Digests » 180

this week's favorite

Three grand challenges in machine learning

Cognitive AI, hierarchy of knowledge, and the answer to the unsustainable growth of all-inclusive deep-learning models.

Scaling up self-supervised audio-visual learning with automatically curated internet videos

The natural association between visual observations and their corresponding sounds has exhibited powerful self-supervision signals for learning video representations, which makes the ever-growing amount of online video an attractive data source for self-supervised learning.

No one rung to rule them all: Addressing scale and expediency in knowledge-based AI

Cognitive AI, hierarchy of knowledge, and the answer to the unsustainable growth of all-inclusive deep-learning models.

How cryptography works to protect ML models

You trained fantastic ML models that add cat’s ears =^..^= (nekomimi) to all people on the video. You decided to make an app for that! Suddenly, your app became popular, and some people wanted to copy it. So, it would be best to protect your ML models from leakage and misuse.

ByteTrack: Multi-object tracking by associating every detection box

Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods obtain identities by associating detection boxes whose scores are higher than a threshold. The objects with low detection scores, e.g. occluded objects, are simply thrown away, which brings non-negligible true object missing and fragmented trajectories.