Ziwei Liu, Ziyuan Huang, Shiwei Zhang, Liang Pan, Ziang Cao, Changhong Fu
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.
Temporal contexts among consecutive frames are far from being fully utilized in existing visual trackers. In this work, we present TCTrack 1 , a comprehensive framework to fully exploit temporal contexts for aerial tracking. The temporal contexts are incorporated at two levels: the extraction of features and the refinement of similarity maps. Specifically, for feature extraction, an online temporally adaptive convolution is proposed to enhance the spatial features using temporal information, which is achieved by dynamically calibrating the convolution weights according to the previous frames. For similarity map refinement, we propose an adaptive temporal transformer, which first effectively encodes temporal knowledge in a memory-efficient way, before the temporal knowledge is decoded for accurate adjustment of the similarity map. TCTrack is effective and efficient: evaluation on four aerial tracking benchmarks shows its impressive performance; real-world UAV tests show its high speed of over 27 FPS on NVIDIA Jetson AGX Xavier.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.01885")
get_code_for_paper("2203.01885")
have("2203.01885")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.01885.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.01885)
Connect an agent — have() is free.