Related papers: Context-Aware Unsupervised Clustering for Person S…
Clustering is an unsupervised machine learning methodology where unlabeled elements/objects are grouped together aiming to the construction of well-established clusters that their elements are classified according to their similarity. The…
With the development of deep learning techniques, supervised learning has achieved performances surpassing those of humans. Researchers have designed numerous corresponding models for different data modalities, achieving excellent results…
Intra-camera supervision (ICS) for person re-identification (Re-ID) assumes that identity labels are independently annotated within each camera view and no inter-camera identity association is labeled. It is a new setting proposed recently…
Correlation clustering is a well-known unsupervised learning setting that deals with positive and negative pairwise similarities. In this paper, we study the case where the pairwise similarities are not given in advance and must be queried…
Learning an object detector or retrieval requires a large data set with manual annotations. Such data sets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we propose to exploit…
Supervised classification approaches can predict labels for unknown data because of the supervised training process. The success of classification is heavily dependent on the labeled training data. Differently, clustering is effective in…
Reliable markerless motion tracking of people participating in a complex group activity from multiple moving cameras is challenging due to frequent occlusions, strong viewpoint and appearance variations, and asynchronous video streams. To…
Unsupervised domain adaptation (UDA) for person re-identification is challenging because of the huge gap between the source and target domain. A typical self-training method is to use pseudo-labels generated by clustering algorithms to…
Domain adaptation in person re-identification (re-ID) has always been a challenging task. In this work, we explore how to harness the natural similar characteristics existing in the samples from the target domain for learning to conduct…
In this paper, we focus on the semi-supervised person re-identification (Re-ID) case, which only has the intra-camera (within-camera) labels but not inter-camera (cross-camera) labels. In real-world applications, these intra-camera labels…
Unsupervised image classification, or image clustering, aims to group unlabeled images into semantically meaningful categories. Early methods integrated representation learning and clustering within an iterative framework. However, the rise…
Several unsupervised and self-supervised approaches have been developed in recent years to learn visual features from large-scale unlabeled datasets. Their main drawback however is that these methods are hardly able to recognize visual…
Existing neural network architectures in computer vision -- whether designed by humans or by machines -- were typically found using both images and their associated labels. In this paper, we ask the question: can we find high-quality neural…
In the conventional person re-id setting, it is assumed that the labeled images are the person images within the bounding box for each individual; this labeling across multiple nonoverlapping camera views from raw video surveillance is…
Image clustering is to group a set of images into disjoint clusters in a way that images in the same cluster are more similar to each other than to those in other clusters, which is an unsupervised or semi-supervised learning process. It is…
Mostexistingpersonre-identification(re-id)methods relyon supervised model learning on per-camera-pair manually labelled pairwise training data. This leads to poor scalability in practical re-id deployment due to the lack of exhaustive…
Person search is a challenging task which aims to achieve joint pedestrian detection and person re-identification (ReID). Previous works have made significant advances under fully and weakly supervised settings. However, existing methods…
After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects. However, building good object localizers (i.e., detectors) currently…
Feature selection methods have an important role on the readability of data and the reduction of complexity of learning algorithms. In recent years, a variety of efforts are investigated on feature selection problems based on unsupervised…
Face recognition from a single image per person is a challenging problem because the training sample is extremely small. We consider a variation of this problem. In our problem, we recognize only one person, and there are no labeled data…