State-of-the-art image captioning methods mostly focus on improving visual features, less attention has been paid to utilizing the inherent properties of language to boost captioning performance. In this paper, we show that vocabulary coherence between words and syntactic paradigm of sentences are also important to generate high-quality image caption. Following the conventional encoder-decoder framework, we propose the Reflective Decoding Network (RDN) for image captioning, which enhances both the long-sequence dependency and position perception of words in a caption decoder. Our model learns to collaboratively attend on both visual and textual features and meanwhile perceive each word's relative position in the sentence to maximize the information delivered in the generated caption. We evaluate the effectiveness of our RDN on the COCO image captioning datasets and achieve superior performance over the previous methods. Further experiments reveal that our approach is particularly advantageous for hard cases with complex scenes to describe by captions.
Despite the recent developments on neural summarization systems, the underlying logic behind the improvements from the systems and its corpus-dependency remains largely unexplored. Position of sentences in the original text, for example, is a well known bias for news summarization. Following in the spirit of the claim that summarization is a combination of sub-functions, we define three sub-aspects of summarization: position, importance, and diversity and conduct an extensive analysis of the biases of each sub-aspect with respect to the domain of nine different summarization corpora (e.g., news, academic papers, meeting minutes, movie script, books, posts). We find that while position exhibits substantial bias in news articles, this is not the case, for example, with academic papers and meeting minutes. Furthermore, our empirical study shows that different types of summarization systems (e.g., neural-based) are composed of different degrees of the sub-aspects. Our study provides useful lessons regarding consideration of underlying sub-aspects when collecting a new summarization dataset or developing a new system.
In this article, we study laughter found in child-robot interaction where it had not been prompted intentionally. Different types of laughter and speech-laugh are annotated and processed. In a descriptive part, we report on the position of laughter and speech-laugh in syntax and dialogue structure, and on communicative functions. In a second part, we report on automatic classification performance and on acoustic characteristics, based on extensive feature selection procedures.
Sequence labeling is a fundamental task in natural language processing and has been widely studied. Recently, RNN-based sequence labeling models have increasingly gained attentions. Despite superior performance achieved by learning the long short-term (i.e., successive) dependencies, the way of sequentially processing inputs might limit the ability to capture the non-continuous relations over tokens within a sentence. To tackle the problem, we focus on how to effectively model successive and discrete dependencies of each token for enhancing the sequence labeling performance. Specifically, we propose an innovative attention-based model (called position-aware selfattention, i.e., PSA) as well as a well-designed self-attentional context fusion layer within a neural network architecture, to explore the positional information of an input sequence for capturing the latent relations among tokens. Extensive experiments on three classical tasks in sequence labeling domain, i.e., partof-speech (POS) tagging, named entity recognition (NER) and phrase chunking, demonstrate our proposed model outperforms the state-of-the-arts without any external knowledge, in terms of various metrics.
Conversational question answering (ConvQA) is a simplified but concrete setting of conversational search. One of its major challenges is to leverage the conversation history to understand and answer the current question. In this work, we propose a novel solution for ConvQA that involves three aspects. First, we propose a positional history answer embedding method to encode conversation history with position information using BERT in a natural way. BERT is a powerful technique for text representation. Second, we design a history attention mechanism (HAM) to conduct a "soft selection" for conversation histories. This method attends to history turns with different weights based on how helpful they are on answering the current question. Third, in addition to handling conversation history, we take advantage of multi-task learning (MTL) to do answer prediction along with another essential conversation task (dialog act prediction) using a uniform model architecture. MTL is able to learn more expressive and generic representations to improve the performance of ConvQA. We demonstrate the effectiveness of our model with extensive experimental evaluations on QuAC, a large-scale ConvQA dataset. We show that position information plays an important role in conversation history modeling. We also visualize the history attention and provide new insights into conversation history understanding.
Proactively perceiving others' intentions is a crucial skill to effectively interact in unstructured, dynamic and novel environments. This work proposes a first step towards embedding this skill in support robots for search and rescue missions. Predicting the responders' intentions, indeed, will enable exploration approaches which will identify and prioritise areas that are more relevant for the responder and, thus, for the task, leading to the development of safer, more robust and efficient joint exploration strategies. More specifically, this paper presents an active intention recognition paradigm to perceive, even under sensory constraints, not only the target's position but also the first responder's movements, which can provide information on his/her intentions (e.g. reaching the position where he/she expects the target to be). This mechanism is implemented by employing an extension of Monte-Carlo-based planning techniques for partially observable environments, where the reward function is augmented with an entropy reduction bonus. We test in simulation several configurations of reward augmentation, both information theoretic and not, as well as belief state approximations and obtain substantial improvements over the basic approach.
According to screenwriting theory, turning points (e.g., change of plans, major setback, climax) are crucial narrative moments within a screenplay: they define the plot structure, determine its progression and segment the screenplay into thematic units (e.g., setup, complications, aftermath). We propose the task of turning point identification in movies as a means of analyzing their narrative structure. We argue that turning points and the segmentation they provide can facilitate processing long, complex narratives, such as screenplays, for summarization and question answering. We introduce a dataset consisting of screenplays and plot synopses annotated with turning points and present an end-to-end neural network model that identifies turning points in plot synopses and projects them onto scenes in screenplays. Our model outperforms strong baselines based on state-of-the-art sentence representations and the expected position of turning points.
Recently proposed quantum-chaotic sensors achieve quantum enhancements in measurement precision by applying nonlinear control pulses to the dynamics of the quantum sensor while using classical initial states that are easy to prepare. Here, we use the cross-entropy method of reinforcement learning to optimize the strength and position of control pulses. Compared to the quantum-chaotic sensors with periodic control pulses in the presence of superradiant damping, we find that decoherence can be fought even better and measurement precision can be enhanced further by optimizing the control. In some examples, we find enhancements in sensitivity by more than an order of magnitude. By visualizing the evolution of the quantum state, the mechanism exploited by the reinforcement learning method is identified as a kind of spin-squeezing strategy that is adapted to the superradiant damping.
Nowadays online social networks are used extensively for personal and commercial purposes. This widespread popularity makes them an ideal platform for advertisements. Social media can be used for both direct and word-of-mouth (WoM) marketing. Although WoM marketing is considered more effective and it requires less advertisement cost, it is currently being under-utilized. To do WoM marketing, we need to identify a set of people who can use their authoritative position in social network to promote a given product. In this paper, we show how to do WoM marketing in Facebook group, which is a question answer type of social network. We also present concept of reinforced WoM marketing, where multiple authorities can together promote a product to increase the effectiveness of marketing. We perform our experiments on Facebook group dataset consisting of 0.3 million messages and 10 million user reactions.
In this paper, we propose a deep convolutional neural network (CNN) for anomaly detection in surveillance videos. The model is adapted from a typical auto-encoder working on video patches under the perspective of sparse combination learning. Our CNN focuses on (unsupervisedly) learning common characteristics of normal events with the emphasis of their spatial locations (by supervised losses). To our knowledge, this is the first work that directly adapts the patch position as the target of a classification sub-network. The model is capable to provide a score of anomaly assessment for each video frame. Our experiments were performed on 4 benchmark datasets with various anomalous events and the obtained results were competitive with state-of-the-art studies.
In this paper, we propose a deep reinforcement learning (DRL) solution to the grasping problem using 2.5D images as the only source of information. In particular, we developed a simulated environment where a robot equipped with a vacuum gripper has the aim of reaching blocks with planar surfaces. These blocks can have different dimensions, shapes, position and orientation. Unity 3D allowed us to simulate a real-world setup, where a depth camera is placed in a fixed position and the stream of images is used by our policy network to learn how to solve the task. We explored different DRL algorithms and problem configurations. The experiments demonstrated the effectiveness of the proposed DRL algorithm applied to grasp tasks guided by visual depth camera inputs. When using the proper policy, the proposed method estimates a robot tool configuration that reaches the object surface with negligible position and orientation errors. This is, to the best of our knowledge, the first successful attempt of using 2.5D images only as of the input of a DRL algorithm, to solve the grasping problem regressing 3D world coordinates.
In this paper, we investigate the integration of sentence position and semantic role of words in a PageRank system to build a key phrase ranking method. We present the evaluation results of our approach on three scientific articles. We show that semantic role information, when integrated with a PageRank system, can become a new lexical feature. Our approach had an overall improvement on all the data sets over the state-of-art baseline approaches.
Design Thinking workshops are used by companies to help generate new ideas for technologies and products by engaging subjects in exercises to understand their users' wants and become more empathetic towards their needs. The "aha moment" experienced during these thought-provoking, step outside the yourself activities occurs when a group of persons iterate over several problems and converge upon a solution that will fit seamlessly everyday life. With the increasing use and cost of Design workshops being offered, it is important that technology be developed that can help identify empathy and its onset in humans. This position paper presents an approach to modeling empathy using Gaussian mixture models and heart rate and skin conductance. This paper also presents an updated approach to Design Thinking that helps to ensure participants are thinking outside of their own race's, culture's, or other affiliations' motives.
New technologies drastically change recruitment techniques. Some research projects aim at designing interactive systems that help candidates practice job interviews. Other studies aim at the automatic detection of social signals (e.g. smile, turn of speech, etc...) in videos of job interviews. These studies are limited with respect to the number of interviews they process, but also by the fact that they only analyze simulated job interviews (e.g. students pretending to apply for a fake position). Asynchronous video interviewing tools have become mature products on the human resources market, and thus, a popular step in the recruitment process. As part of a project to help recruiters, we collected a corpus of more than 7000 candidates having asynchronous video job interviews for real positions and recording videos of themselves answering a set of questions. We propose a new hierarchical attention model called HireNet that aims at predicting the hirability of the candidates as evaluated by recruiters. In HireNet, an interview is considered as a sequence of questions and answers containing salient socials signals. Two contextual sources of information are modeled in HireNet: the words contained in the question and in the job position. Our model achieves better F1-scores than previous approaches for each modality (verbal content, audio and video). Results from early and late multimodal fusion suggest that more sophisticated fusion schemes are needed to improve on the monomodal results. Finally, some examples of moments captured by the attention mechanisms suggest our model could potentially be used to help finding key moments in an asynchronous job interview.
Over the last decade, computer science has made progress towards extracting body pose from single camera photographs or videos. This promises to enable movement science to detect disease, quantify movement performance, and take the science out of the lab into the real world. However, current pose tracking algorithms fall short of the needs of movement science; the types of movement data that matter are poorly estimated. For instance, the metrics currently used for evaluating pose tracking algorithms use noisy hand-labeled ground truth data and do not prioritize precision of relevant variables like three-dimensional position, velocity, acceleration, and forces which are crucial for movement science. Here, we introduce the scientific disciplines that use movement data, the types of data they need, and discuss the changes needed to make pose tracking truly transformative for movement science.
Image-text matching tasks have recently attracted a lot of attention in the computer vision field. The key point of this cross-domain problem is how to accurately measure the similarity between the visual and the textual contents, which demands a fine understanding of both modalities. In this paper, we propose a novel position focused attention network (PFAN) to investigate the relation between the visual and the textual views. In this work, we integrate the object position clue to enhance the visual-text joint-embedding learning. We first split the images into blocks, by which we infer the relative position of region in the image. Then, an attention mechanism is proposed to model the relations between the image region and blocks and generate the valuable position feature, which will be further utilized to enhance the region expression and model a more reliable relationship between the visual image and the textual sentence. Experiments on the popular datasets Flickr30K and MS-COCO show the effectiveness of the proposed method. Besides the public datasets, we also conduct experiments on our collected practical large-scale news dataset (Tencent-News) to validate the practical application value of proposed method. As far as we know, this is the first attempt to test the performance on the practical application. Our method achieves the state-of-art performance on all of these three datasets.
Reinforcement learning algorithms have shown great success in solving different problems ranging from playing video games to robotics. However, they struggle to solve delicate robotic problems, especially those involving contact interactions. Though in principle a policy directly outputting joint torques should be able to learn to perform these tasks, in practice we see that it has difficulty to robustly solve the problem without any given structure in the action space. In this paper, we investigate how the choice of action space can give robust performance in presence of contact uncertainties. We propose learning a policy giving as output impedance and desired position in joint space and compare the performance of that approach to torque and position control under different contact uncertainties. Furthermore, we propose an additional reward term designed to regularize these variable impedance control policies, giving them interpretability and facilitating their transfer to real systems. We present extensive experiments in simulation of both floating and fixed-base systems in tasks involving contact uncertainties, as well as results for running the learned policies on a real system.
Segmenting white matter bundles from human tractograms is a task of interest for several applications. Current methods for bundle segmentation consider either only prior knowledge about the relative anatomical position of a bundle, or only its geometrical properties. Our aim is to improve the results of segmentation by proposing a method that takes into account information about both the underlying anatomy and the geometry of bundles at the same time. To achieve this goal, we extend a state-of-the-art example-based method based on the Linear Assignment Problem (LAP) by including prior anatomical information within the optimization process. The proposed method shows a significant improvement with respect to the original method, in particular on small bundles.
Autonomous helicopter landing is a challenging task that requires precise information about the aircraft states regarding the helicopters position, attitude, as well as position of the helipad. To this end, we propose a solution that fuses data from an Inertial Measurement Unit (IMU) and a monocular camera which is capable of detecting helipads position in the image plane. The algorithm utilises manifold based nonlinear optimisation over preintegrated IMU measurements and reprojection error in temporally uniformly distributed keyframes, exhibiting good performance in terms of accuracy and being computationally feasible. Our contributions of this paper are the formal address of the landmarks Jacobian expressions and the adaptation of equality constrained Gauss-Newton method to this specific problem. Numerical simulations on MATLAB/Simulink confirm the validity of given claims.
Up to 17% of all motorcycle accidents occur when the rider is maneuvering through a curve and the main cause of curve accidents can be attributed to inappropriate speed and wrong intra-lane position of the motorcycle. Existing curve warning systems lack crucial state estimation components and do not scale well. We propose a new type of road curvature warning system for motorcycles, combining the latest advances in computer vision, optimal control and mapping technologies to alleviate these shortcomings. Our contributes are fourfold: 1) we predict the motorcycle's intra-lane position using a convolutional neural network (CNN), 2) we predict the motorcycle roll angle using a CNN, 3) we use an upgraded controller model that incorporates road incline for a more realistic model and prediction, 4) we design a scale-able system by utilizing HERE Technologies map database to obtain the accurate road geometry of the future path. In addition, we present two datasets that are used for training and evaluating of our system respectively, both datasets will be made publicly available. We test our system on a diverse set of real world scenarios and present a detailed case-study. We show that our system is able to predict more accurate and safer curve trajectories, and consequently warn and improve the safety for motorcyclists.