AI Paper Atlas

Research map / Detection and segmentation / Tracking

Object Tracking using Spatio-Temporal Networks for Future Prediction Location

Yuan Liu, Ruoteng Li, Yu Cheng, Robby T. Tan, Xiubao Sui

ECCV 2020 · Detection and segmentation › Tracking · approach: Memory and correlation-based MOT · 25 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 trajectory prediction to DiMP trackerDiMP · VOT2019robustness (failure rate): 0.361 -> 0.311Improved
add trajectory prediction to DiMP trackerDiMP · OTB-100AUC: 67.7 -> 69.3Improved
add trajectory prediction to DiMP trackerDiMP · UAV123AUC: 64.3 -> 64.9Improved
add trajectory prediction to DiMP trackerDiMP · OTB-100 occlusion attributeAUC: 63.5 -> 67.0Improved
add trajectory prediction to DiMP trackerDiMP · UAV123 in-plane rotation attributeAUC: 47.8 -> 47.1Hurt
add trajectory prediction to DiMP trackerDiMP · OTB-100 fast motion attributeAUC: 68.5 -> 69.0No clear effect
add trajectory prediction to SiamMaskSiamMask · VOT2018EAO: 0.380 -> 0.398Improved
add trajectory prediction to SiamMask-LDSiamMask-LD · VOT2018robustness (failure rate): 0.234 -> 0.201Improved
add trajectory prediction to SiamMask-LDSiamMask-LD · VOT2018speed (FPS): 43 -> 13Hurt
add background motion cue (ablation)trajectory prediction network · VOT2018EAO: 0.394 -> 0.436Improved
add image cue (ablation)trajectory prediction network · VOT2018EAO: 0.434 -> 0.436Improved
use location map instead of raw location value (ablation)trajectory prediction network · VOT2018EAO: 0.429 -> 0.436Improved

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