AI Paper Atlas

Research map / Detection and segmentation / Tracking

DepthTrack: Unveiling the Power of RGBD Tracking

Song Yan, Jinyu Yang, Jani Käpylä, Feng Zheng, Aleš Leonardis, Joni-Kristian Kämäräinen

ICCV 2021 · Detection and segmentation › Tracking · approach: Unified transformer tracking · 105 citations (OpenAlex)

Read the paperCheck 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
add depth-trained depth branch (DeT) (ablation)DiMP50 · DepthTrack test (sequence-based)F-score: 0.405 -> 0.532Improved
add depth-trained depth branch (DeT) (ablation)ATOM · DepthTrack test (sequence-based)F-score: 0.363 -> 0.440Improved
train depth backbone on depth data instead of reusing RGB-trained DiMP50 on depth (ablation)DiMP50 depth-only · DepthTrack test (sequence-based)F-score: 0.206 -> 0.394Improved
depth-only DeT versus RGB DiMP50 (ablation)DeT-DiMP50 (D) · DepthTrack test (frame-based)F-score: 0.395 -> 0.411Improved
use max pooling instead of convolutional pooling for RGB-D merge (ablation)DeT-DiMP50 · DepthTrack test (sequence-based)F-score: 0.496 -> 0.532Improved
use mean pooling instead of max pooling for RGB-D merge (ablation)DeT-DiMP50 · DepthTrack test (sequence-based)F-score: 0.532 -> 0.530No clear effect
use mean pooling instead of max pooling for RGB-D merge (ablation)DeT-ATOM · DepthTrack test (sequence-based)F-score: 0.440 -> 0.457Improved
any of the three pooling layers versus RGB-only master (ablation)DeT-ATOM · DepthTrack test (frame-based)F-score: 0.336 -> 0.411Improved
add DeT depth branch trained on DepthTrack, tested on CDTB without fine-tuning (ablation)DiMP50 · CDTB (cross-dataset, sequence-based)F-score: 0.552 -> 0.642Improved
add DeT depth branch trained on DepthTrack, tested on CDTB without fine-tuning (ablation)ATOM · CDTB (cross-dataset, sequence-based)F-score: 0.542 -> 0.585Improved
mean pooling instead of max on CDTB (ablation)DeT-DiMP50 · CDTB (cross-dataset, sequence-based)F-score: 0.642 -> 0.657Improved
DeT (short-term, depth-trained) versus long-term RGBD winnerATCAIS · DepthTrack test (sequence-based)F-score: 0.476 -> 0.532Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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