Collaborating Authors

The Image Similarity Challenge and data set for detecting image manipulation


We also worked with trained third-party annotators to manually transform a smaller subset of the images to ensure we have even more selections representative of the way a human user would transform images. The annotators used image manipulation software GIMP to manually alter images in diverse ways that we cannot easily automate, for example handwriting or drawing on the images or cropping to leave only the part of the image most salient to the human eye. The Image Similarity Challenge invites participants to test their image matching techniques on the Image Similarity data set. More information for researchers is available here, and the accompanying paper is available here. For researchers considering attending NeurIPS 2021 in December, we're also pleased to announce that the Image Similarity Challenge has been accepted for the NeurIPS 2021 competition track, where we will be announcing the winners of this challenge (The competition is subject to official rules.

Node Similarity For Anomaly Detection in Attributed Graphs

AAAI Conferences

Most graph-based anomaly detection work uses structural graph connectivity or node information for discovering anomalies in a graph. Approaches solely relying on node information for detecting anomalies do not exploit the structural information, and approaches relying on just the structural connectivity information do not exploit node label values, or attribute information. Little research has been done that uses both structural connectivity as well as node attributes for finding anomalies in data represented as a graph. In this work, we attempt to use both the node attribute information together with the structural connectivity in order to discover anomalies in a graph. While existing approaches treat all the attribute values as discrete, when the attributes are numeric values, they lose their measure of similarity or closeness of information. In this work, in order to preserve the closeness information, we consider the similarities in node values using not only single attributes, but also multiple attributes. In order to discover the similarity between the attribute values, we use a discretization method, distance-based similarity measures, and a k-means clustering approach. After discovering nodes with similar label values, we use revised labels together with structural properties for discovering anomalies in a graph. Our hypothesis is that if we use node label similarity information together with structural properties of the graph, we can detect anomalies which would be missed by approaches only relying on either structural connectivity or node attribute information.

FANTrack: 3D Multi-Object Tracking with Feature Association Network Artificial Intelligence

We propose a data-driven approach to online multi-object tracking (MOT) that uses a convolutional neural network (CNN) for data association in a tracking-by-detection framework. The problem of multi-target tracking aims to assign noisy detections to a-priori unknown and time-varying number of tracked objects across a sequence of frames. A majority of the existing solutions focus on either tediously designing cost functions or formulating the task of data association as a complex optimization problem that can be solved effectively. Instead, we exploit the power of deep learning to formulate the data association problem as inference in a CNN. To this end, we propose to learn a similarity function that combines cues from both image and spatial features of objects. Our solution learns to perform global assignments in 3D purely from data, handles noisy detections and a varying number of targets, and is easy to train. We evaluate our approach on the challenging KITTI dataset and show competitive results. Our code is available at

Dynamic change-point detection using similarity networks Machine Learning

From a sequence of similarity networks, with edges representing certain similarity measures between nodes, we are interested in detecting a change-point which changes the statistical property of the networks. After the change, a subset of anomalous nodes which compares dissimilarly with the normal nodes. We study a simple sequential change detection procedure based on node-wise average similarity measures, and study its theoretical property. Simulation and real-data examples demonstrate such a simply stopping procedure has reasonably good performance. We further discuss the faulty sensor isolation (estimating anomalous nodes) using community detection.

An Unsupervised Normalization Algorithm for Noisy Text: A Case Study for Information Retrieval and Stance Detection Artificial Intelligence

A large fraction of textual data available today contains various types of 'noise', such as OCR noise in digitized documents, noise due to informal writing style of users on microblogging sites, and so on. To enable tasks such as search/retrieval and classification over all the available data, we need robust algorithms for text normalization, i.e., for cleaning different kinds of noise in the text. There have been several efforts towards cleaning or normalizing noisy text; however, many of the existing text normalization methods are supervised and require language-dependent resources or large amounts of training data that is difficult to obtain. We propose an unsupervised algorithm for text normalization that does not need any training data / human intervention. The proposed algorithm is applicable to text over different languages, and can handle both machine-generated and human-generated noise. Experiments over several standard datasets show that text normalization through the proposed algorithm enables better retrieval and stance detection, as compared to that using several baseline text normalization methods. Implementation of our algorithm can be found at