Канал: GluonCV

Learning the physical world from High-resolution Tactile Sensing

Learning the physical world from High-resolution Tactile Sensing

Computer Vision with Sight, Sound, and Speech

Computer Vision with Sight, Sound, and Speech

Video, Multimodality & Similarity

Video, Multimodality & Similarity

Neuro-Symbolic Dynamic Visual Reasoning

Neuro-Symbolic Dynamic Visual Reasoning

Computer Perception with Perceivers

Computer Perception with Perceivers

Leveraging Motion in Videos

Leveraging Motion in Videos

Representing Longer Videos - TokenLearner

Representing Longer Videos - TokenLearner

Video-Modelling for Fine-Grained Understanding

Video-Modelling for Fine-Grained Understanding

Multimodal Learning from Videos

Multimodal Learning from Videos

Efficient and Compositional Human Event Understanding

Efficient and Compositional Human Event Understanding

Do you see what I see? Large-scale learning from multimodal videos

Do you see what I see? Large-scale learning from multimodal videos

Introduction to Human Activity Understanding in Videos (Talk 1/6)

Introduction to Human Activity Understanding in Videos (Talk 1/6)

A Journey Through Video Research at AWS (Talk 5/6)

A Journey Through Video Research at AWS (Talk 5/6)

Structured Representations for Video Understanding (Talk 6/6)

Structured Representations for Video Understanding (Talk 6/6)

A Chronological Review of Recent SoTA and Beyond (Talk 2/6)

A Chronological Review of Recent SoTA and Beyond (Talk 2/6)

Deploy Video Models (Talk 4/6)

Deploy Video Models (Talk 4/6)

Decord: An Efficient Video Reader for Deep Learning (Talk 3/6)

Decord: An Efficient Video Reader for Deep Learning (Talk 3/6)