Multi-task Recurrent Neural Network for Immediacy Prediction

By Xiao Chu, Wanli Ouyang, Wei Yang, Xiaogang Wang. 2015

54 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Natural Language Processing, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Natural Language Processing

In Human-Computer Interaction

Citations in the corpus

An Overview of Multi-task Learning (2018, background): “…images include object categorization [86], image segmentation [89,90], identifying brain imaging predictors [91], saliency detection [92], action recognition [93], scene classification [94], multi-attribute prediction [95], multi-camera person re-identification [96], and immediacy prediction [97].”
A Survey on Multi-Task Learning (2017, methodology): “In [179], a recurrent neural network (RNN) is used for immediacy prediction and the output layer has multiple units to estimate the interaction, distance, stand orientation, relative orientation, and”
Unsupervised Domain Adaptation with Residual Transfer Networks (2016, background): “s domains (Li et al., 2014), the residual transfer can be applied to the feature layers (e.g. fc6–fc7) of the deep network to bridge the source and target representations. (2) In multi-task learning (Chu et al., 2015) that solves multiple potentially correlated tasks together to improve performanceo”
A Domain Based Approach to Social Relation Recognition (2017, methodology): “Additionally, we utilize the published models of proximity [10] and activity [47] for extracting body features.”
Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-Temporal Path Proposals (2017, methodology): “For sequential data, the family of Recurrent Neural Networks including LongShort Term Memory Network(LSTM) [14] and Gated Recurrent Neural Network [4] have achieved great success for tasks including image captioning [18], speech recognition [11], visual question answering [2], person search [24], im”
Factors in Finetuning Deep Model for Object Detection with Long-Tail Distribution (2016, methodology): “Finetuning from the deep model pretrained on the large-scale ImageNet dataset is found to yield state-of-the-art performance for many vision tasks such as tracking [38], segmentation [12], object detection [35, 25, 22], action recognition [16], and human pose estimation [5].”
Structured Feature Learning for Pose Estimation (2016, background): “The first is to model the geometrical distribution of body joints [35, 30, 31, 19, 9, 6, 1, 11, 25, 2, 21, 17, 34, 7] which can be viewed as post processing on detection score maps and prediction labels.”
CRF-CNN: Modeling Structured Information in Human Pose Estimation (2016, unknown): “They are complementary.”
Amalgamating Knowledge from Heterogeneous Graph Neural Networks (2021, background): “Another work in [3] constructs a multi-task recurrent neural network, of which the output layer has multiple units to simultaneously estimate the relative distance, interactions, and standing orientations.”
Learning Multiple Tasks with Multilinear Relationship Networks (2015, background): “Our work contrasts from prior relationship learning [29, 31] and multi-task deep learning [22, 32, 7, 27] methods in two key aspects.”
Learning Multiple Tasks with Deep Relationship Networks (2015, methodology): “Most multi-task deep learning methods [9, 26, 33, 7] learn a shared representation in the feature layers and multiple independent classifiers in the classifier layer without inferring the task relationships.”
From Facial Expression Recognition to Interpersonal Relation Prediction (2016, methodology): “tures (Chu et al. 2015) to achieve an even richer modeling and prediction of relations.”