no code implementations • Image and Vision Computing 2022 • FanYang, ZhengWang, YangWu, SakrianiSakti, SatoshiNakamura
In our online approach, the location and motion of each object are cast to adaptive searching windows, and within searching windows, matching is only related to the similarity of appearance features.
Ranked #9 on Multiple Object Tracking on BDD100K val
1 code implementation • The Thirty-Second AAAI Conference on Artificial Intelligence 2018 • ZhengWang, Xiaojun Ye, Chaokun Wang, YuexinWu, ChangpingWang, Kaiwen Liang
To alleviate this, we propose a novel semi-supervised network embedding method, termed Relaxed Similarity and Dissimilarity Network Embedding (RSDNE).