SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.00832 · AAAI · 2020

An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos

Kurt Keutzer, Sicheng Zhao, Pengfei Xu, Ma, Hua Chai, Jufeng Yang, Yang Gu, Tengfei Xing, Runbo Hu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
maysonma/VAANet — 3 of 6
copy not recorded — 1 of 1
FunctionStatusWhere it lives
Bottleneck Ran maysonma/VAANet/models/vaanet.py
pointer only (licence: NONE) · get_code("d476b566a0250682")
ResNet Ran maysonma/VAANet/models/vaanet.py
pointer only (licence: NONE) · get_code("c2b6d13ee2ae9766")
get_fine_tuning_parameters Ran this paper's copy was not recorded; identical code first harvested from tianhai123/3D-ResNets
pointer only · get_code("93801ecf3026ab06")
resnet101 Ran maysonma/VAANet/models/vaanet.py
pointer only (licence: NONE) · get_code("a6d391f0f1cb1769")
VAANet Not yet run maysonma/VAANet/models/vaanet.py
pointer only (licence: NONE) · get_code("063e586c19fb6c79")
VisualStream Not yet run maysonma/VAANet/models/vaanet.py
pointer only (licence: NONE) · get_code("bafadcd84c9c9aca")
pretrained_resnet101 Not yet run maysonma/VAANet/models/vaanet.py
pointer only (licence: NONE) · get_code("3f3c849ccdbc385e")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Emotion recognition in user-generated videos plays an important role in human-centered computing. Existing methods mainly employ traditional two-stage shallow pipeline, i.e. extracting visual and/or audio features and training classifiers. In this paper, we propose to recognize video emotions in an end-to-end manner based on convolutional neural networks (CNNs). Specifically, we develop a deep Visual-Audio Attention Network (VAANet), a novel architecture that integrates spatial, channel-wise, and temporal attentions into a visual 3D CNN and temporal attentions into an audio 2D CNN. Further, we design a special classification loss, i.e. polarity-consistent cross-entropy loss, based on the polarity-emotion hierarchy constraint to guide the attention generation. Extensive experiments conducted on the challenging VideoEmotion-8 and Ekman-6 datasets demonstrate that the proposed VAANet outperforms the state-of-the-art approaches for video emotion recognition. Our source code is released at: https://github.com/maysonma/VAANet.

For agents

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

get_harvested_code_for_paper("2003.00832")
get_code_for_paper("2003.00832")
have("2003.00832")

Connect an agent — have() is free.