Bayesian Nonparametric Modeling for Predicting Dynamic Dependencies in Multiple Object Tracking

The paper considers the problem of tracking an unknown and time-varying number of unlabeled moving objects using multiple unordered measurements with unknown association to the objects. The proposed tracking approach integrates Bayesian nonparametric modeling with Markov chain Monte Carlo methods to estimate the parameters of each object when present in the tracking scene. In particular, we adopt the dependent Dirichlet process (DDP) to learn the multiple object state prior by exploiting inherent dynamic dependencies in the state transition using the dynamic clustering property of the DDP. Using the DDP to draw the mixing measures, Dirichlet process mixtures are used to learn and assign each measurement to its associated object identity. The Bayesian posterior to estimate the target trajectories is efficiently implemented using a Gibbs sampler inference scheme. A second tracking approach is proposed that replaces the DDP with the dependent Pitman–Yor process in order to allow for a higher flexibility in clustering. The improved tracking performance of the new approaches is demonstrated by comparison to the generalized labeled multi-Bernoulli filter.

Pribumi di Mata Kolonial dalam Kumpulan Cerpen Teh dan Pengkhianat Karya Iksaka Banu

This research aims to discuss social and cultural aspects that are closely related to Indonesian history regarding events of colonialism in the collection of short stories entitled Teh dan Pengkhianat by applying new historicism. This is a descriptive qualitative research. The theory used to analyze the relevance of literary works as social documents is from new historicism, Stephen Greenblatt (1980). Besides, the theory used to investigate colonialist perspectives on indigenous peoples is form orientalism, Edward Said (1935). The results of this research are as follows. First, historical representations are marked by fear, restraint, compulsion, and counterforce of indigenous people in the colonial period before and after 1945. Second, social representation is marked by humanity, preparation, and persistence in dealing with the variola virus that occurred in 1644. Third, cultural representations are marked by the hard work of indigenous people for equal rights in clothing style until transportation. Data that demonstrates hard work is the existence (space, process, and object), identity (matching), and unity/multiplicity (merging) of indigenous peoples and colonialists.

Metafora Konseptual Dalam Cerita Pendek Berbahasa Inggris Di Platform The Short Story: Kajian Semantik Kognitif

This research intends to clarify the forms of metaphors, conceptual meaning, and image scheme that appear in the five English short stories named The Short Story online platform by applying cognitive semantics. This is a descriptive qualitative research. The whole result of this research is illustrated by words. The theory used in analyzing the metaphors is from Saeed (2009). Besides, the theory for investigating the scheme is from Cruse and Croft (2004). The result of this research is 12 metaphors that have been classified based on their categories. First, five data of conventional metaphors with conceptual meaning such as life choice, darkness, noise, nervousness, and old. Second, four data of systematic metaphors with conceptual meaning such as fearness, compulsion, fire, and waving. Third, two data of asymmetric metaphors with conceptual meaning such as preparation and persistence. The last, one data of abstraction metaphor with conceptual meaning that is hard working. Those data have 4 image schemes, such as force (restraint, compulsion, and counterforce), existence (space, process, object), identity (matching), and unity/multiplicity (merging).

Facilitation of object encoding in infants by the observation of giving

We propose that humans are prepared to interpret giving as a diagnostic cue of reciprocal–exchange relations from infancy. A prediction following from this hypothesis is that infants will represent the identity of an object they see being given, because this information is critical for evaluating potential future reciprocation. Across three looking-time experiments we tested whether the observation of a transfer action induces 12-month-olds to encode the identity of a single object handled by an agent. We found that infants encoded the object identity when the agent gave the object (Experiment 1), but not when she took it (Experiment 2), despite being able to represent the goal of both actions (Experiments 1 and 3). Consistent with our hypothesis, these results suggest that the infants’ representation of giving comprises information necessary for comparing the value of transferred goods across sharing episodes.

Unsupervised changes in core object recognition behavior are predicted by neural plasticity in inferior temporal cortex

Temporal continuity of object identity is a feature of natural visual input, and is potentially exploited -- in an unsupervised manner -- by the ventral visual stream to build the neural representation in inferior temporal (IT) cortex. Here we investigated whether plasticity of individual IT neurons underlies human core-object-recognition behavioral changes induced with unsupervised visual experience. We built a single-neuron plasticity model combined with a previously established IT population-to-recognition-behavior linking model to predict human learning effects. We found that our model, after constrained by neurophysiological data, largely predicted the mean direction, magnitude and time course of human performance changes. We also found a previously unreported dependency of the observed human performance change on the initial task difficulty. This result adds support to the hypothesis that tolerant core object recognition in human and non-human primates is instructed -- at least in part -- by naturally occurring unsupervised temporal contiguity experience.

Affordance-Based Grasping Point Detection Using Graph Convolutional Networks for Industrial Bin-Picking Applications

Grasping point detection has traditionally been a core robotic and computer vision problem. In recent years, deep learning based methods have been widely used to predict grasping points, and have shown strong generalization capabilities under uncertainty. Particularly, approaches that aim at predicting object affordances without relying on the object identity, have obtained promising results in random bin-picking applications. However, most of them rely on RGB/RGB-D images, and it is not clear up to what extent 3D spatial information is used. Graph Convolutional Networks (GCNs) have been successfully used for object classification and scene segmentation in point clouds, and also to predict grasping points in simple laboratory experimentation. In the present proposal, we adapted the Deep Graph Convolutional Network model with the intuition that learning from n-dimensional point clouds would lead to a performance boost to predict object affordances. To the best of our knowledge, this is the first time that GCNs are applied to predict affordances for suction and gripper end effectors in an industrial bin-picking environment. Additionally, we designed a bin-picking oriented data preprocessing pipeline which contributes to ease the learning process and to create a flexible solution for any bin-picking application. To train our models, we created a highly accurate RGB-D/3D dataset which is openly available on demand. Finally, we benchmarked our method against a 2D Fully Convolutional Network based method, improving the top-1 precision score by 1.8% and 1.7% for suction and gripper respectively.

Working Memory in Unilateral Spatial Neglect: Evidence for Impaired Binding of Object Identity and Object Location

Working memory (WM) is known to be impaired in patients with stroke experiencing unilateral spatial neglect (USN). Here, we examined in a systematic manner three WM components: memory of object identity, memory of object location, and binding between object identity and location. Moreover, we used two different retention intervals to isolate maintenance from other mnemonic and perceptual processes. Fourteen USN first-event stroke patients with right-hemisphere damage were tested in two different WM experiments using long and short retention intervals and an analog response scale. Patients exhibited more identification errors for items displayed on the contralesional side. Localization errors were also more prominent in the contralesional side, especially after a long retention interval. These localization errors were often a result of swap errors, that is, erroneous localizations of correctly identified contralesional objects in correctly memorized locations of ipsilesional objects. We conclude that a key WM deficit in USN is a lateralized impairment in binding between the identity of an object and its spatial tag.