Neural OmniVideo: Fusing World Knowledge into Smart Video-Specific Models
The field of computer vision has made unprecedented progress in applying Deep Learning (DL) to images. Nevertheless, expanding this progress to videos is dramatically lagging behind, due to two key challenges: (i) video data is hi...
ver más
¿Tienes un proyecto y buscas un partner? Gracias a nuestro motor inteligente podemos recomendarte los mejores socios y ponerte en contacto con ellos. Te lo explicamos en este video
Proyectos interesantes
PID2021-125711OB-I00
COMBINANDO TECNICAS DE MODELIZACION Y APRENDIZAJE AUTOMATICO...
145K€
Cerrado
TIN2016-79717-R
APRENDIZAJE PROFUNDO MULTI-TAREA PARA RECONOCIMIENTO DE OBJE...
39K€
Cerrado
TheoryDL
Practically Relevant Theory of Deep Learning
1M€
Cerrado
PID2020-120611RB-I00
CONTROLANDO EL OLVIDO EN REDES NEURONALES: APRENDIZAJE CONTI...
122K€
Cerrado
PID2019-104174GB-I00
TRANSFERENCIA DE CONOCIEMIENTO PARA REPRESENTACIONES EN REDE...
78K€
Cerrado
QQML
Trading Quantity for Quality in Machine Learning
100K€
Cerrado
Información proyecto OmniVideo
Duración del proyecto: 60 meses
Fecha Inicio: 2024-01-15
Fecha Fin: 2029-01-31
Fecha límite de participación
Sin fecha límite de participación.
Descripción del proyecto
The field of computer vision has made unprecedented progress in applying Deep Learning (DL) to images. Nevertheless, expanding this progress to videos is dramatically lagging behind, due to two key challenges: (i) video data is highly complex and diverse, requiring order of magnitude more training data than images, and (ii) raw video data is extremely high dimensional. These challenges make the processing of entire video pixel-volumes at scale prohibitively expensive and ineffective. Thus, applying DL at scale to video is restricted to short clips or aggressively sub-sampled videos.
On the other side of the spectrum, video-specific models—a single or a few neural networks trained on a single video—exhibit several key properties: (i) facilitate effective video representations (e.g., layers) that make video analysis and editing significantly more tractable, (ii) enable long-range temporal analysis by encoding the video through the network, and (iii) are not restricted to the distribution of training data. Nevertheless, the capabilities, applicability and robustness of such models are hampered by having access to only low-level information in the video
We propose to combine the power of these two approaches by the new concept of Neural OmniVideo Models: DL-based frameworks that effectively represent the dynamics of a given video, coupled with the vast knowledge learned by an ensemble of external models. We are aimed at pioneering novel methodologies for developing such models for video analysis and synthesis tasks. Our approach will have several important outcomes:
• Give rise to fundamentally novel effective video representations.
• Go beyond state-of-the-art in classical video analysis tasks that involve long-range temporal analysis.
• Enhance the perception of our dynamic world through new synthesis capabilities.
• Gain profound understanding of the internal representation learned by state-of-the-art large-scale models, and unveil new priors about our dynamic.