Search

Zero-Shot Learning (ZSL) for visual recognition is typically achieved by exploiting a semantic embedding space. In such a space, both seen and unseen class labels as well as image features can be embedded so that the similarity among them can be measured directly. In this work, we consider that the key to effective ZSL is to compute an optimal distance metric in the semantic embedding space. Existing ZSL works employ either euclidean or cosine distances. However, in a high-dimensional space where the projected class labels (prototypes) are sparse, these distances are suboptimal, resulting in a number of problems including hubness and domain shift. To overcome these problems, a novel manifold distance computed on a semantic class prototype graph is proposed which takes into account the rich intrinsic semantic structure, i.e., semantic manifold, of the class prototype distribution. To further alleviate the domain shift problem, a new regularisation term is introduced into a ranking loss based embedding model. Specifically, the ranking loss objective is regularised by unseen class prototypes to prevent the projected object features from being biased towards the seen prototypes. Extensive experiments on four benchmarks show that our method significantly outperforms the state-of-the-art. [ABSTRACT FROM AUTHOR]

Video analysis often begins with background subtraction. This problem is often approached in two steps—a background model followed by a regularisation scheme. A model of the background allows it to be distinguished on a per-pixel basis from the foreground, whilst the regularisation combines information from adjacent pixels. We present a new method based on Dirichlet process Gaussian mixture models, which are used to estimate per-pixel background distributions. It is followed by probabilistic regularisation. Using a non-parametric Bayesian method allows per-pixel mode counts to be automatically inferred, avoiding over-/under- fitting. We also develop novel model learning algorithms for continuous update of the model in a principled fashion as the scene changes. These key advantages enable us to outperform the state-of-the-art alternatives on four benchmarks. [ABSTRACT FROM PUBLISHER]

Person re-identification (re-id) aims to match people across non-overlapping camera views in a public space. This is a challenging problem because the people captured in surveillance videos often wear similar clothing. Consequently, the differences in their appearance are typically subtle and only detectable at particular locations and scales. In this paper, we propose a deep re-id network (MuDeep) that is composed of two novel types of layers – a multi-scale deep learning layer, and a leader-based attention learning layer. Specifically, the former learns deep discriminative feature representations at different scales, while the latter utilizes the information from multiple scales to lead and determine the optimal weightings for each scale. The importance of different spatial locations for extracting discriminative features is learned explicitly via our leader-based attention learning layer. Extensive experiments are carried out to demonstrate that the proposed MuDeep outperforms the state-of-the-art on a number of benchmarks and has a better generalization ability under a domain generalization setting. [ABSTRACT FROM AUTHOR]

A number of vision problems such as zero-shot learning and person re-identification can be considered as cross-class transfer learning problems. As mid-level semantic properties shared cross different object classes, attributes have been studied extensively for knowledge transfer across classes. Most previous attribute learning methods focus only on human-defined/nameable semantic attributes, whilst ignoring the fact there also exist undefined/latent shareable visual properties, or latent attributes. These latent attributes can be either discriminative or non-discriminative parts depending on whether they can contribute to an object recognition task. In this work, we argue that learning the latent attributes jointly with user-defined semantic attributes not only leads to better representation but also helps semantic attribute prediction. A novel dictionary learning model is proposed which decomposes the dictionary space into three parts corresponding to semantic, latent discriminative and latent background attributes respectively. Such a joint attribute learning model is then extended by following a multi-task transfer learning framework to address a more challenging unsupervised domain adaptation problem, where annotations are only available on an auxiliary dataset and the target dataset is completely unlabelled. Extensive experiments show that the proposed models, though being linear and thus extremely efficient to compute, produce state-of-the-art results on both zero-shot learning and person re-identification. [ABSTRACT FROM AUTHOR]

A weakly supervised semantic segmentation (WSSS) method aims to learn a segmentation model from weak (image-level) as opposed to strong (pixel-level) labels. By avoiding the tedious pixel-level annotation process, it can exploit the unlimited supply of user-tagged images from media-sharing sites such as Flickr for large scale applications. However, these ‘free’ tags/labels are often noisy and few existing works address the problem of learning with both weak and noisy labels. In this work, we cast the WSSS problem into a label noise reduction problem. Specifically, after segmenting each image into a set of superpixels, the weak and potentially noisy image-level labels are propagated to the superpixel level resulting in highly noisy labels; the key to semantic segmentation is thus to identify and correct the superpixel noisy labels. To this end, a novel $L_1$ -optimisation based sparse learning model is formulated to directly and explicitly detect noisy labels. To solve the $L_1$ -optimisation problem, we further develop an efficient learning algorithm by introducing an intermediate labelling variable. Extensive experiments on three benchmark datasets show that our method yields state-of-the-art results given noise-free labels, whilst significantly outperforming the existing methods when the weak labels are also noisy. [ABSTRACT FROM PUBLISHER]

Solving the problem of matching people across non-overlapping multi-camera views, known as person re-identification (re-id), has received increasing interests in computer vision. In a real-world application scenario, a watch-list (gallery set) of a handful of known target people are provided with very few (in many cases only a single) image(s) (shots) per target. Existing re-id methods are largely unsuitable to address this open-world re-id challenge because they are designed for (1) a closed-world scenario where the gallery and probe sets are assumed to contain exactly the same people, (2) person-wise identification whereby the model attempts to verify exhaustively against each individual in the gallery set, and (3) learning a matching model using multi-shots. In this paper, a novel transfer local relative distance comparison (t-LRDC) model is formulated to address the open-world person re-identification problem by one-shot group-based verification. The model is designed to mine and transfer useful information from a labelled open-world non-target dataset. Extensive experiments demonstrate that the proposed approach outperforms both non-transfer learning and existing transfer learning based re-id methods. [ABSTRACT FROM PUBLISHER]

Benefitting from the outstanding capabilities of intelligent controlling and prediction, federated learning (FL) has been widely applied in Internet of Vehicle (IoV). However, applying FL into fog-computing-based IoV still suffers from two crucial problems: (i) how to achieve the privacy-preserving FL under the flexible architecture of fog computing with no assistance of cloud server, and (ii) how to guarantee the privacy-preserving FL to perform with high efficiency and low overhead in fog-computing settings. For addressing the above issues, we propose a practical framework, named Galaxy, the first of its kind in the regime of privacy-preserving FL under the setting of non-cloud-assisted fog computing. Based on the secure multi-party computation (MPC) technology, our framework satisfies the $\boldsymbol{(T,N)}$ -threshold property, permitting $\boldsymbol{N}$ (a scalable number) fog nodes to cooperate with multiple users for implementing privacy-preserving FL, while resisting the collusion up to $\boldsymbol{T}-\boldsymbol{1}$ fog nodes, and being robust to at most $\boldsymbol{N}-\boldsymbol{T}$ fog nodes simultaneously dropping out. Besides, considering the practical scenario that low-quality data may negatively impair the FL model convergence, our scheme can handle users’ low-quality data while protecting all user-related information under our secure framework. Based on the above superior properties, our scheme can perform with high scalability, high processing efficiency, and low resource overhead, being practical for fog-computing-based IoV. Extensive experiment results demonstrate our scheme with high-level performance. [ABSTRACT FROM AUTHOR]

One of the most interesting and desired capabilities for automated video behavior analysis is the identification of rarely occurring and subtle behaviors. This is of practical value because dangerous or illegal activities often have few or possibly only one prior example to learn from and are often subtle. Rare and subtle behavior learning is challenging for two reasons: 1) Contemporary modeling approaches require more data and supervision than may be available and 2) the most interesting and potentially critical rare behaviors are often visually subtle—occurring among more obvious typical behaviors or being defined by only small spatio-temporal deviations from typical behaviors. In this paper, we introduce a novel weakly supervised joint topic model which addresses these issues. Specifically, we introduce a multiclass topic model with partially shared latent structure and associated learning and inference algorithms. These contributions will permit modeling of behaviors from as few as one example, even without localization by the user and when occurring in clutter, and subsequent classification and localization of such behaviors online and in real time. We extensively validate our approach on two standard public-space data sets, where it clearly outperforms a batch of contemporary alternatives. [ABSTRACT FROM PUBLISHER]