Asking and answering questions are inseparable parts of human social life.The primary purposes of asking questions are to gain knowledge or request help which has been the subject of question-answering studies.However, questions can also reflect negative intentions and include implicit offenses, such as highlighting one's lack of knowledge or bolstering an alleged superior knowledge, which can lead to conflict in conversations; yet has been scarcely researched.This paper is the first study to introduce a dataset (Question Intention Dataset) that includes questions with positive/neutral and negative intentions and the underlying intention categories within each group.We further conduct a meta-analysis to highlight tacit and apparent intents.We also propose a classification method using Transformers augmented by TF-IDF-based features and report the results of several models for classifying the main intention categories.We aim to highlight the importance of taking intentions into account, especially implicit and negative ones, to gain insight into conflict-evoking questions and better understand human-human communication on the web for NLP applications.

The proliferation of social media and online communication platforms has made social interactions more accessible, leading to a significant expansion of research into language use with a particular focus on toxic behavior and hate speech. Few studies, however, have focused on the tacit information that may imply a negative intention and the perspective that impacts the interpretation of such intention. Conversation is a joint activity that relies on coordination between what one party expresses and how the other party construes what has been expressed. Thus, how a message is perceived becomes equally important regardless of whether the sent message includes any form of explicit attack or offense. This study focuses on identifying the implicit attacks and negative intentions in text-based conversation from the reader’s point of view. We focus on questions in conversations and investigate the underlying perceived intention. We introduce our dataset that includes questions, intention polarity, and type of attacks. We conduct a meta-analysis on the data to demonstrate how a question may be used as a means of attack and how different perspectives can lead to multiple interpretations. We also report benchmark results of several models for detecting instances of tacit attacks in questions with the aim of avoiding latent or manifest conflict in conversations.

Producing realistic character animations is one of the essential tasks in human-AI interactions. Considered as a sequence of poses of a humanoid, the task can be considered as a sequence generation problem with spatiotemporal smoothness and realism constraints. Additionally, we wish to control the behavior of AI agents by giving them what to do and, more specifically, how to do it. We proposed a spatiotemporally-conditioned GAN that generates a sequence that is similar to a given sequence in terms of semantics and spatiotemporal dynamics. Using LSTM-based generator and graph ConvNet discriminator, this system is trained end-to-end on a large gathered dataset of gestures, expressions, and actions. Experiments showed that compared to traditional conditional GAN, our method creates plausible, realistic, and semantically relevant humanoid animation sequences that match user expectations.

Employing one or more additional classifiers to break the self-learning loop in tracing-by-detection has gained considerable attention. Most of such trackers merely utilize the redundancy to address the accumulating label error in the tracking loop, and suffer from high computational complexity as well as tracking challenges that may interrupt all classifiers (e.g. temporal occlusions). We propose the active co-tracking framework, in which the main classifier of the tracker labels samples of the video sequence, and only consults auxiliary classifier when it is uncertain. Based on the source of the uncertainty and the differences of two classifiers (e.g. accuracy, speed, update frequency, etc.), different policies should be taken to exchange information between two classifiers. Here, we introduce a reinforcement learning approach to find the appropriate policy by considering the state of tracker in a specific sequence. The proposed method yields promising results in comparison to the best tracking-by-detection approaches.

The performance of an adaptive tracking-by-detection algorithm not only depends on the classification and updating processes but also on the sampling. Typically, such trackers select their samples from the vicinity of the last predicted object location, or from its expected location using a predefined motion model, which does not exploit the contents of the samples nor the information provided by the classifier. We introduced the idea of most informative sampling, in which the sampler attempts to select samples that trouble the classifier of a discriminative tracker. We then proposed an active discriminative co-tracker that embed an adversarial sampler to increase its robustness against various tracking challenges. Experiments show that our proposed tracker outperforms state-of-the-art trackers on various benchmark videos.

Embodied Conversational Agents often employ advanced multimodal analysis of human users for affective inference, however, its facial expressions in response are often pre-made or coded animations. Generated data-driven facial animations have the advantage that they can be more natural and do not require a database at run-time. The open source modular framework FACSvatar is presented, which processes and animates FACS based data in real-time. Tools that create 3D human models are supported and facial data can be visualized in popular tools in the gaming industry. All functionality is split-up into modules set-up in a publisher-subscriber pattern to provide easy integration with other platforms. A deep learning module for real-time generation of AU data for data-driven animation is implemented. A user evaluation of their expressions being animated through our framework was done. Their ratings were slightly positive, but more improvements have to be made in terms of data quality and individual fine-tuning. Also, the modules' latency and performance have been measured. On average, FACS data is visualized in 28.55 ms.

A discriminative ensemble tracker employs multiple classifiers, each of which casts a vote on all of the obtained samples. The votes are then aggregated in an attempt to localize the target object. Such method relies on collective competence and the diversity of the ensemble to approach the target/non-target classification task from different views. However, by updating all of the ensemble using a shared set of samples and their final labels, such diversity is lost or reduced to the diversity provided by the underlying features or internal classifiers' dynamics. Additionally, the classifiers do not exchange information with each other while striving to serve the collective goal, i.e., better classification. In this study, we propose an active collaborative information exchange scheme for ensemble tracking. This, not only orchestrates different classifiers towards a common goal but also provides an intelligent update mechanism to keep the diversity of classifiers and to mitigate the shortcomings of one with the others. The data exchange is optimized with regard to an ensemble uncertainty utility function, and the ensemble is updated via co-training. The evaluations demonstrate promising results realized by the proposed algorithm for the real-world online tracking.