Masayuki Mukunoki

Set based discriminative ranking for recognition

Recently both face recognition and body-based person re-identification have been extended from single-image based scenarios to video-based or even more generally image-set based problems. Set-based recognition brings new research and application opportunities while at the same time raises great modeling and optimization challenges. How to make the best use of the available multiple samples for each individual while at the same time not be disturbed by the great within-set variations is considered by us to be the major issue. Due to the difficulty of designing a global optimal learning model, most existing solutions are still based on unsupervised matching, which can be further categorized into three groups: a) set-based signature generation, b) direct set-to-set matching, and c) between-set distance finding. The first two count on good feature representation while the third explores data set structure and set-based distance measurement. The main shortage of them is the lack of learning-based discrimination ability. In this paper, we propose a set-based discriminative ranking model (SBDR), which iterates between set-to-set distance finding and discriminative feature space projection to achieve simultaneous optimization of these two. Extensive experiments on widely-used face recognition and person re-identification datasets not only demonstrate the superiority of our approach, but also shed some light on its properties and application domain.

Collaboratively Regularized Nearest Points for Set Based Recognition.

Set based recognition has been attracting more and more attention in recent years, benefitting from two facts: the difficulty of collecting sets of images for recognition fades quickly, and set based recognition models generally outperform the ones for single instance based recognition. In this paper, we propose a novel model called collaboratively regularized nearest points (CRNP) for solving this problem. The proposal inherits the merits of simplicity, robustness, and high-efficiency from the very recently introduced regularized nearest points (RNP) method on finding the set-to-set distance using the l2-norm regularized affine hulls. Meanwhile, CRNP makes use of the powerful discriminative ability induced by collaborative representation, following the same idea as that in sparse recognition for classification (SRC) for image-based recognition and collaborative sparse approximation (CSA) for set-based recognition. However, CRNP uses l2-norm instead of the expensive l1-norm for coefficients regularization, which makes it much more efficient. Extensive experiments on five benchmark datasets for face recognition and person re-identification demonstrate that CRNP is not only more effective but also significantly faster than other state-of-the-art methods, including RNP and CSA.

Optimizing Mean Reciprocal Rank for person re-identification

Person re-identification is one of the most challenging issues in network-based surveillance. The difficulties mainly come from the great appearance variations induced by illumination, camera view and body pose changes. Maybe influenced by the research on face recognition and general object recognition, this problem is habitually treated as a verification or classification problem, and much effort has been put on optimizing standard recognition criteria. However, we found that in practical applications the users usually have different expectations. For example, in a real surveillance system, we may expect that a visual user interface can show us the relevant images in the first few (e.g. 20) candidates, but not necessarily before all the irrelevant ones. In other words, there is no problem to leave the final judgement to the users. Based on such an observation, this paper treats the re-identification problem as a ranking problem and directly optimizes a listwise ranking function named Mean Reciprocal Rank (MRR), which is considered by us to be able to generate results closest to human expectations. Using a maximum-margin based structured learning model, we are able to show improved re-identification results on widely-used benchmark datasets

Shadow removal from a real image based on shadow density

Shadows are physical phenomena observed in most natural scenes. Since shadows and shades enhance the reality of images, many studies on shadowing and shading have been done for realistic image generation. Shadows, however, often poses difficulties when using real images in image synthesis, because shadows imply the geometric relationship between objects, light source, and viewpoint. This means that real images including shadows are used for image synthesis only in a limited situation where the lighting condition is consistent with that of the real images [Sato et al. 1999].

Collaborative Sparse Approximation for Multiple-Shot Across-Camera Person Re-identification

In this paper we propose a simple and effective solution to the important and challenging problem of across-camera person re-identification. We focus on the common case in video surveillance where multiple images or video frames are available for each person. Instead of exploring new features, the proposed approach aims at making a better use of such images/frames. It builds a collaborative representation over all the gallery images (of known person individuals) to best approximate the query images (containing an unknown person) via affine combinations. The approximation is measured by the nearest point distance between the two affine hulls constructed by the query images and gallery images, respectively. By enforcing the sparsity of the samples used for approximating the two nearest points, the relative importance of the gallery images belonging to different persons has the ability to reveal the identity of the querying person. Extensive experiments on public benchmark datasets demonstrate that the proposed approach greatly outperforms the state-of-the-art methods.

Common-near-neighbor analysis for person re-identification

Person re-identification tackles the problem whether an observed person of interest reappears in a network of cameras. The difficulty primarily originates from few samples per class but large amounts of intra-class variations in real scenarios: illumination, pose and viewpoint changes across cameras. So far, proposals in the literature have treated this either as a matching problem focusing on feature representation or as a classification/ranking problem relying on metric optimization. This paper presents a new way called Common-Near-Neighbor Analysis, which to some extent combines the strengths of these two methodologies. It analyzes the commonness of the near neighbors of each pair of samples in a learned metric space, measured by a novel rank-order based dissimilarity. Our method, using only color cue, has been tested on widely-used benchmark datasets, showing significant performance improvement over the state-of-the-art.

Tracking Food Materials with Changing Their Appearance in Food Preparing

This paper describes our work in computer vision to track food materials in the food preparation process. Tracking such food materials is difficult, because they are often hidden when moved by hand. Furthermore, their appearance may change in hand when they are cut or peeled. For tracking these objects in such situations, we propose a novel method that matches an object on a cooking table to one grasped in the past. We use the following three criteria to match the objects even when they are cut or peeled: the similarity in their appearance, the validity of their change in appearance, and the grasped order. We experimentally evaluated our method by applying it to the scenes of cutting and peeling food materials. As a result, we achieved an accuracy of 83.6% in matching the objects.

Retrieval of Images Using Pixel-based Objects Models

We apply our Pixel-based object labeling method to the problem of indexing images. Our method is a means to assign an object label to each pixel in out-door scenes. It is suitable for automatic object labeling and applicable to automatic indexing problems.

Can feature-based inductive transfer learning help person re-identification?

Person re-identification concerns about the problem of recognizing people across space (captured by different cameras) and/or over time gaps. Though recently the literature on it grows rapidly, all the proposed solutions have treated it as a normal classification or ranking problem. In this paper, however, we argue that it is in fact a natural transfer learning problem, thus its valuable and also necessary to investigate how the progress on transfer learning could benefit the research on it. We present so far the first study on justifying the effectiveness of a representative transfer learning methodology: feature-based inductive transfer learning, for person re-identification. Extensive experiments on standard datasets with typical methods result in several important findings.

Coupled metric learning for single-shot versus single-shot person reidentification

Abstract. Person reidentification tackles the problem of building a correspondence between different images of the same person captured by distributed cameras. To date, attempts to solve this problem have focused on either feature representation or learning methods. Usually, the greater the number of the samples for each person, the better the reidentification performance is. However, in the real world, we may not be able to acquire enough samples to give acceptable performance. Here, we focus on the so-called “single-shot versus single-shot” problem: matching one image of a person to another. Because of the extremely small sample class size, there is limited scope to statistically weaken the empirical risk for hand-crafted feature representation. Therefore, we resort to metric learning methods, such as the ranking-specialized metric learning to rank (MLR) and the classification-based maximally collapsing metric learning (MCML). Taking advantage of the complementarity between them, we propose a novel “coupled metric learning” approach. This searches for the optimal linear projection for the original feature space using MCML before minimizing the ranking loss via MLR. Experiments on widely used benchmark datasets show encouraging results.