Yanwei Fu

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 shared between an annotated auxiliary dataset and a target dataset with no annotation. A projection from a low-level feature space to the semantic space is learned from the auxiliary dataset and is applied without adaptation to the target dataset. In this paper we identify an inherent limitation with this approach. That is, due to having disjoint and potentially unrelated classes, the projection functions learned from the auxiliary dataset/domain are biased when applied directly to the target dataset/domain. We call this problem the projection domain shift problem and propose a novel framework, transductive multi-view embedding, to solve it. It is ‘transductive’ in that unlabelled target data points are explored for projection adaptation, and ‘multi-view’ in that both low-level feature (view) and multiple semantic representations (views) are embedded to rectify the projection shift. We demonstrate through extensive experiments that our framework (1) rectifies the projection shift between the auxiliary and target domains, (2) exploits the complementarity of multiple semantic representations, (3) achieves state-of-the-art recognition results on image and video benchmark datasets, and (4) enables novel cross-view annotation tasks.

Learning Multimodal Latent Attributes

The rapid development of social media sharing has created a huge demand for automatic media classification and annotation techniques. Attribute learning has emerged as a promising paradigm for bridging the semantic gap and addressing data sparsity via transferring attribute knowledge in object recognition and relatively simple action classification. In this paper, we address the task of attribute learning for understanding multimedia data with sparse and incomplete labels. In particular, we focus on videos of social group activities, which are particularly challenging and topical examples of this task because of their multimodal content and complex and unstructured nature relative to the density of annotations. To solve this problem, we 1) introduce a concept of semilatent attribute space, expressing user-defined and latent attributes in a unified framework, and 2) propose a novel scalable probabilistic topic model for learning multimodal semilatent attributes, which dramatically reduces requirements for an exhaustive accurate attribute ontology and expensive annotation effort. We show that our framework is able to exploit latent attributes to outperform contemporary approaches for addressing a variety of realistic multimedia sparse data learning tasks including: multitask learning, learning with label noise, N-shot transfer learning, and importantly zero-shot learning.

Transductive Multi-View Zero-Shot Learning

Most existing zero-shot learning approaches exploit transfer learning via an intermediate semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no annotation. A projection from a low-level feature space to the semantic representation space is learned from the auxiliary dataset and applied without adaptation to the target dataset. In this paper we identify two inherent limitations with these approaches. First, due to having disjoint and potentially unrelated classes, the projection functions learned from the auxiliary dataset/domain are biased when applied directly to the target dataset/ domain. We call this problem the projection domain shift problem and propose a novel framework, transductive multi-view embedding, to solve it. The second limitation is the prototype sparsity problem which refers to the fact that for each target class, only a single prototype is available for zero-shot learning given a semantic representation. To overcome this problem, a novel heterogeneous multi-view hypergraph label propagation method is formulated for zero-shot learning in the transductive embedding space. It effectively exploits the complementary information offered by different semantic representations and takes advantage of the manifold structures of multiple representation spaces in a coherent manner. We demonstrate through extensive experiments that the proposed approach (1) rectifies the projection shift between the auxiliary and target domains, (2) exploits the complementarity of multiple semantic representations, (3) significantly outperforms existing methods for both zero-shot and N-shot recognition on three image and video benchmark datasets, and (4) enables novel cross-view annotation tasks.

Attribute learning for understanding unstructured social activity

The rapid development of social video sharing platforms has created a huge demand for automatic video classification and annotation techniques, in particular for videos containing social activities of a group of people (e.g. YouTube video of a wedding reception). Recently, attribute learning has emerged as a promising paradigm for transferring learning to sparsely labelled classes in object or single-object short action classification. In contrast to existing work, this paper for the first time, tackles the problem of attribute learning for understanding group social activities with sparse labels. This problem is more challenging because of the complex multi-object nature of social activities, and the unstructured nature of the activity context. To solve this problem, we (1) contribute an unstructured social activity attribute (USAA) dataset with both visual and audio attributes, (2) introduce the concept of semi-latent attribute space and (3) propose a novel model for learning the latent attributes which alleviate the dependence of existing models on exact and exhaustive manual specification of the attribute-space. We show that our framework is able to exploit latent attributes to outperform contemporary approaches for addressing a variety of realistic multi-media sparse data learning tasks including: multi-task learning, N-shot transfer learning, learning with label noise and importantly zero-shot learning.

Semi-supervised Vocabulary-Informed Learning

Despite significant progress in object categorization, in recent years, a number of important challenges remain, mainly, ability to learn from limited labeled data and ability to recognize object classes within large, potentially open, set of labels. Zero-shot learning is one way of addressing these challenges, but it has only been shown to work with limited sized class vocabularies and typically requires separation between supervised and unsupervised classes, allowing former to inform the latter but not vice versa. We propose the notion of semi-supervised vocabulary-informed learning to alleviate the above mentioned challenges and address problems of supervised, zero-shot and open set recognition using a unified framework. Specifically, we propose a maximum margin framework for semantic manifold-based recognition that incorporates distance constraints from (both supervised and unsupervised) vocabulary atoms, ensuring that labeled samples are projected closest to their correct prototypes, in the embedding space, than to others. We show that resulting model shows improvements in supervised, zero-shot, and large open set recognition, with up to 310K class vocabulary on AwA and ImageNet datasets.

Harnessing Object and Scene Semantics for Large-Scale Video Understanding

Large-scale action recognition and video categorization are important problems in computer vision. To address these problems, we propose a novel object-and scene-based semantic fusion network and representation. Our semantic fusion network combines three streams of information using a three-layer neural network: (i) frame-based low-level CNN features, (ii) object features from a state-of-the-art large-scale CNN object-detector trained to recognize 20K classes, and (iii) scene features from a state-of-the-art CNN scene-detector trained to recognize 205 scenes. The trained network achieves improvements in supervised activity and video categorization in two complex large-scale datasets - ActivityNet and FCVID, respectively. Further, by examining and back propagating information through the fusion network, semantic relationships (correlations) between video classes and objects/scenes can be discovered. These video class-object/video class-scene relationships can in turn be used as semantic representation for the video classes themselves. We illustrate effectiveness of this semantic representation through experiments on zero-shot action/video classification and clustering.

Interestingness Prediction by Robust Learning to Rank

The problem of predicting image or video interestingness from their low-level feature representations has received increasing interest. As a highly subjective visual attribute, annotating the interestingness value of training data for learning a prediction model is challenging. To make the annotation less subjective and more reliable, recent studies employ crowdsourcing tools to collect pairwise comparisons – relying on majority voting to prune the annotation outliers/errors. In this paper, we propose a more principled way to identify annotation outliers by formulating the interestingness prediction task as a unified robust learning to rank problem, tackling both the outlier detection and interestingness prediction tasks jointly. Extensive experiments on both image and video interestingness benchmark datasets demonstrate that our new approach significantly outperforms state-of-the-art alternatives.

Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels

The problem of estimating subjective visual properties from image and video has attracted increasing interest. A subjective visual property is useful either on its own (e.g. image and video interestingness) or as an intermediate representation for visual recognition (e.g. a relative attribute). Due to its ambiguous nature, annotating the value of a subjective visual property for learning a prediction model is challenging. To make the annotation more reliable, recent studies employ crowdsourcing tools to collect pairwise comparison labels. However, using crowdsourced data also introduces outliers. Existing methods rely on majority voting to prune the annotation outliers/errors. They thus require a large amount of pairwise labels to be collected. More importantly as a local outlier detection method, majority voting is ineffective in identifying outliers that can cause global ranking inconsistencies. In this paper, we propose a more principled way to identify annotation outliers by formulating the subjective visual property prediction task as a unified robust learning to rank problem, tackling both the outlier detection and learning to rank jointly. This differs from existing methods in that (1) the proposed method integrates local pairwise comparison labels together to minimise a cost that corresponds to global inconsistency of ranking order, and (2) the outlier detection and learning to rank problems are solved jointly. This not only leads to better detection of annotation outliers but also enables learning with extremely sparse annotations.

Transductive Multi-label Zero-shot Learning

Zero-shot learning has received increasing interest as a means to alleviate the often prohibitive expense of annotating training data for large scale recognition problems. These methods have achieved great success via learning intermediate semantic representations in the form of attributes and more recently, semantic word vectors. However, they have thus far been constrained to the single-label case, in contrast to the growing popularity and importance of more realistic multi-label data. In this paper, for the first time, we investigate and formalise a general framework for multi-label zero-shot learning, addressing the unique challenge therein: how to exploit multi-label correlation at test time with no training data for those classes? In particular, we propose (1) a multi-output deep regression model to project an image into a semantic word space, which explicitly exploits the correlations in the intermediate semantic layer of word vectors; (2) a novel zero-shot learning algorithm for multi-label data that exploits the unique compositionality property of semantic word vector representations; and (3) a transductive learning strategy to enable the regression model learned from seen classes to generalise well to unseen classes. Our zero-shot learning experiments on a number of standard multi-label datasets demonstrate that our method outperforms a variety of baselines.

Heterogeneous Knowledge Transfer in Video Emotion Recognition, Attribution and Summarization

Emotion is a key element in user-generated video. However, it is difficult to understand emotions conveyed in such videos due to the complex and unstructured nature of user-generated content and the sparsity of video frames expressing emotion. In this paper, for the first time, we propose a technique for transferring knowledge from heterogeneous external sources, including image and textual data, to facilitate three related tasks in understanding video emotion: emotion recognition, emotion attribution and emotion-oriented summarization. Specifically, our framework (1) learns a video encoding from an auxiliary emotional image dataset in order to improve supervised video emotion recognition, and (2) transfers knowledge from an auxiliary textual corpora for zero-shot recognition of emotion classes unseen during training. The proposed technique for knowledge transfer facilitates novel applications of emotion attribution and emotion-oriented summarization. A comprehensive set of experiments on multiple datasets demonstrate the effectiveness of our framework.