of the selected 1+6 integration (ablation)DMTrack detection head · LaSOTSuccess: 53.0 -> 53.2No clear effect
add re-id embedding association rather than position constraint (ablation)DMTrack object association · LaSOTSuccess: 46.9 -> 57.4Improved
add re-id embedding association rather than appearance constraint (ablation)DMTrack object association · LaSOTSuccess: 55.2 -> 57.4Improved
use re-id association rather than position constraint (ablation)DMTrack object association · LaSOTFPS: 32 -> 31Improved
use re-id association rather than appearance constraint (ablation)DMTrack object association · LaSOTFPS: 16 -> 31Improved
combine global detection with explicit object associationDMTrack · VOT2018LTF-score: 0.629 -> 0.683Improved
use DMTrack instead of Siam R-CNNlong-term tracking · OxUvA testMaxGM: 72.3 -> 68.8Hurt
use DMTrack instead of TLDlong-term tracking · OxUvA testTNR: 89.5 -> 69.4Hurt
use DMTrack instead of LT_DSElong-term tracking · VOT2019LTF-score: 0.695 -> 0.687Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy