SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1608.00797 · 2016

CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016

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

This paper presents the method that underlies our submission to the untrimmed video classification task of ActivityNet Challenge 2016. We follow the basic pipeline of temporal segment networks and further raise the performance via a number of other techniques. Specifically, we use the latest deep model architecture, e.g., ResNet and Inception V3, and introduce new aggregation schemes (top-k and attention-weighted pooling). Additionally, we incorporate the audio as a complementary channel, extracting relevant information via a CNN applied to the spectrograms. With these techniques, we derive an ensemble of deep models, which, together, attains a high classification accuracy (mAP $93.23\%$) on the testing set and secured the first place in the challenge.

For agents

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

get_harvested_code_for_paper("1608.00797")
get_code_for_paper("1608.00797")
have("1608.00797")

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

curl https://syntology.ai/api/ran/1608.00797.json

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

[![Syntology run record](https://syntology.ai/api/ran/1608.00797.svg)](https://syntology.ai/paper/1608.00797)

Connect an agent — have() is free.