Xiao Wang, Weiming Hu, Bing Li, Zhipeng Zhang, Yihao Liu
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Siamese tracking has achieved groundbreaking performance in recent years, where the essence is the efficient matching operator cross-correlation and its variants. Besides the remarkable success, it is important to note that the heuristic matching network design relies heavily on expert experience. Moreover, we experimentally find that one sole matching operator is difficult to guarantee stable tracking in all challenging environments. Thus, in this work, we introduce six novel matching operators from the perspective of feature fusion instead of explicit similarity learning, namely Concatenation, Pointwise-Addition, Pairwise-Relation, FiLM, Simple-Transformer and Transductive-Guidance, to explore more feasibility on matching operator selection. The analyses reveal these operators' selective adaptability on different environment degradation types, which inspires us to combine them to explore complementary features. To this end, we propose binary channel manipulation (BCM) to search for the optimal combination of these operators. BCM determines to retrain or discard one operator by learning its contribution to other tracking steps. By inserting the learned matching networks to a strong baseline tracker Ocean [47], our model achieves favorable gains by 67.2
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2108.00803")
get_code_for_paper("2108.00803")
have("2108.00803")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2108.00803.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2108.00803)
Connect an agent — have() is free.