speech-emotion-recognition

Vocal Bursts Valence Prediction

3260 papers • 126 benchmarks • 313 datasets

predict the degrees of valence and arousal for the given vocal bursts

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in speech-emotion-recognition

Trend

Dataset

Best Model

Actions

HUME-VB

Libraries

i

Use these libraries to find speech-emotion-recognition models and implementations

bryanyzhu/two-stream-pytorch

2 papers 549

Datasets

HUME-VB

Subtasks

No subtasks available.

Most implemented papers

Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

Ping Luo, Xiaoou Tang, Jianping Shi, Xingang Pan•Tue Jul 24 2018

IBN-Net is presented, a novel convolutional architecture, which remarkably enhances a CNN’s modeling ability on one domain as well as its generalization capacity on another domain without finetuning.

879

Content

0

Paper Graph

Two-Stream Convolutional Networks for Action Recognition in Videos

Andrew Zisserman, K. Simonyan•Sun Jun 08 2014

This work proposes a two-stream ConvNet architecture which incorporates spatial and temporal networks and demonstrates that a ConvNet trained on multi-frame dense optical flow is able to achieve very good performance in spite of limited training data.

7921 0

Paper Graph

PacGAN: The Power of Two Samples in Generative Adversarial Networks

Sewoong Oh, Zinan Lin, G. Fanti, A. Khetan•Mon Dec 11 2017

It is shown that packing naturally penalizes generators with mode collapse, thereby favoring generator distributions with less mode collapse during the training process, and numerical experiments suggests that packing provides significant improvements in practice as well.

360 0

Paper Graph

Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks

A. Champandard•Fri Mar 04 2016

This paper introduces a novel concept to augment such generative architectures with semantic annotations, either by manually authoring pixel labels or using existing solutions for semantic segmentation, resulting in a content-aware generative algorithm that offers meaningful control over the outcome.

251 0

Paper Graph

Towards Good Practices for Very Deep Two-Stream ConvNets

Y. Qiao, Limin Wang, Yuanjun Xiong, Zhe Wang•Tue Jul 07 2015

This report presents very deep two-stream ConvNets for action recognition, by adapting recent very deep architectures into video domain, and extends the Caffe toolbox into Multi-GPU implementation with high computational efficiency and low memory consumption.

457 0

Paper Graph

Two-pass Discourse Segmentation with Pairing and Global Features

Graeme Hirst, V. Feng•Tue Jul 29 2014

It is shown that both the pairing and global features are useful on their own, and their combination achieved an F1 of 92.6% of identifying insentence discourse boundaries, which is a 17.8% error-rate reduction over the state of the art performance.

18 0

Paper Graph

Light-Head R-CNN: In Defense of Two-Stage Object Detector

Gang Yu, Xiangyu Zhang, Zeming Li, Chao Peng, Yangdong Deng•Sun Nov 19 2017

The authors' ResNet-101 based light-head R-CNN outperforms state-of-art object detectors on COCO while keeping time efficiency and significantly outperforming the single-stage, fast detectors like YOLO and SSD on both speed and accuracy.

386 0

Paper Graph

Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition

Yifan Zhang, Jian Cheng, Hanqing Lu, Lei Shi•Sat May 19 2018

In skeleton-based action recognition, graph convolutional networks (GCNs), which model the human body skeletons as spatiotemporal graphs, have achieved remarkable performance. However, in existing GCN-based methods, the topology of the graph is set manually, and it is fixed over all layers and input samples. This may not be optimal for the hierarchical GCN and diverse samples in action recognition tasks. In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing methods. In this work, we propose a novel two-stream adaptive graph convolutional network (2s-AGCN) for skeleton-based action recognition. The topology of the graph in our model can be either uniformly or individually learned by the BP algorithm in an end-to-end manner. This data-driven method increases the flexibility of the model for graph construction and brings more generality to adapt to various data samples. Moreover, a two-stream framework is proposed to model both the first-order and the second-order information simultaneously, which shows notable improvement for the recognition accuracy. Extensive experiments on the two large-scale datasets, NTU-RGBD and Kinetics-Skeleton, demonstrate that the performance of our model exceeds the state-of-the-art with a significant margin.

1707 0

Paper Graph

MagNet: A Two-Pronged Defense against Adversarial Examples

Hao Chen, Dongyu Meng•Wed May 24 2017

MagNet, a framework for defending neural network classifiers against adversarial examples, is proposed and it is shown empirically that MagNet is effective against the most advanced state-of-the-art attacks in blackbox and graybox scenarios without sacrificing false positive rate on normal examples.

1277 0

Paper Graph

FinalMLP: An Enhanced Two-Stream MLP Model for CTR Prediction

Kelong Mao, Jieming Zhu, Zhenhua Dong, Liangcai Su, Guohao Cai, Yuru Li•Sun Apr 02 2023

This paper presents a simple two-stream feature interaction model, namely FinalMLP, which employs only MLPs in both streams yet achieves surprisingly strong performance and could serve as a new strong baseline for future development of two- stream CTR models.

119 0

Paper Graph

Adding a benchmark result helps the community track progress.