Unified Video Annotation via Multigraph Learning

By Meng Wang, Xiansheng Hua, Richang Hong, Jinhui Tang, Guo-Jun Qi, Yan Song. IEEE transactions on circuits and systems for video technology (Print), 2009

458 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/7ede3b7bbc5ef9ffdc52404497d19cf008ebb897

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 Signal Processing

Citations in the corpus

Learning of Multimodal Representations With Random Walks on the Click Graph (2016, methodology): “, color, texture, shape and spatial layout), graph-based feature fusion techniques ( [12], [13]) which explore the complementation of multiple features during the learning process are also investigated, showing better performance than that of using concatenated high-dimensional global feature vector”
Multiple feature hashing for real-time large scale near-duplicate video retrieval (2011, background): “The late fusion algorithms [22, 24, 25] ﬁrst generate separate results from different features, and then combine these results together by different strategies.”
Strengthening learning algorithms by feature discovery (2012, methodology): “Feature selection is used in various new machine learning classifiers, including learning to select features using their properties [11], feature selection for unlabeled data [12], selection using ensemble methods [12], feature combination by multimodal learning [26], genetic feature selection [3], ”
Content-based visual search learned from social media (2012, methodology): “Instead of feature concatenation, another method is to combine visual similarities of the individual features [41, 80, 128].”
Cross-Modal Retrieval With CNN Visual Features: A New Baseline (2017, unknown): “[20], [22], [29], [33], [47], [49]–[52], [54], [57], [60], [62], [64], [66], [68] are also proposed to address multimodal problems.”
3-D Object Retrieval and Recognition With Hypergraph Analysis (2012, background): “The hypergraph has been investigated in many data mining and information retrieval tasks [35], [37], [38], [41], [42] because of its capability of capturing the higher order relationship of samples.”
Scalable Semi-Supervised Learning by Efficient Anchor Graph Regularization (2016, background): “Based on the above formulation, these algorithms generally produce satisfying classification results in a manifold space [12], [13], [20], [40], [45], [50].”
Attribute Learning for Understanding Unstructured Social Activity (2012, background): “User-defined video attribute learning is related to the video concept detection (video ontology) work in the multimedia community [16,17,18,19,20,21,22,23] which has defined top-down shared visual concepts, in order to recognise them in video.”
Recent advances and trends in visual tracking: A review (2011, methodology): “In [91], multi-graph learning was used to unify video annotation.”
Video Question Answering via Gradually Refined Attention over Appearance and Motion (2017, background): “Video question answering (VideoQA) can help us quickly acquire the necessary information we seek from videos, which is beneficial to various real-life applications [4, 8, 28, 29, 36].”
Unsupervised Feature Selection Using Nonnegative Spectral Analysis (2012, background): “The dimension of data is often very high in many domains (Jain and Zongker 1997; Guyon and Elisseeff 2003), such as image and video understanding (Wang et al. 2009a; 2009b), and bio-informatics.”
Semi-Supervised Manifold Learning Based Multigraph Fusion for High-Resolution Remote Sensing Image Classification (2014, methodology): “To solve this problem, we adopt an exponent trick proposed in [10], in which ω i serves as a substitute for ωi via an exponent r > 1, i.”
Click Prediction for Web Image Reranking Using Multimodal Sparse Coding (2014, methodology): “Extracted visual information is then used to re-rank related images to the top of the list.”
Multi-view hypergraph learning by patch alignment framework (2013, methodology): “It unifies spectral analysis based dimensionality reduction approaches, including LLE/NPE/ONPP, ISOMAP, LE/LPP, LTSA/ LLTSA, HLLE, PCA and LDA.”