Sharing features between objects and their attributes

Hwang, Sung Ju; Sha, Fei; Grauman, Kristen

doi:10.1109/cvpr.2011.5995543

Cited by 111 publications

(76 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Attribute-centric models have been explored for images [18,6,12,31] and to a lesser extent videos [8,11,21]. Most existing studies [18,17,25,26,30,37,1] assume that an exhaustive ontology of attributes has been manually specified at either the class or instance level. However, annotating attributes scales poorly as ontologies tend to be domain specific.…”

Section: Related Workmentioning

confidence: 99%

Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation

Hospedales

Xiang

et al. 2014

Lecture Notes in Computer Science

197

206

View full text Add to dashboard Cite

Abstract. 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 lowlevel 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.

show abstract

Section: Related Workmentioning

confidence: 99%

Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation

Hospedales

Xiang

et al. 2014

Lecture Notes in Computer Science

197

206

View full text Add to dashboard Cite

show abstract

“…In particular, label hierarchies have been used to share representations [15,2,8,17] and combine models [18,38,27].…”

Section: Related Workmentioning

confidence: 99%

Large-Scale Object Classification Using Label Relation Graphs

Deng

Ding

Jia

et al. 2014

Lecture Notes in Computer Science

336

305

View full text Add to dashboard Cite

Abstract. In this paper we study how to perform object classification in a principled way that exploits the rich structure of real world labels. We develop a new model that allows encoding of flexible relations between labels. We introduce Hierarchy and Exclusion (HEX) graphs, a new formalism that captures semantic relations between any two labels applied to the same object: mutual exclusion, overlap and subsumption. We then provide rigorous theoretical analysis that illustrates properties of HEX graphs such as consistency, equivalence, and computational implications of the graph structure. Next, we propose a probabilistic classification model based on HEX graphs and show that it enjoys a number of desirable properties. Finally, we evaluate our method using a large-scale benchmark. Empirical results demonstrate that our model can significantly improve object classification by exploiting the label relations.

show abstract

“…Semantic attribute representations have various benefits: They are often more powerful than using low-level features directly for high-level tasks such as classification [12]; they provide a form of transfer/multi-task learning because an attribute can be learned from multiple classes or instances exhibiting that attribute [8]; they can be used in conjunction with raw data for greater effectiveness [8,13]; and finally they are a suitable representation for direct human interaction, therefore allowing searches to be specified or constrained by attributes [11,12,21]. This final property can facilitate man-in-the-loop active learning when available data for model training is sparse and biased.…”

Section: Related Work and Contributionsmentioning

confidence: 99%

Person Re-identification by Attributes

Layne¹,

Hospedales²,

Gong³

2012

Procedings of the British Machine Vision Conference 2012

299

186

View full text Add to dashboard Cite

Visually identifying a target individual reliably in a crowded environment observed by a distributed camera network is critical to a variety of tasks in managing business information, border control, and crime prevention. Automatic re-identification of a human candidate from public space CCTV video is challenging due to spatiotemporal visual feature variations and strong visual similarity between different people, compounded by low-resolution and poor quality video data. In this work, we propose a novel method for re-identification that learns a selection and weighting of mid-level semantic attributes to describe people. Specifically, the model learns an attribute-centric, parts-based feature representation. This differs from and complements existing low-level features for re-identification that rely purely on bottom-up statistics for feature selection, which are limited in discriminating and identifying reliably visual appearances of target people appearing in different camera views under certain degrees of occlusion due to crowdedness. Our experiments demonstrate the effectiveness of our approach compared to existing feature representations when applied to benchmarking datasets.

show abstract

Sharing features between objects and their attributes

Cited by 111 publications

References 20 publications

Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation

Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation

Large-Scale Object Classification Using Label Relation Graphs

Person Re-identification by Attributes

Contact Info

Product

Resources

About