Jie Chen, Meng Cao, 𝑥, Yuexian Zou, Can Zhang, Dongming Yang, 𝑥 𝑥
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.
Here arises the single snippet cheating issue: "hard" snippets are too vague to be classified. In this paper, we argue that learning by comparing helps identify these hard snippets and we propose to utilize snippet Contrastive learning to Localize Actions, CoLA for short. Specifically, we propose a Snippet Contrast (SniCo) Loss to refine the hard snippet representation in feature space, which guides the network to perceive precise temporal boundaries and avoid the temporal interval interruption. Besides, since it is infeasible to access frame-level annotations, we introduce a Hard Snippet Mining algorithm to locate the potential hard snippets. Substantial analyses verify that this mining strategy efficaciously captures the hard snippets and SniCo Loss leads to more informative feature representation. Extensive experiments show that CoLA achieves state-of-the-art results on THUMOS'14 and ActivityNet v1.2 datasets.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.16392")
get_code_for_paper("2103.16392")
have("2103.16392")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.16392.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.16392)
Connect an agent — have() is free.