Image matting is an ill-posed problem. It requires a user input trimap or some strokes to obtain an alpha matte of the foreground object.

Ant evolution favored large colonies over individual strength. Breakthroughs, discoveries, and DIY tips sent every weekday. Here's a fun (and creepy) fact: The Earth is home to approximately 20 quadrillion ants . To put zeroes on it, that's around 20,000,000,000,000,000 of the six-legged insects living all around us. How did such diminutive creatures attain their prominent--and ecologically vital -role on the planet?

Image matting is an ill-posed problem. It requires a user input trimap or some strokes to obtain an alpha matte of the foreground object.

For years, dual roles have been played largely for laughs. Think of Adam Sandler's Razzie-sweeping twin turn in Jack and Jill, or Lisa Kudrow as both Phoebe and Ursula Buffay on Friends. Eddie Murphy was always particularly prolific, his most multiplicitous performance as a clutch of Klumps for Nutty Professor II. There are exceptions, of course. But for every Legend or The Prestige there are ten Austin Powers, Bowfingers and – shudder – Norbits.

Human instance matting aims to estimate an alpha matte for each human instance in an image, which is extremely challenging and has rarely been studied so far. Despite some efforts to use instance segmentation to generate a trimap for each instance and apply trimap-based matting methods, the resulting alpha mattes are often inaccurate due to inaccurate segmentation. In addition, this approach is computationally inefficient due to multiple executions of the matting method. To address these problems, this paper proposes a novel End-to-End Human Instance Matting (E2E-HIM) framework for simultaneous multiple instance matting in a more efficient manner. Specifically, a general perception network first extracts image features and decodes instance contexts into latent codes. Then, a united guidance network exploits spatial attention and semantics embedding to generate united semantics guidance, which encodes the locations and semantic correspondences of all instances. Finally, an instance matting network decodes the image features and united semantics guidance to predict all instance-level alpha mattes. In addition, we construct a large-scale human instance matting dataset (HIM-100K) comprising over 100,000 human images with instance alpha matte labels. Experiments on HIM-100K demonstrate the proposed E2E-HIM outperforms the existing methods on human instance matting with 50% lower errors and 5X faster speed (6 instances in a 640X640 image). Experiments on the PPM-100, RWP-636, and P3M datasets demonstrate that E2E-HIM also achieves competitive performance on traditional human matting.

Adobe takes home the award thanks to its new, exciting update to Premiere Pro: text-based editing. At NAB, Adobe showed us why Premiere Pro is the go-to editing software for so many editors. While text-based editing was the highlight for us, Adobe also unveiled an impressive range of new features across its Creative Cloud video programs. Adobe showcased new features in Premiere Pro that will be shipping in May. These included text-based editing along with an AI-based workflow powered by Adobe Sensei.

Image matting is an ill-posed problem. It requires a user input trimap or some strokes to obtain an alpha matte of the foreground object. A fine user input is essential to obtain a good result, which is either time consuming or suitable for experienced users who know where to place the strokes. In this paper, we explore the intrinsic relationship between the user input and the matting algorithm to address the problem of where and when the user should provide the input. Our aim is to discover the most informative sequence of regions for user input in order to produce a good alpha matte with minimum labeling efforts. To this end, we propose an active matting method with recurrent reinforcement learning. The proposed framework involves human in the loop by sequentially detecting informative regions for trivial human judgement. Comparing to traditional matting algorithms, the proposed framework requires much less efforts, and can produce satisfactory results with just 10 regions. Through extensive experiments, we show that the proposed model reduces user efforts significantly and achieves comparable performance to dense trimaps in a user-friendly manner. We further show that the learned informative knowledge can be generalized across different matting algorithms.

Image matting is an ill-posed problem. It requires a user input trimap or some strokes to obtain an alpha matte of the foreground object. A fine user input is essential to obtain a good result, which is either time consuming or suitable for experienced users who know where to place the strokes. In this paper, we explore the intrinsic relationship between the user input and the matting algorithm to address the problem of where and when the user should provide the input. Our aim is to discover the most informative sequence of regions for user input in order to produce a good alpha matte with minimum labeling efforts. To this end, we propose an active matting method with recurrent reinforcement learning. The proposed framework involves human in the loop by sequentially detecting informative regions for trivial human judgement. Comparing to traditional matting algorithms, the proposed framework requires much less efforts, and can produce satisfactory results with just 10 regions. Through extensive experiments, we show that the proposed model reduces user efforts significantly and achieves comparable performance to dense trimaps in a user-friendly manner. We further show that the learned informative knowledge can be generalized across different matting algorithms.

Together with The Heart Fund, 42.cx wants to solve public health challenges by modelizing diseases patterns through applied artificial intelligence to support THF doctors during their medical tasks. The generated prediction system will run on portable devices to disrupt healthcare in developing countries and to fight cardiovascular disease. "The Heart Fund combats cardiovascular diseases by offering access to care to millions of children in developing countries. For the first time in history with this partnership, artificial intelligence scientists have access to thousands of electrocardiograms (ECG), blood panels, evaluations and resulting diagnosis. This allows us to build more accurate models than ever before. With our technology a highly qualified diagnosis can be performed at thousands of different locations at the same time, around the clock anywhere in the world. It's practically like having the know-how and knowledge of the best cardiologic surgeons combined and being present at the same time anywhere.,"