Videos convey rich information. Dynamic spatio-temporal relationships between people/objects, and diverse multimodal events are present in a video clip. Hence, it is important to develop automated models that can accurately extract such information from videos. Answering questions on videos is one of the tasks which can evaluate such AI abilities. In this paper, we propose a video question answering model which effectively integrates multi-modal input sources and finds the temporally relevant information to answer questions. Specifically, we first employ dense image captions to help identify objects and their detailed salient regions and actions, and hence give the model useful extra information (in explicit textual format to allow easier matching) for answering questions. Moreover, our model is also comprised of dual-level attention (word/object and frame level), multi-head self/cross-integration for different sources (video and dense captions), and gates which pass more relevant information to the classifier. Finally, we also cast the frame selection problem as a multi-label classification task and introduce two loss functions, In-andOut Frame Score Margin (IOFSM) and Balanced Binary Cross-Entropy (BBCE), to better supervise the model with human importance annotations. We evaluate our model on the challenging TVQA dataset, where each of our model components provides significant gains, and our overall model outperforms the state-of-the-art by a large margin (74.09% versus 70.52%). We also present several word, object, and frame level visualization studies.
more »
« less
Model Transfer for Event Tracking as Transcript Understanding for Videos of Small Group Interaction
Videos of group interactions contain a wealth
of information beyond the information directly
communicated in a transcript of the discussion.
Tracking who has participated throughout an
extended interaction and what each of their trajectories has been in relation to one another is the foundation for joint activity understanding,
though it comes with some unique challenges
in videos of tightly coupled group work. Motivated by insights into the properties of such
scenarios, including group composition and the
properties of task-oriented, goal-directed tasks,
we present a successful proof-of-concept. In
particular, we present a transfer experiment to
a dyadic robot construction task, an ablation
study, and a qualitative analysis.
more »
« less
- NSF-PAR ID:
- 10356813
- Date Published:
- Journal Name:
- International Conference on Computational Linguistics
- Volume:
- 29
- Issue:
- 12
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Introduction Social media has created opportunities for children to gather social support online (Blackwell et al., 2016; Gonzales, 2017; Jackson, Bailey, & Foucault Welles, 2018; Khasawneh, Rogers, Bertrand, Madathil, & Gramopadhye, 2019; Ponathil, Agnisarman, Khasawneh, Narasimha, & Madathil, 2017). However, social media also has the potential to expose children and adolescents to undesirable behaviors. Research showed that social media can be used to harass, discriminate (Fritz & Gonzales, 2018), dox (Wood, Rose, & Thompson, 2018), and socially disenfranchise children (Page, Wisniewski, Knijnenburg, & Namara, 2018). Other research proposes that social media use might be correlated to the significant increase in suicide rates and depressive symptoms among children and adolescents in the past ten years (Mitchell, Wells, Priebe, & Ybarra, 2014). Evidence based research suggests that suicidal and unwanted behaviors can be promulgated through social contagion effects, which model, normalize, and reinforce self-harming behavior (Hilton, 2017). These harmful behaviors and social contagion effects may occur more frequently through repetitive exposure and modelling via social media, especially when such content goes “viral” (Hilton, 2017). One example of viral self-harming behavior that has generated significant media attention is the Blue Whale Challenge (BWC). The hearsay about this challenge is that individuals at all ages are persuaded to participate in self-harm and eventually kill themselves (Mukhra, Baryah, Krishan, & Kanchan, 2017). Research is needed specifically concerning BWC ethical concerns, the effects the game may have on teenagers, and potential governmental interventions. To address this gap in the literature, the current study uses qualitative and content analysis research techniques to illustrate the risk of self-harm and suicide contagion through the portrayal of BWC on YouTube and Twitter Posts. The purpose of this study is to analyze the portrayal of BWC on YouTube and Twitter in order to identify the themes that are presented on YouTube and Twitter posts that share and discuss BWC. In addition, we want to explore to what extent are YouTube videos compliant with safe and effective suicide messaging guidelines proposed by the Suicide Prevention Resource Center (SPRC). Method Two social media websites were used to gather the data: 60 videos and 1,112 comments from YouTube and 150 posts from Twitter. The common themes of the YouTube videos, comments on those videos, and the Twitter posts were identified using grounded, thematic content analysis on the collected data (Padgett, 2001). Three codebooks were built, one for each type of data. The data for each site were analyzed, and the common themes were identified. A deductive coding analysis was conducted on the YouTube videos based on the nine SPRC safe and effective messaging guidelines (Suicide Prevention Resource Center, 2006). The analysis explored the number of videos that violated these guidelines and which guidelines were violated the most. The inter-rater reliabilities between the coders ranged from 0.61 – 0.81 based on Cohen’s kappa. Then the coders conducted consensus coding. Results & Findings Three common themes were identified among all the posts in the three social media platforms included in this study. The first theme included posts where social media users were trying to raise awareness and warning parents about this dangerous phenomenon in order to reduce the risk of any potential participation in BWC. This was the most common theme in the videos and posts. Additionally, the posts claimed that there are more than 100 people who have played BWC worldwide and provided detailed description of what each individual did while playing the game. These videos also described the tasks and different names of the game. Only few videos provided recommendations to teenagers who might be playing or thinking of playing the game and fewer videos mentioned that the provided statistics were not confirmed by reliable sources. The second theme included posts of people that either criticized the teenagers who participated in BWC or made fun of them for a couple of reasons: they agreed with the purpose of BWC of “cleaning the society of people with mental issues,” or they misunderstood why teenagers participate in these kind of challenges, such as thinking they mainly participate due to peer pressure or to “show off”. The last theme we identified was that most of these users tend to speak in detail about someone who already participated in BWC. These videos and posts provided information about their demographics and interviews with their parents or acquaintances, who also provide more details about the participant’s personal life. The evaluation of the videos based on the SPRC safe messaging guidelines showed that 37% of the YouTube videos met fewer than 3 of the 9 safe messaging guidelines. Around 50% of them met only 4 to 6 of the guidelines, while the remaining 13% met 7 or more of the guidelines. Discussion This study is the first to systematically investigate the quality, portrayal, and reach of BWC on social media. Based on our findings from the emerging themes and the evaluation of the SPRC safe messaging guidelines we suggest that these videos could contribute to the spread of these deadly challenges (or suicide in general since the game might be a hoax) instead of raising awareness. Our suggestion is parallel with similar studies conducted on the portrait of suicide in traditional media (Fekete & Macsai, 1990; Fekete & Schmidtke, 1995). Most posts on social media romanticized people who have died by following this challenge, and younger vulnerable teens may see the victims as role models, leading them to end their lives in the same way (Fekete & Schmidtke, 1995). The videos presented statistics about the number of suicides believed to be related to this challenge in a way that made suicide seem common (Cialdini, 2003). In addition, the videos presented extensive personal information about the people who have died by suicide while playing the BWC. These videos also provided detailed descriptions of the final task, including pictures of self-harm, material that may encourage vulnerable teens to consider ending their lives and provide them with methods on how to do so (Fekete & Macsai, 1990). On the other hand, these videos both failed to emphasize prevention by highlighting effective treatments for mental health problems and failed to encourage teenagers with mental health problems to seek help and providing information on where to find it. YouTube and Twitter are capable of influencing a large number of teenagers (Khasawneh, Ponathil, Firat Ozkan, & Chalil Madathil, 2018; Pater & Mynatt, 2017). We suggest that it is urgent to monitor social media posts related to BWC and similar self-harm challenges (e.g., the Momo Challenge). Additionally, the SPRC should properly educate social media users, particularly those with more influence (e.g., celebrities) on elements that boost negative contagion effects. While the veracity of these challenges is doubted by some, posting about the challenges in unsafe manners can contribute to contagion regardless of the challlenges’ true nature.more » « less
-
more » « less
Abstract The dynamics of selective attention necessarily influences the course of early perceptual development. The intersensory redundancy hypothesis proposes that in early development information presented redundantly across two or more senses selectively recruits attention to the amodal properties of an object or event. In contrast, information presented to a single sense enhances attention to modality‐specific properties. The present study assessed the second of these predictions in neonatal bobwhite quail (
Colinus virginianus ), with a focus on the role of task difficulty in directing selective attention. In Experiment 1, we exposed quail chicks to unimodal auditory, nonredundant audiovisual, or redundant audiovisual presentations of a bobwhite maternal call paired with a pulsing light for 10 min/h on the day following hatching. Chicks were subsequently individually tested 24 h later for their unimodal auditory preference between the familiarized maternal call and the same call with pitch altered by two steps. Chicks from all experimental groups preferred the familiarized maternal call over the altered maternal call. In Experiment 2, we repeated the exposure conditions of Experiment 1, but presented a more difficult task by narrowing the pitch range between the two maternal calls during testing. Chicks in the unimodal auditory and nonredundant audiovisual conditions preferred the familiarized call, whereas chicks in the redundant audiovisual exposure group showed no detection of the pitch change. Our results indicate that early discrimination of pitch change is disrupted by intersensory redundancy under difficult but not easy task conditions. These findings, along with findings from human infants, highlight the role of task difficulty in shifting attentional selectivity and underscore the dynamic nature of neonatal attentional salience hierarchies. -
ABSTRACT Physics forms the core of any Materials Science Programme at undergraduate level. Knowing the properties of materials is fundamental to developing and designing new materials and new applications for known materials. “Physical Physics” is a physics education approach which is an innovative and promising instruction model that integrates physical activity with mechanics and material properties. It aims to significantly enhance the learning experience and to illustrate how physics works, while allowing students to be active participants and take ownership of the learning process. It has been successfully piloted with undergraduate students studying mechanics on a Games Development Programme. It is a structured guided learning approach which provides a scaffold for learners to develop their problem solving skills. The objective of having applied physics on a programme is to introduce students to the mathematical world. Today students view the world through smart devices. By incorporating student recorded videos into the laboratory experience the student can visualise the mathematical world. Sitting in a classroom learning about material properties does not easily facilitate an understanding of mathematical equations as mapping to a physical reality. In order to get the students motivated and immersed in the real mathematical and physical world, an approach which makes them think about the cause and effect of actions is used. Incorporating physical action with physics enables students to assimilate knowledge and adopt an action problem solving approach to the physics concept. This is an integrated approach that requires synthesis of information from various sources in order to accomplish the task. As a transferable skill, this will ensure that the material scientists will be visionary in their approach to real life problems.more » « less
-
Problem solving is a signature skill of engineers. Incorporating videos in engineering education has potential to stimulate multi-senses and further open new ways of learning and thinking. Here, problem solving was examined on problems written by previous students that applied course concepts by reverse engineering the actions in videos. Since the videos usually come from YouTube, the student-written problems are designated YouTube problems. This research focused on examining the rigor of YouTube problems as well as students’ problem-solving skills when solving YouTube problems compared to Textbook problems. A quasi-experimental, treatment/control group design was employed, and data collected was evaluated using multiple instruments. NASA Task Load Index survey was used to collect 1200 ratings that assessed rigor of homework problems. Problem-solving ability was assessed using a previously-developed rubric with over 2600 student solutions scored. In the treatment group where students were assigned ten Textbook and nine YouTube problems, students reported an overall similarity in rigor for both YouTube and Textbook problems. Students in the treatment group displayed 6% better problem solving when completing YouTube problems compared to Textbook problems. Although higher perceptions of problem difficulty correlated with lower problem-solving ability across both groups and problem types, students in the treatment group exhibited smaller decreases in problem-solving ability as a result of increasing difficulty in the Textbook problems. Overall, student-written problems inspired by YouTube videos can easily be adapted as homework practice and possess potential benefits in enhancing students’ learning experience. Link: https://www.ijee.ie/contents/c370521.htmlmore » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
