1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking

20 Jan 2021  ·  Fei Du, Bo Xu, Jiasheng Tang, Yuqi Zhang, Fan Wang, Hao Li ·

We extend the classical tracking-by-detection paradigm to this tracking-any-object task. Solid detection results are first extracted from TAO dataset. Some state-of-the-art techniques like \textbf{BA}lanced-\textbf{G}roup \textbf{S}oftmax (\textbf{BAGS}\cite{li2020overcoming}) and DetectoRS\cite{qiao2020detectors} are integrated during detection. Then we learned appearance features to represent any object by training feature learning networks. We ensemble several models for improving detection and feature representation. Simple linking strategies with most similar appearance features and tracklet-level post association module are finally applied to generate final tracking results. Our method is submitted as \textbf{AOA} on the challenge website. Code is available at https://github.com/feiaxyt/Winner_ECCV20_TAO.

PDF Abstract

Datasets


Results from the Paper


Ranked #7 on Multi-Object Tracking on TAO (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Multi-Object Tracking TAO AOA Track mAP 27.461 # 1
TETA 25.27 # 7
LocA 23.40 # 7
AssocA 30.56 # 7
ClsA 21.86 # 4

Methods


No methods listed for this paper. Add relevant methods here