Terminus Group, Beijing, China
Abstract:Unseen Action Recognition (UAR) aims to recognise novel action categories without training examples. While previous methods focus on inner-dataset seen/unseen splits, this paper proposes a pipeline using a large-scale training source to achieve a Universal Representation (UR) that can generalise to a more realistic Cross-Dataset UAR (CD-UAR) scenario. We first address UAR as a Generalised Multiple-Instance Learning (GMIL) problem and discover 'building-blocks' from the large-scale ActivityNet dataset using distribution kernels. Essential visual and semantic components are preserved in a shared space to achieve the UR that can efficiently generalise to new datasets. Predicted UR exemplars can be improved by a simple semantic adaptation, and then an unseen action can be directly recognised using UR during the test. Without further training, extensive experiments manifest significant improvements over the UCF101 and HMDB51 benchmarks.
Abstract:Recent studies show that large-scale sketch-based image retrieval (SBIR) can be efficiently tackled by cross-modal binary representation learning methods, where Hamming distance matching significantly speeds up the process of similarity search. Providing training and test data subjected to a fixed set of pre-defined categories, the cutting-edge SBIR and cross-modal hashing works obtain acceptable retrieval performance. However, most of the existing methods fail when the categories of query sketches have never been seen during training. In this paper, the above problem is briefed as a novel but realistic zero-shot SBIR hashing task. We elaborate the challenges of this special task and accordingly propose a zero-shot sketch-image hashing (ZSIH) model. An end-to-end three-network architecture is built, two of which are treated as the binary encoders. The third network mitigates the sketch-image heterogeneity and enhances the semantic relations among data by utilizing the Kronecker fusion layer and graph convolution, respectively. As an important part of ZSIH, we formulate a generative hashing scheme in reconstructing semantic knowledge representations for zero-shot retrieval. To the best of our knowledge, ZSIH is the first zero-shot hashing work suitable for SBIR and cross-modal search. Comprehensive experiments are conducted on two extended datasets, i.e., Sketchy and TU-Berlin with a novel zero-shot train-test split. The proposed model remarkably outperforms related works.
Abstract:This paper proposes a deep learning model to efficiently detect salient regions in videos. It addresses two important issues: (1) deep video saliency model training with the absence of sufficiently large and pixel-wise annotated video data, and (2) fast video saliency training and detection. The proposed deep video saliency network consists of two modules, for capturing the spatial and temporal saliency information, respectively. The dynamic saliency model, explicitly incorporating saliency estimates from the static saliency model, directly produces spatiotemporal saliency inference without time-consuming optical flow computation. We further propose a novel data augmentation technique that simulates video training data from existing annotated image datasets, which enables our network to learn diverse saliency information and prevents overfitting with the limited number of training videos. Leveraging our synthetic video data (150K video sequences) and real videos, our deep video saliency model successfully learns both spatial and temporal saliency cues, thus producing accurate spatiotemporal saliency estimate. We advance the state-of-the-art on the DAVIS dataset (MAE of .06) and the FBMS dataset (MAE of .07), and do so with much improved speed (2fps with all steps).
Abstract:Face retrieval has received much attention over the past few decades, and many efforts have been made in retrieving face images against pose, illumination, and expression variations. However, the conventional works fail to meet the requirements of a potential and novel task --- retrieving a person's face image at a specific age, especially when the specific 'age' is not given as a numeral, i.e. 'retrieving someone's image at the similar age period shown by another person's image'. To tackle this problem, we propose a dual reference face retrieval framework in this paper, where the system takes two inputs: an identity reference image which indicates the target identity and an age reference image which reflects the target age. In our framework, the raw images are first projected on a joint manifold, which preserves both the age and identity locality. Then two similarity metrics of age and identity are exploited and optimized by utilizing our proposed quartet-based model. The experiments show promising results, outperforming hierarchical methods.
Abstract:Correlation filters are special classifiers designed for shift-invariant object recognition, which are robust to pattern distortions. The recent literature shows that combining a set of sub-filters trained based on a single or a small group of images obtains the best performance. The idea is equivalent to estimating variable distribution based on the data sampling (bagging), which can be interpreted as finding solutions (variable distribution approximation) directly from sampled data space. However, this methodology fails to account for the variations existed in the data. In this paper, we introduce an intermediate step -- solution sampling -- after the data sampling step to form a subspace, in which an optimal solution can be estimated. More specifically, we propose a new method, named latent constrained correlation filters (LCCF), by mapping the correlation filters to a given latent subspace, and develop a new learning framework in the latent subspace that embeds distribution-related constraints into the original problem. To solve the optimization problem, we introduce a subspace based alternating direction method of multipliers (SADMM), which is proven to converge at the saddle point. Our approach is successfully applied to three different tasks, including eye localization, car detection and object tracking. Extensive experiments demonstrate that LCCF outperforms the state-of-the-art methods. The source code will be publicly available. https://github.com/bczhangbczhang/.
Abstract:Cross-modal hashing is usually regarded as an effective technique for large-scale textual-visual cross retrieval, where data from different modalities are mapped into a shared Hamming space for matching. Most of the traditional textual-visual binary encoding methods only consider holistic image representations and fail to model descriptive sentences. This renders existing methods inappropriate to handle the rich semantics of informative cross-modal data for quality textual-visual search tasks. To address the problem of hashing cross-modal data with semantic-rich cues, in this paper, a novel integrated deep architecture is developed to effectively encode the detailed semantics of informative images and long descriptive sentences, named as Textual-Visual Deep Binaries (TVDB). In particular, region-based convolutional networks with long short-term memory units are introduced to fully explore image regional details while semantic cues of sentences are modeled by a text convolutional network. Additionally, we propose a stochastic batch-wise training routine, where high-quality binary codes and deep encoding functions are efficiently optimized in an alternating manner. Experiments are conducted on three multimedia datasets, i.e. Microsoft COCO, IAPR TC-12, and INRIA Web Queries, where the proposed TVDB model significantly outperforms state-of-the-art binary coding methods in the task of cross-modal retrieval.
Abstract:Existing block-diagonal representation researches mainly focuses on casting block-diagonal regularization on training data, while only little attention is dedicated to concurrently learning both block-diagonal representations of training and test data. In this paper, we propose a discriminative block-diagonal low-rank representation (BDLRR) method for recognition. In particular, the elaborate BDLRR is formulated as a joint optimization problem of shrinking the unfavorable representation from off-block-diagonal elements and strengthening the compact block-diagonal representation under the semi-supervised framework of low-rank representation. To this end, we first impose penalty constraints on the negative representation to eliminate the correlation between different classes such that the incoherence criterion of the extra-class representation is boosted. Moreover, a constructed subspace model is developed to enhance the self-expressive power of training samples and further build the representation bridge between the training and test samples, such that the coherence of the learned intra-class representation is consistently heightened. Finally, the resulting optimization problem is solved elegantly by employing an alternative optimization strategy, and a simple recognition algorithm on the learned representation is utilized for final prediction. Extensive experimental results demonstrate that the proposed method achieves superb recognition results on four face image datasets, three character datasets, and the fifteen scene multi-categories dataset. It not only shows superior potential on image recognition but also outperforms state-of-the-art methods.
Abstract:Cross-modal image synthesis is a topical problem in medical image computing. Existing methods for image synthesis are either tailored to a specific application, require large scale training sets, or are based on partitioning images into overlapping patches. In this paper, we propose a novel Dual cOnvolutional filTer lEarning (DOTE) approach to overcome the drawbacks of these approaches. We construct a closed loop joint filter learning strategy that generates informative feedback for model self-optimization. Our method can leverage data more efficiently thus reducing the size of the required training set. We extensively evaluate DOTE in two challenging tasks: image super-resolution and cross-modality synthesis. The experimental results demonstrate superior performance of our method over other state-of-the-art methods.
Abstract:There is a neglected fact in the traditional machine learning methods that the data sampling can actually lead to the solution sampling. We consider this observation to be important because having the solution sampling available makes the variable distribution estimation, which is a problem in many learning-related applications, more tractable. In this paper, we implement this idea on correlation filter, which has attracted much attention in the past few years due to its high performance with a low computational cost. More specifically, we propose a new method, named latent constrained correlation filters (LCCF) by mapping the correlation filters to a given latent subspace, in which we establish a new learning framework that embeds distribution-related constraints into the original problem. We further introduce a subspace based alternating direction method of multipliers (SADMM) to efficiently solve the optimization problem, which is proved to converge at the saddle point. Our approach is successfully applied to two different tasks inclduing eye localization and car detection. Extensive experiments demonstrate that LCCF outperforms the state-of-the-art methods when samples are suffered from noise and occlusion.
Abstract:Magnetic Resonance Imaging (MRI) offers high-resolution \emph{in vivo} imaging and rich functional and anatomical multimodality tissue contrast. In practice, however, there are challenges associated with considerations of scanning costs, patient comfort, and scanning time that constrain how much data can be acquired in clinical or research studies. In this paper, we explore the possibility of generating high-resolution and multimodal images from low-resolution single-modality imagery. We propose the weakly-supervised joint convolutional sparse coding to simultaneously solve the problems of super-resolution (SR) and cross-modality image synthesis. The learning process requires only a few registered multimodal image pairs as the training set. Additionally, the quality of the joint dictionary learning can be improved using a larger set of unpaired images. To combine unpaired data from different image resolutions/modalities, a hetero-domain image alignment term is proposed. Local image neighborhoods are naturally preserved by operating on the whole image domain (as opposed to image patches) and using joint convolutional sparse coding. The paired images are enhanced in the joint learning process with unpaired data and an additional maximum mean discrepancy term, which minimizes the dissimilarity between their feature distributions. Experiments show that the proposed method outperforms state-of-the-art techniques on both SR reconstruction and simultaneous SR and cross-modality synthesis.