SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.00380 · CVPR · 2021

Online Multiple Object Tracking with Cross-Task Synergy

Dacheng Tao, Xinchao Wang, Song Guo, Jingya Wang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Modern online multiple object tracking (MOT) methods usually focus on two directions to improve tracking performance. One is to predict new positions in an incoming frame based on tracking information from previous frames, and the other is to enhance data association by generating more discriminative identity embeddings. Some works combined both directions within one framework but handled them as two individual tasks, thus gaining little mutual benefits. In this paper, we propose a novel unified model with synergy between position prediction and embedding association. The two tasks are linked by temporal-aware target attention and distractor attention, as well as identityaware memory aggregation model. Specifically, the attention modules can make the prediction focus more on targets and less on distractors, therefore more reliable embeddings can be extracted accordingly for association. On the other hand, such reliable embeddings can boost identityawareness through memory aggregation, hence strengthen attention modules and suppress drifts. In this way, the synergy between position prediction and embedding association is achieved, which leads to strong robustness to occlusions. Extensive experiments demonstrate the superiority of our proposed model over a wide range of existing methods on MOTChallenge benchmarks. Our code and models are publicly available at https://github.com/ songguocode/TADAM .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2104.00380")
get_code_for_paper("2104.00380")
have("2104.00380")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2104.00380.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2104.00380.svg)](https://syntology.ai/paper/2104.00380)

Connect an agent — have() is free.