The Planteome database: an integrated resource for reference ontologies, plant genomics and phenomics.

The Planteome project (http://www.planteome.org) provides a suite of reference and species-specific ontologies for plants and annotations to genes and phenotypes. Ontologies serve as common standards for semantic integration of a large and growing corpus of plant genomics, phenomics and genetics data. The reference ontologies include the Plant Ontology, Plant Trait Ontology and the Plant Experimental Conditions Ontology developed by the Planteome project, along with the Gene Ontology, Chemical Entities of Biological Interest, Phenotype and Attribute Ontology, and others. The project also provides access to species-specific Crop Ontologies developed by various plant breeding and research communities from around the world. We provide integrated data on plant traits, phenotypes, and gene function and expression from 95 plant taxa, annotated with reference ontology terms. The Planteome project is developing a plant gene annotation platform; Planteome Noctua, to facilitate community engagement. All the Planteome ontologies are publicly available and are maintained at the Planteome GitHub site (https://github.com/Planteome) for sharing, tracking revisions and new requests. The annotated data are freely accessible from the ontology browser (http://browser.planteome.org/amigo) and our data repository.

CX-ToM: Counterfactual explanations with theory-of-mind for enhancing human trust in image recognition models.

We propose CX-ToM, short for counterfactual explanations with theory-of-mind, a new explainable AI (XAI) framework for explaining decisions made by a deep convolutional neural network (CNN). In contrast to the current methods in XAI that generate explanations as a single shot response, we pose explanation as an iterative communication process, i.e., dialogue between the machine and human user. More concretely, our CX-ToM framework generates a sequence of explanations in a dialogue by mediating the differences between the minds of the machine and human user. To do this, we use Theory of Mind (ToM) which helps us in explicitly modeling the human's intention, the machine's mind as inferred by the human, as well as human's mind as inferred by the machine. Moreover, most state-of-the-art XAI frameworks provide attention (or heat map) based explanations. In our work, we show that these attention-based explanations are not sufficient for increasing human trust in the underlying CNN model. In CX-ToM, we instead use counterfactual explanations called fault-lines which we define as follows: given an input image I for which a CNN classification model M predicts class c pred , a fault-line identifies the minimal semantic-level features (e.g., stripes on zebra), referred to as explainable concepts, that need to be added to or deleted from I to alter the classification category of I by M to another specified class c alt . Extensive experiments verify our hypotheses, demonstrating that our CX-ToM significantly outperforms the state-of-the-art XAI models.

Unsupervised category modeling, recognition, and segmentation in images.

Suppose a set of arbitrary (unlabeled) images contains frequent occurrences of 2D objects from an unknown category. This paper is aimed at simultaneously solving the following related problems: (1) unsupervised identification of photometric, geometric, and topological properties of multiscale regions comprising instances of the 2D category; (2) learning a region-based structural model of the category in terms of these properties; and (3) detection, recognition and segmentation of objects from the category in new images. To this end, each image is represented by a tree that captures a multiscale image segmentation. The trees are matched to extract the maximally matching subtrees across the set, which are taken as instances of the target category. The extracted subtrees are then fused into a tree-union that represents the canonical category model. Detection, recognition, and segmentation of objects from the learned category are achieved simultaneously by finding matches of the category model with the segmentation tree of a new image. Experimental validation on benchmark datasets demonstrates the robustness and high accuracy of the learned category models, when only a few training examples are used for learning without any human supervision.

Learning and Inferring "Dark Matter" and Predicting Human Intents and Trajectories in Videos.

This paper presents a method for localizing functional objects and predicting human intents and trajectories in surveillance videos of public spaces, under no supervision in training. People in public spaces are expected to intentionally take shortest paths (subject to obstacles) toward certain objects (e.g., vending machine, picnic table, dumpster etc.) where they can satisfy certain needs (e.g., quench thirst). Since these objects are typically very small or heavily occluded, they cannot be inferred by their visual appearance but indirectly by their influence on people's trajectories. Therefore, we call them "dark matter", by analogy to cosmology, since their presence can only be observed as attractive or repulsive "fields" in the public space. A person in the scene is modeled as an intelligent agent engaged in one of the "fields" selected depending his/her intent. An agent's trajectory is derived from an Agent-based Lagrangian Mechanics. The agents can change their intents in the middle of motion and thus alter the trajectory. For evaluation, we compiled and annotated a new dataset. The results demonstrate our effectiveness in predicting human intent behaviors and trajectories, and localizing and discovering distinct types of "dark matter" in wide public spaces.

Doubly Sparse Relevance Vector Machine for Continuous Facial Behavior Estimation.

Certain inner feelings and physiological states like pain are subjective states that cannot be directly measured, but can be estimated from spontaneous facial expressions. Since they are typically characterized by subtle movements of facial parts, analysis of the facial details is required. To this end, we formulate a new regression method for continuous estimation of the intensity of facial behavior interpretation, called Doubly Sparse Relevance Vector Machine (DSRVM). DSRVM enforces double sparsity by jointly selecting the most relevant training examples (a.k.a. relevance vectors) and the most important kernels associated with facial parts relevant for interpretation of observed facial expressions. This advances prior work on multi-kernel learning, where sparsity of relevant kernels is typically ignored. Empirical evaluation on challenging Shoulder Pain videos, and the benchmark DISFA and SEMAINE datasets demonstrate that DSRVM outperforms competing approaches with a multi-fold reduction of running times in training and testing.

Sum Product Networks for Activity Recognition.

This paper addresses detection and localization of human activities in videos. We focus on activities that may have variable spatiotemporal arrangements of parts, and numbers of actors. Such activities are represented by a sum-product network (SPN). A product node in SPN represents a particular arrangement of parts, and a sum node represents alternative arrangements. The sums and products are hierarchically organized, and grounded onto space-time windows covering the video. The windows provide evidence about the activity classes based on the Counting Grid (CG) model of visual words. This evidence is propagated bottom-up and top-down to parse the SPN graph for the explanation of the video. The node connectivity and model parameters of SPN and CG are jointly learned under two settings, weakly supervised, and supervised. For evaluation, we use our new Volleyball dataset, along with the benchmark datasets VIRAT, UT-Interactions, KTH, and TRECVID MED 2011. Our video classification and activity localization are superior to those of the state of the art on these datasets.

Dynamic Trees for unsupervised segmentation and matching of image regions.

We present a probabilistic framework--namely, multiscale generative models known as Dynamic Trees (DT)--for unsupervised image segmentation and subsequent matching of segmented regions in a given set of images. Beyond these novel applications of DTs, we propose important additions for this modeling paradigm. First, we introduce a novel DT architecture, where multilayered observable data are incorporated at all scales of the model. Second, we derive a novel probabilistic inference algorithm for DTs--Structured Variational Approximation (SVA)--which explicitly accounts for the statistical dependence of node positions and model structure in the approximate posterior distribution, thereby relaxing poorly justified independence assumptions in previous work. Finally, we propose a similarity measure for matching dynamic-tree models, representing segmented image regions, across images. Our results for several data sets show that DTs are capable of capturing important component-subcomponent relationships among objects and their parts, and that DTs perform well in segmenting images into plausible pixel clusters. We demonstrate the significantly improved properties of the SVA algorithm--both in terms of substantially faster convergence rates and larger approximate posteriors for the inferred models--when compared with competing inference algorithms. Furthermore, results on unsupervised object recognition demonstrate the viability of the proposed similarity measure for matching dynamic-structure statistical models.

AISO: Annotation of Image Segments with Ontologies.

BACKGROUND: Large quantities of digital images are now generated for biological collections, including those developed in projects premised on the high-throughput screening of genome-phenome experiments. These images often carry annotations on taxonomy and observable features, such as anatomical structures and phenotype variations often recorded in response to the environmental factors under which the organisms were sampled. At present, most of these annotations are described in free text, may involve limited use of non-standard vocabularies, and rarely specify precise coordinates of features on the image plane such that a computer vision algorithm could identify, extract and annotate them. Therefore, researchers and curators need a tool that can identify and demarcate features in an image plane and allow their annotation with semantically contextual ontology terms. Such a tool would generate data useful for inter and intra-specific comparison and encourage the integration of curation standards. In the future, quality annotated image segments may provide training data sets for developing machine learning applications for automated image annotation. RESULTS: We developed a novel image segmentation and annotation software application, "Annotation of Image Segments with Ontologies" (AISO). The tool enables researchers and curators to delineate portions of an image into multiple highlighted segments and annotate them with an ontology-based controlled vocabulary. AISO is a freely available Java-based desktop application and runs on multiple platforms. It can be downloaded at http://www.plantontology.org/software/AISO. CONCLUSIONS: AISO enables curators and researchers to annotate digital images with ontology terms in a manner which ensures the future computational value of the annotated images. We foresee uses for such data-encoded image annotations in biological data mining, machine learning, predictive annotation, semantic inference, and comparative analyses.

Hough forest random field for object recognition and segmentation.

This paper presents a new computational framework for detecting and segmenting object occurrences in images. We combine Hough forest (HF) and conditional random field (CRF) into HFRF to assign labels of object classes to image regions. HF captures intrinsic and contextual properties of objects. CRF then fuses the labeling hypotheses generated by HF for identifying every object occurrence. Interaction between HF and CRF happens in HFRF inference, which uses the Metropolis-Hastings algorithm. The Metropolis-Hastings reversible jumps depend on two ratios of proposal and posterior distributions. Instead of estimating four distributions, we directly compute the two ratios using HF. In leaf nodes, HF records class histograms of training examples and information about their configurations. This evidence is used in inference for nonparametric estimation of the two distribution ratios. Our empirical evaluation on benchmark datasets demonstrates higher average precision rates of object detection, smaller object segmentation error, and faster convergence rates of our inference, relative to the state of the art. The paper also presents theoretical error bounds of HF and HFRF applied to a two-class object detection and segmentation.

Next-generation phenomics for the Tree of Life.

The phenotype represents a critical interface between the genome and the environment in which organisms live and evolve. Phenotypic characters also are a rich source of biodiversity data for tree building, and they enable scientists to reconstruct the evolutionary history of organisms, including most fossil taxa, for which genetic data are unavailable. Therefore, phenotypic data are necessary for building a comprehensive Tree of Life. In contrast to recent advances in molecular sequencing, which has become faster and cheaper through recent technological advances, phenotypic data collection remains often prohibitively slow and expensive. The next-generation phenomics project is a collaborative, multidisciplinary effort to leverage advances in image analysis, crowdsourcing, and natural language processing to develop and implement novel approaches for discovering and scoring the phenome, the collection of phentotypic characters for a species. This research represents a new approach to data collection that has the potential to transform phylogenetics research and to enable rapid advances in constructing the Tree of Life. Our goal is to assemble large phenomic datasets built using new methods and to provide the public and scientific community with tools for phenomic data assembly that will enable rapid and automated study of phenotypes across the Tree of Life.

Video painting with space-time-varying style parameters.

Artists use different means of stylization to control the focus on different objects in the scene. This allows them to portray complex meaning and achieve certain artistic effects. Most prior work on painterly rendering of videos, however, uses only a single painting style, with fixed global parameters, irrespective of objects and their layout in the images. This often leads to inadequate artistic control. Moreover, brush stroke orientation is typically assumed to follow an everywhere continuous directional field. In this paper, we propose a video painting system that accounts for the spatial support of objects in the images or videos, and uses this information to specify style parameters and stroke orientation for painterly rendering. Since objects occupy distinct image locations and move relatively smoothly from one video frame to another, our object-based painterly rendering approach is characterized by style parameters that coherently vary in space and time. Space-time-varying style parameters enable more artistic freedom, such as emphasis/de-emphasis, increase or decrease of contrast, exaggeration or abstraction of different objects in the scene in a temporally coherent fashion.

Local-learning-based feature selection for high-dimensional data analysis.

This paper considers feature selection for data classification in the presence of a huge number of irrelevant features. We propose a new feature-selection algorithm that addresses several major issues with prior work, including problems with algorithm implementation, computational complexity, and solution accuracy. The key idea is to decompose an arbitrarily complex nonlinear problem into a set of locally linear ones through local learning, and then learn feature relevance globally within the large margin framework. The proposed algorithm is based on well-established machine learning and numerical analysis techniques, without making any assumptions about the underlying data distribution. It is capable of processing many thousands of features within minutes on a personal computer while maintaining a very high accuracy that is nearly insensitive to a growing number of irrelevant features. Theoretical analyses of the algorithm's sample complexity suggest that the algorithm has a logarithmical sample complexity with respect to the number of features. Experiments on 11 synthetic and real-world data sets demonstrate the viability of our formulation of the feature-selection problem for supervised learning and the effectiveness of our algorithm.