2022
DOI: 10.1016/j.patrec.2022.01.003
|View full text |Cite
|
Sign up to set email alerts
|

Multi-label video classification via coupling attentional multiple instance learning with label relation graph

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
9
0

Year Published

2022
2022
2025
2025

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 14 publications
(9 citation statements)
references
References 7 publications
0
9
0
Order By: Relevance
“…In graph convolutional networks (GCNs) there are many ways to employ convolutional layer operators. Based on these variations alternative models are proposed such as the graph transformer network 27 , graph isomorphism network 28 , multi-attention label relation learning CNN 29 , causal incremental GCN 30 , principal neighborhood aggregation-based GCN 31 , among other approaches. Since GCNs do not assign different weights to neighboring nodes, graph attention network (GAT) gains ground as it takes different neighboring nodes into account 32 .…”
Section: Related Workmentioning
confidence: 99%
“…In graph convolutional networks (GCNs) there are many ways to employ convolutional layer operators. Based on these variations alternative models are proposed such as the graph transformer network 27 , graph isomorphism network 28 , multi-attention label relation learning CNN 29 , causal incremental GCN 30 , principal neighborhood aggregation-based GCN 31 , among other approaches. Since GCNs do not assign different weights to neighboring nodes, graph attention network (GAT) gains ground as it takes different neighboring nodes into account 32 .…”
Section: Related Workmentioning
confidence: 99%
“…Multi-label classification methods assign tags from a predefined word set to videos [4,15,36]. Sophisticated methods leverage extra information besides video content, such as tag graph with knowledge [3,9,14,38], query log 1 https://github.com/SCZwangxiao/RADAR-MM2022.git [21], user behavior [2], and user profile [11,33]. Among all the above extra information, tag graph has attracted the most attention.…”
Section: Related Work 21 Video Taggingmentioning
confidence: 99%
“…• Video tagging methods: ML-GCN [3], NeXtVLAD [15,36], CMA [38], and MALL-CNN [14]. We compared them to demonstrate the effectiveness of incorporating extra social networks and tag graph information.…”
Section: Baselinesmentioning
confidence: 99%
See 1 more Smart Citation
“…Treating each label independently [12] ignores their potential correlations as well as increases training times significantly with each additional label. Several works investigate multi-label recognition problems using graph learning approaches to model label correlations and co-occurrences [30,47]. However, such approaches do not learn from label similarities between samples and do not project these similarities to the latent representation space.…”
Section: Learning Representations and Label Relationsmentioning
confidence: 99%