ABSTRACT
When animating and giving life to a virtual character, it is important to consider the idling behaviours of the character as well. Like any other animations, these could be recorded and handcrafted, or, they could be generated by a motion model. Such models are theoretically capable of producing and simulating variable motions in an automatic fashion, alleviating the work of animators who can then focus on more expressive behaviours. While there is a growing interest in motion models built on data, recording enough spontaneous human motions and behaviours for the learning of the models is challenging. The setting in which the recording of the data happens is usually unnatural for the participants. In this paper, we present a data collection which protocol was designed for eliciting and capturing natural and spontaneous human idle motions. This protocol works by hiding from the participant the true intent of the data collection in order to genuinely make them wait. The dataset we collected using this protocol is also presented and is made available to the community of researchers.
- Marcella H Boynton, David B Portnoy, and Blair T Johnson. 2013. Exploring the ethics and psychological impact of deception in psychological research. IRB 35, 2 (2013), 7.Google Scholar
- Angelo Cafaro, Hannes Högni Vilhjálmsson, Timothy Bickmore, Dirk Heylen, Kamilla Rún Jóhannsdóttir, and Gunnar Steinn Valgarsson. 2012. First impressions: Users’ judgments of virtual agents’ personality and interpersonal attitude in first encounters. In International conference on intelligent virtual agents(Lecture Notes in Computer Science, Vol. 7502), Yukiko Nakano, Michael Neff, Ana Paiva, and Marilyn Walker (Eds.). Springer Berlin Heidelberg, 67–80. https://doi.org/10.1007/978-3-642-33197-8_7Google ScholarDigital Library
- Zhe Cao, Tomas Simon, Shih-En Wei, and Yaser Sheikh. 2017. Realtime multi-person 2d pose estimation using part affinity fields. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7291–7299.Google ScholarCross Ref
- Kyunghyun Cho, Bart Van Merriënboer, Dzmitry Bahdanau, and Yoshua Bengio. 2014. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259(2014).Google Scholar
- Arjan Egges, Tom Molet, and Nadia Magnenat-Thalmann. 2004. Personalised real-time idle motion synthesis. 121–130. https://doi.org/10.1109/PCCGA.2004.1348342Google Scholar
- Ylva Ferstl, Michael Neff, and Rachel McDonnell. 2020. Adversarial gesture generation with realistic gesture phasing. Computers & Graphics(2020).Google Scholar
- Michael Gleicher. 1999. Animation from observation: Motion capture and motion editing. COMPUTER GRAPHICS-NEW YORK-ASSOCIATION FOR COMPUTING MACHINERY- 33, 4(1999), 51–54.Google ScholarDigital Library
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672–2680.Google Scholar
- Maja Kocoń. 2013. Idle motion synthesis of human head and face in virtual reality environment. In International Conference on Serious Games Development and Applications. Springer, 299–306.Google ScholarCross Ref
- Taras Kucherenko, Dai Hasegawa, Gustav Eje Henter, Naoshi Kaneko, and Hedvig Kjellström. 2019. Analyzing input and output representations for speech-driven gesture generation. In Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents. 97–104.Google ScholarDigital Library
- Stacy Marsella, Ari Shapiro, Andrew Feng, Yuyu Xu, Margaux Lhommet, and Stefan Scherer. 2013. Towards higher quality character performance in previz. In Proceedings of the Symposium on Digital Production. 31–35.Google ScholarDigital Library
- Sungphill Moon, Youngbin Park, Dong Wook Ko, and Il Hong Suh. 2016. Multiple kinect sensor fusion for human skeleton tracking using Kalman filtering. International Journal of Advanced Robotic Systems 13, 2 (2016), 65.Google ScholarCross Ref
- Malgorzata Oczak and Agnieszka Niedźwieńska. 2007. Debriefing in deceptive research: A proposed new procedure. Journal of Empirical Research on Human Research Ethics 2, 3(2007), 49–59.Google ScholarCross Ref
- Antonio Pascual-Leone, Terence Singh, and Alan Scoboria. 2010. Using deception ethically: Practical research guidelines for researchers and reviewers.Canadian Psychology/psychologie canadienne 51, 4 (2010), 241.Google Scholar
- Diana Phillips Mahoney. 1997. Procedural Animation-Prodecural animation techniques, which use algorithms or mathematical expressions to drive the movement of objects or volumes over time, already are delivering some significant. Computer Graphics World-Tulsa 20, 5 (1997), 39–48.Google Scholar
- David Sturman. 1984. Interactive key frame animation of 3-D articulated models. In Graphics Interface, Vol. 86.Google Scholar
- David J Sturman. 1994. A brief history of motion capture for computer character animation. SIGGRAPH94, Course9 (1994).Google Scholar
- Denis Tome, Chris Russell, and Lourdes Agapito. 2017. Lifting from the deep: Convolutional 3d pose estimation from a single image. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2500–2509.Google ScholarCross Ref
- Yuliang Xiu, Jiefeng Li, Haoyu Wang, Yinghong Fang, and Cewu Lu. 2018. Pose Flow: Efficient Online Pose Tracking. In BMVC.Google Scholar
Index Terms
- IdlePose : A Dataset of Spontaneous Idle Motions
Recommendations
TikTalk: A Video-Based Dialogue Dataset for Multi-Modal Chitchat in Real World
MM '23: Proceedings of the 31st ACM International Conference on MultimediaTo facilitate the research on intelligent and human-like chatbots with multi-modal context, we introduce a new video-based multi-modal dialogue dataset, called TikTalk. We collect 38K videos from a popular video-sharing platform, along with 367K ...
SwimXYZ: A large-scale dataset of synthetic swimming motions and videos
MIG '23: Proceedings of the 16th ACM SIGGRAPH Conference on Motion, Interaction and GamesTechnologies play an increasingly important role in sports and become a real competitive advantage for the athletes who benefit from it. Among them, the use of motion capture is developing in various sports to optimize sporting gestures. Unfortunately, ...
Multimodal Entity Linking: A New Dataset and A Baseline
MM '21: Proceedings of the 29th ACM International Conference on MultimediaIn this paper, we introduce a new Multimodal Entity Linking (MEL) task on the multimodal data. The MEL task discovers entities in multiple modalities and various forms within large-scale multimodal data and maps multimodal mentions in a document to ...
Comments