Favorite Posted by Dan Kondratyuk and David Ross, Software Engineers, Google Research A recent wave of video generation models has burst onto the scene, in many cases showcasing stunning picturesque quality. One of the current bottlenecks in video generation is in the ability to produce coherent large motions. In many
Favorite Linked below is an excellent video on the 2022 KM strategy from the UN Development program. Good to see the focus on culture and networks. View Original Source (nickmilton.com) Here.
Favorite Posted by Sanjay Subramanian, PhD student, UC Berkeley, and Arsha Nagrani, Research Scientist, Google Research, Perception Team Visual question answering (VQA) is a machine learning task that requires a model to answer a question about an image or a set of images. Conventional VQA approaches need a large amount
Favorite Posted by Antoine Yang, Student Researcher, and Arsha Nagrani, Research Scientist, Google Research, Perception team Videos have become an increasingly important part of our daily lives, spanning fields such as entertainment, education, and communication. Understanding the content of videos, however, is a challenging task as videos often contain multiple
Favorite Posted by Fitsum Reda and Janne Kontkanen, Google Research Frame interpolation is the process of synthesizing in-between images from a given set of images. The technique is often used for temporal up-sampling to increase the refresh rate of videos or to create slow motion effects. Nowadays, with digital cameras
Favorite Described in a Harvard Business School article from 2016, here is the pledge that WD40 staff take to commit to organisational-wide sharing and learning. This is the Learning Manic Pledge; part of WD40’s “tribal culture“. The pledge is as follows: I am responsible for taking action, asking questions, getting
Favorite Posted by Paul Hongsuck Seo and Arsha Nagrani, Research Scientists, Google Research, Perception Team Multimodal video captioning systems utilize both the video frames and speech to generate natural language descriptions (captions) of videos. Such systems are stepping stones towards the longstanding goal of building multimodal conversational systems that effortlessly
Favorite The video below is from a talk I gave to the Gesellschaft für Wissensmanagement (GfWM) knowledge camp last week, on the topic of “value focused KM”. You can find more videos from the same event here. The video lasts about 30 minutes, and covers the source of value that KM
Favorite The video below is a conversation between Nancy Dixon and Tom Stewart, two of the early pioneers of the KM discipline. This is great stuff with important insights – please set aside 30 minutes to listen to it! The conversation is part of Columbia University’s “IKNS Conversations That Matter” series