Easy Samples First: Self-paced Reranking for Zero-Example Multimedia Search

By Lu Jiang, Deyu Meng, Teruko Mitamura, Alexander G. Hauptmann. ACM Multimedia, 2014

349 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/934b09cd0a3bc008435d9c509915d6842bc59aa4

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Self-Paced Boost Learning for Classification (2016, methodology): “Several examples of the self-paced function have been listed in [Jiang et al., 2014a], such as hard weighting, linear weighting, and mixture weighting.”
Learning What Data to Learn (2017, methodology): “• SPL typically works for shallow model training (Lee & Grauman, 2011; Jiang et al., 2014a;b) that does not involve frequent model updated.”
Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting (2019, methodology): “For example, SPL [26] and its extensions [28, 29], iterative reweighting [27, 17] and other recent work [46, 30], pay more focus on easy samples with smaller losses.”
Easy Questions First? A Case Study on Curriculum Learning for Question Answering (2016, methodology): “Since its inception, variations of SPL such as self-paced re-ranking (Jiang et al., 2014a), selfpaced learning with diversity (Jiang et al., 2014b), self-paced multiple-instance learning (Zhang et al., 2015) and self-paced curriculum learning (Jiang et al., 2015) have been proposed.”
Cost-Effective Active Learning for Deep Image Classification (2017, methodology): “Inspired by the insights and lessons from a signiﬁcant amount of previous works as well as the recently proposed technique, i.e., self-paced learning [29], [30], [31], [32], we address above mentioned issues by cost-effectively combining the CNN and AL via a complementary sample selection.”
Learning to Teach (2018, methodology): “Curriculum learning (CL) (Bengio et al., 2009; Spitkovsky et al., 2010; Graves et al., 2017) and self-paced learning (SPL) (Kumar et al., 2010; Lee & Grauman, 2011; Jiang et al., 2014b) heuristically deﬁne the scheduling of training data in a from-easy-to-hard order.”
Dual Encoding for Zero-Example Video Retrieval (2018, background): “party, but with no training videos provided [3, 6, 9, 12, 20, 31].”
A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection (2015, methodology): “By virtue of its generality, the SPL theory has been widely applied to various tasks, such as object tracking [29], image classification [30], and multimedia event detection [15, 16].”
Small Sample Learning in Big Data Era (2018, methodology): “…are learning regimes inspired by the learning process of humans and animals that implements learning through gradually including samples into training process from easy to complex so as to increase the entropy of training samples (Bengio et al., 2009; Kumar et al., 2010; Jiang et al., 2014a,b).”
What Objective Does Self-paced Learning Indeed Optimize? (2015, methodology): “(4) represents the hard, linear and mixture SP-regularizers proposed in [2], [17], and [18], respectively.”
Zero-Shot Event Detection by Multimodal Distributional Semantic Embedding of Videos (2015, methodology): “This indicates that our system (Dalton etal, 2013) (event title query) 3.4 % - Concept retrieval (Dalton etal, 2013) 13.1% 0.830 Our Full + SPaR reranking (Jiang et al. 2014a) 13.5% 0.790 Full system (Wu et al. 2014) 12.6 0.730 Reranking Systems Without Reranking (Jiang et al. 2014b) 3.9% - CPRF (Ya”
Self-Training for Jointly Learning to Ask and Answer Questions (2018, background): “A manifestation of this idea is self-paced learning (SPL) (Kumar et al., 2010; Jiang et al., 2014, 2015) which selects samples based on the local loss term of the sample.”
Self-Paced Curriculum Learning (2015, methodology): “2014b), reranking (Jiang et al. 2014a), domain adaption (Tang et al.”
A Survey on Curriculum Learning (2021, methodology): “To allow more possibility on SP-regularizer designs, a general and formal definition is taken as follows [40], [141]:”
Contrastive Adaptation Network for Unsupervised Domain Adaptation (2019, background): “Recent advancements in deep neural networks have successfully improved a variety of learning problems [40, 8, 26, 19, 20].”
RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval (2020, background): “Image retrieval has been a classical vision problem with numerous applications such as product search [22,6,1], multimodal image retrieval [32,3], image geolocalization [7], event detection [12], among others.”
Co-Saliency Detection via a Self-Paced Multiple-Instance Learning Framework (2017, background): “In multimedia event detection [41], Jiang et al. proposed selfpaced reranking models in a self-paced fashion.”
Graph Distillation for Action Detection with Privileged Modalities (2017, background): “The success in RGB videos has given rise to a series of studies on action recognition in multimodal videos [10,20,22,25,51,55].”