![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Article
Continual learning via region-aware memory
Continual learning for classification is a common learning scenario in practice yet remains an open challenge for deep neural networks (DNNs). The contemporary DNNs suffer from catastrophic forgetting—they are...
-
Article
Semantic Contrastive Embedding for Generalized Zero-Shot Learning
Generalized zero-shot learning (GZSL) aims to recognize objects from both seen and unseen classes when only the labeled examples from seen classes are provided. Recent feature generation methods learn a genera...
-
Chapter and Conference Paper
Zero-Shot Image Super-Resolution with Depth Guided Internal Degradation Learning
In the past few years, we have witnessed the great progress of image super-resolution (SR) thanks to the power of deep learning. However, a major limitation of the current image SR approaches is that they assu...
-
Chapter and Conference Paper
Multilevel Collaborative Attention Network for Person Search
Person search aims to apply pedestrian detection and person re-identification simultaneously to search persons in images, which inevitably introduces pedestrian box misalignment during the procedure. And the d...
-
Article
Towards Safe Semi-supervised Classification: Adjusted Cluster Assumption via Clustering
Semi-supervised classification methods can perform even worse than the supervised counterparts in some cases. It undoubtedly reduces their confidence in real applications, and it is desired to improve the safe...
-
Chapter and Conference Paper
Person Re-Identification by Unsupervised \(\ell _1\) Graph Learning
Most existing person re-identification (Re-ID) methods are based on supervised learning of a discriminative distance metric. They thus require a large amount of labelled training image pairs which severely lim...
-
Article
Open AccessPairwise constraint propagation via low-rank matrix recovery
As a kind of weaker supervisory information, pairwise constraints can be exploited to guide the data analysis process, such as data clustering. This paper formulates pairwise constraint propagation, which aims...
-
Article
Open AccessLocal similarity learning for pairwise constraint propagation
Pairwise constraint propagation studies the problem of propagating the scarce pairwise constraints across the entire dataset. Effective propagation algorithms have previously been designed based on the graph-b...
-
Chapter and Conference Paper
Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation
Most existing zero-shot learning approaches exploit transfer learning via an intermediate-level semantic representation such as visual attributes or semantic word vectors. Such a semantic representation is sha...
-
Article
Incremental visual objects clustering with the growing vocabulary tree
With the bag-of-visual-words image representation, we can use the text analysis methods, such as pLSA and LDA, to solve the visual objects clustering and classification problems. However the previous works onl...
-
Chapter and Conference Paper
Large Scale Visual Classification via Learned Dictionaries and Sparse Representation
We address the large scale visual classification problem. The approach is based on sparse and redundant representations over trained dictionaries. The proposed algorithm firstly trains dictionaries using the i...