Results 1 to 10 of about 89,511 (182)
Contrastive Predictive Coding for Human Activity Recognition [PDF]
Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies, 2020 Feature extraction is crucial for human activity recognition (HAR) using body-worn movement sensors. Recently, learned representations have been used successfully, offering promising alternatives to manually engineered features.
H. Haresamudram, Irfan Essa, T. Ploetz
semanticscholar +1 more source
Learning Discriminative Representations for Skeleton Based Action Recognition [PDF]
Computer Vision and Pattern Recognition, 2023 Human action recognition aims at classifying the category of human action from a segment of a video. Recently, people have dived into designing GCN-based models to extract features from skeletons for performing this task, because skeleton representations
Huanyu Zhou, Qingjie Liu, Yunhong Wang
semanticscholar +1 more source
Mnemicity versus temporality: Distinguishing between components of episodic representations.
Journal of experimental psychology. General, 2022 Human beings regularly "mentally travel" to past and future times in memory and imagination. In theory, whether an event is remembered or imagined (its "mnemicity") underspecifies whether it is oriented toward the past or the future (its "temporality ...
Johannes B. Mahr, D. Schacter
semanticscholar +1 more source
Learning Video Representations from Large Language Models [PDF]
Computer Vision and Pattern Recognition, 2022 We introduce LAVILA, a new approach to learning video-language representations by leveraging Large Language Models (LLMs). We repurpose pre-trained LLMs to be conditioned on visual input, and finetune them to create automatic video narrators.
Yue Zhao +3 more
semanticscholar +1 more source
More Than the Face: Representations of Bodies in the Inferior Temporal Cortex.
Annual Review of Vision Science, 2022 Visual representations of bodies, in addition to those of faces, contribute to the recognition of con- and heterospecifics, to action recognition, and to nonverbal communication.
R. Vogels
semanticscholar +1 more source
FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videos [PDF]
ACM Multimedia, 2022 Neural fields, also known as coordinate-based or implicit neural representations, have shown a remarkable capability of representing, generating, and manipulating various forms of signals.
J. Lee, Daniel Rho, J. Ko, Eunbyung Park
semanticscholar +1 more source
Dal Laocoonte a Watchmen. La poesia sta alla pittura come il cinema al fumetto
Aisthesis, 2012 Moving from the famous essay by G.E. Lessing (Laokoon, 1766), my paper aims at applying Lessing’s distinction between poetry and painting (conceived as the art of temporality – painting – and the art of spatiality – poetry) to the couple cinema/comics ...
Mariagrazia Portera
doaj +5 more sources
Documenta Praehistorica, 2023 This paper aims to make a comparison of the figurative representations of the Pali Aike volcanic field (province of Santa Cruz, Argentina – province of Magallanes, Chile) with those registered in other sectors of southern Patagonia, such as the southern
Paula Daniela Funes
doaj +1 more source
bioRxiv, 2021 Our understanding of the world is shaped by inferences about underlying structure. For example, at the gym, you might notice that the same people tend to arrive around the same time and infer that they are friends that work out together.
Athula Pudhiyidath +7 more
semanticscholar +1 more source
Regimes of Temporality: China, Tibet and the Politics of Time in the Post-2008 Era [PDF]
, 2020 While the politics of time are an important dimension of Chinese state discourse about Tibet, it remains insufficiently explored in theoretical and practical terms.
Kehoe, S., Kehoe, S.
core +1 more source