How to use headers and footers in Word

If you create a Word document where you want to include page numbers, the author’s name, the document title, or similar details without distracting from the content, you can use headers and footers.

As the names imply, headers appear at the top of the document and footers appear at the bottom. The items that you include in the header or footer are dimmed in appearance. By default, headers and footers display on every page of your document. However, you can alternate by even and odd pages or have the first page of your document different than the rest.

Let’s look at how to add headers and footers in Word as well as customize them to fit your needs.

Add a premade header or footer in Word

Because the process is the same for both headers and footers, you can follow these same steps to add either one or both to your document.

Word provides premade headers and footers that give you a layout such as columns or a banded strip. You can then use the suggested details or add your own.

Step 1: Go to the Insert tab and head to the Header and footer section of the ribbon.

Step 2: Open the Header or Footer drop-down menu and pick the layout you want. You’ll notice some layouts have preset details like document title or page number.

Step 3: After you select the layout, you’ll see the header or footer open automatically. Enter the details into the highlighted text area.

Step 4: When you finish customizing one or both locations, pick Close header and footer in the ribbon or double-click a spot outside of the header or footer area in your document.

Premade header layout added to a Word document.

Add a blank header or footer

You don’t have to start with a premade layout for your header or footer. You can simply open one or the other and enter the details you want.

Step 1: Go to the very top of your document for a header or very bottom for a footer.

Step 2: Double-click inside the area of the top or bottom margin.

Header area pointed out in Word.

Step 3: When the header or footer area opens, place your cursor inside and enter the details you want.

Step 4: After you finish, pick Close header and footer in the ribbon or select a spot in your document.

Cursor inside the header area of a Word document.

Customize a header or footer

You can insert fields for document details, change the pages you want to display a header or footer, and adjust the size of the header or footer area.

Step 1: Open the header or footer area by double-clicking the spot inside the top or bottom margin. This displays the Header and footer tab with tools in the ribbon.

Step 2: To add the date and time, a document field, or an image, select one of these options from the Insert section of the ribbon.

Insert section of the Header and Footer tab in Word.

Step 3: To change the pages where you want the header or footer to appear, go to the Options section of the ribbon. Check the box for Different first page to use a specific header or footer on the first page only. Or, check the box for Different odd and even pages to use certain headers on every other page.

Options section of the Header and Footer tab in Word.

Step 4: To adjust the size of the header or footer, use the boxes in the Position section of the ribbon. You can enter a measurement into the top or bottom box or use the arrows to increase or decrease the size in small increments.

Position section of the Header and Footer tab in Word.

Step 5: To use a layout or include page numbers with a certain layout, use the drop-down menus on the left side of the ribbon in the Header and footer section. You’ll see the same options as the first set of steps here for using a premade header or footer as well as page numbers.

Layouts on the Header and Footer tab in Word.

Remove a header or footer

If after you add a header or footer to your document, you want to remove it, you can do so easily.

Step 1: Go to the Insert tab and head to the Header and footer section of the ribbon.

Step 2: Open the Header or Footer drop-down menu for whichever area you want to remove.

Step 3: Select Remove header or Remove footer.

Remove Header in the drop-down menu.

Headers and footers in Word give you the ideal spots for document details you want to display. Whether page numbers, the date, title, or even a company logo, take advantage of those spaces in your next document.

For more, look at ways to improve your workflow in Word or some things you might not know you can do in Word.

Editors’ Choice

Repost: Original Source and Author Link


Passkeys were never an Apple-only word, but the confusion is understandable

When Apple introduced passkeys, its implementation of FIDO Alliance’s password-less secure authentication technology, the company did it in the most Apple way possible. It made an icon and printed a very on Apple brand-looking “Passkeys” next to it, complete in the San Francisco font. And if you’ve watched only part of the WWDC presentation on Apple’s passkeys, it’s possible to assume passkeys are an exclusive feature of Apple’s iCloud Keychain. Just a reminder: it’s not.

The term “passkey” will also be used by major players Microsoft and Google. It’s used as a common noun and can be pluralized or singular, for instance: “you should set a passkey for your banking app.” In other words, treat the word “passkey” as you would treat the word “password”. Passkeys work by letting you log in to an app or website with just your username and your pre-authenticated device — which uses a cryptographic token instead of a password and text message code that could get phished or otherwise compromised.

Apple’s software engineering manager Ricky Mondello started a Twitter thread yesterday to promote the new technology and to clarify what it means. Microsoft’s VP of identity Alex Simons chimed in the thread and confirmed that Microsoft will also be adopting the name. All involved parties seem to be committed to spreading awareness of passkeys, and thus far none are trying to claim it as their own.

“Passkey” is certainly an easier to digest name compared to “FIDO authentication,” which could be really confusing when used verbally — like is this where I want to enter the name of my first pet? But seriously, if you’ve ever had to explain to the common person what two-factor authentication was, and it took longer than five minutes, imagine teaching them what FIDO authentication is.

In order for the technology to succeed, it needs that marketing push, and what better way to get the word out there than to let Apple take the helm. If Apple was really trying to trick people into thinking that passkeys are an Apple-only technology it probably would have been branded Apple PassKeys.

If you’re on the developer betas for macOS or iOS, you can start using passkeys now where available. Google plans to open the developer tools needed to implement passkeys on Android “towards the end of 2022”. And Microsoft currently supports passkeys on the web using Windows Hello, and will support logging into a MS account using passkeys from an iOS or Android device “in the near future”.

Repost: Original Source and Author Link


Hackers can now take over your computer through Microsoft Word

A new zero-day vulnerability in Microsoft Office could potentially allow hackers to take control of your computer. The vulnerability can be exploited even if you don’t actually open an infected file.

Although we’re still waiting for an official fix, Microsoft has released a workaround for this exploit, so if you frequently use MS Office, be sure to check it out.

Interesting maldoc was submitted from Belarus. It uses Word's external link to load the HTML and then uses the "ms-msdt" scheme to execute PowerShell code.

— nao_sec (@nao_sec) May 27, 2022

The vulnerability has been dubbed Follina by one of the researchers who first looked into it — Kevin Beaumont, who also wrote a lengthy post about it. It first came to light on May 27 through a tweet by nao_sec, although Microsoft allegedly first heard of it as early as April. Although no patch has been released for it just yet, Microsoft’s workaround involves disabling the Microsoft Support Diagnostic Tool (MSDT), which is how the exploit gets entry into the attacked computer.

This exploit affects primarily .rtf files, but other MS Word files can also be affected. A feature in MS Word called Templates allows the program to load and execute code from external sources. Follina relies on this in order to enter the computer and then runs a series of commands that opens up MSDT. Under regular circumstances, MSDT is a safe tool that Microsoft uses to debug various issues for Windows users. Unfortunately, in this case, it also grants remote access to your computer, which helps the exploit take control of it.

In the case of .rtf files, the exploit can run even if you don’t open the file. As long as you view it in File Explorer, Follina can be executed. Once the attacker gains control of your computer via MSDT, it’s up to them as far as what they want to do. They might download malicious software, leak files, and do pretty much everything else.

Beaumont has shared plenty of examples of the way Follina has already been exploited and found in various files. The exploit is being used for financial extortion, among other things. Needless to say — you don’t want this on your computer.

What do you do until Microsoft releases a patch?

There are a few steps you can take to stay safe from the Follina exploit until Microsoft itself releases a patch that will fix this problem. As things stand now, the workaround is the official fix, and we don’t know for a fact that anything else is sure to follow.

First and foremost, check whether your version of Microsoft Office could potentially be affected. So far, the vulnerability has been found in Office 2013, 2016, 2019, 2021, Office ProPlus, and Office 365. There is no telling whether older versions of Microsoft Office are safe, though, so it’s better to take additional steps to protect yourself.

If you’re able to avoid using .doc, .docx, and .rtf files for the time being, it’s not a bad idea. Consider switching to cloud-based alternatives like Google Docs. Only accept and download files from 100%-proven sources — which is a good guideline to live by, in general.

Last but not least, follow Microsoft’s guidance on disabling MSDT. It will require you to open the Command Prompt and run it as administrator, then input a couple of entries. If everything goes through as planned, you should be safe from Follina. Nevertheless, remember to always be cautious.

Editors’ Choice

Repost: Original Source and Author Link


Facebook’s AI can copy the style of text in photos from a single word

Elevate your enterprise data technology and strategy at Transform 2021.

Facebook today introduced TextStyleBrush, an AI research project that can copy the style of text in a photo from just a single word. The company claims that TextStyleBrush, which can edit and replace arbitrary text in images, is the first “unsupervised” system of its kind that can recognize both typefaces and handwriting.

AI-generated images have been advancing at a breakneck pace, and they have obvious business applications, like photorealistic translation of languages in augmented reality (AR). (The AR market was anticipated to be worth $18.8 billion by the end of 2020, according to Statista.) But building a system that’s flexible enough to understand the nuances of text and handwriting is a difficult challenge because it means comprehending styles for not just typography and calligraphy but for transformations like rotations, curved text, deformations, background clutter, and image noise.

Facebook TextStyleBrush

TextStyleBrush works much like style brush tools in word processors but for text aesthetics in images, according to Facebook. Unlike previous approaches, which define specific parameters like typeface or target style supervision, it takes a more holistic training approach and disentangles the content of a text image from all aspects of its appearance.

Unsupervised learning

The “unsupervised” part of the system refers to unsupervised learning, the process by which the system was subjected to “unknown” data that had no previously defined categories or labels. TextStyleBrush had to teach itself to classify data, processing the unlabeled data to learn from its inherent structure.

As Facebook notes, training systems like TextStyleBrush typically involves annotated data that teaches the system to classify individual pixels as either “foreground” or “background” objects. But it’s tough to apply this to images captured in the real world. Handwriting can be one pixel in width or less, and collecting high-quality training data requires labeling the foregrounds and backgrounds.

By contrast, given a detected “text box” containing a source style, TextStyleBrush renders new content in the style of the source text using a single sample. While it occasionally struggles with text written in metallic objects and characters in different colors, Facebook says TextStyleBrush proves it’s possible to build systems that can learn to transfer text aesthetics with more flexibility than was possible before.

Facebook TextStyleBrush

“We hope this work will continue to lower barriers to photorealistic translation [and] creative self-expression,” Facebook said in a blog post. “While this technology is research, it can power a variety of useful applications in the future, like translating text in images to different languages, creating personalized messaging and captions, and maybe one day facilitating real-world translation of street signs using AR.”

The capabilities, methods, and results of the work on TextStyleBrush are available on Facebook’s developer portal. The company says it plans to submit it to a peer-reviewed journal in the future.


VentureBeat’s mission is to be a digital town square for technical decision-makers to gain knowledge about transformative technology and transact.

Our site delivers essential information on data technologies and strategies to guide you as you lead your organizations. We invite you to become a member of our community, to access:

  • up-to-date information on the subjects of interest to you
  • our newsletters
  • gated thought-leader content and discounted access to our prized events, such as Transform 2021: Learn More
  • networking features, and more

Become a member

Repost: Original Source and Author Link


6 Things You Didn’t Know You Could Do in Microsoft Word

The first thing you fire up when you have a research paper, resume, or another important document to type up is likely Microsoft Word. There are lots of great things you can do with it, but there are also some secrets in Word that might surprise you.

Here are six things you didn’t know you could do in Microsoft Word. We’ll touch all the bases, including voice dictation, cropping images, and much more.

Voice dictation

With voice dictation, you can use Word’s speech-to-text feature to speak out your words instead of having to type them on the keyboard. This is great for when you’re feeling lazy, and it could even end up saving you some time.

Microsoft says the feature works across MacOS and Windows 10, and even on iOS and Android — as long as you’re subscribed to Microsoft 365. It won’t work if you own the version of Word included with Office versions, such as Office 2019, according to Microsoft.

We’ll focus on Windows 10 here, but the full directions for other platforms are available on Microsoft’s website. Just open a new document, go to the Home tab, and then look for Dictate. From there, click the Dictate button and wait for the button to turn on and start listening to you.

Start speaking to see the text appear on the screen, and then insert your punctuation by speaking it out loud (such as period, or comma.) You can fix your mistakes by saying things like “undo” or “delete” or “delete last XX words” or “delete that.” Formatting commands like “bold” “italics” “underline” also work.

Translate your documents

Did you just get a document in another language? Perhaps from a colleague or a friend in another location in the world? You might think this means you’ll have to visit Google Translate and copy and paste your entire document to get it into English. But there’s no need to do that! Word has your back.

In Word for Microsoft 365 (again, we’re talking about the subscription-based version of Office, which includes Word), Word will automatically offer to translate your document for you. You also can translate phrases into other languages. Just make sure you’re connected to the internet and have Office connected experiences enabled to use the feature.

To translate an entire document, you just need to click the Review tab. From there, Word will offer to translate the document, and you can accept. If this does not work, you can click the Review tab and then Translate. A newer, machine-translated copy of the document will then be created for you.

You also can translate individual text to other languages by highlighting the text, then going to Review > Language > Translate. Translating individual text might work in Office 2019, according to Microsoft.

Transcribe your interviews in Word Online

If you’re subscribed to Microsoft 365 to access Word and the other Office apps, there’s a bonus feature for you. If you open Word on the web, then you can turn your recorded interviews into actual words on the screen, without having to do all the typing yourself.

Just open a new blank document online, then click the Home tab followed by Dictate. You should then see the Transcribe button. Click the Upload Audio button, and upload your interview or audio file. You also can start the recording. Word will then do its magic in the background, and output a full transcript in the sidebar. You can click the transcript to edit it or copy it over to your main document.

Resume Assistant in Word

If you’re on the hunt for a job, then Microsoft Word can help. While most jobs prefer a resume that’s based on a template, you can use Word for some inspiration in resume typing and then tweak your resume to stand out from the rest. This feature is known as the Resume Assistant.

You can fire up the Resume Assistant by clicking the Review tab and then choosing Resume Assistant. The entire experience is powered by LinkedIn. Choose the Get Started button and then follow the prompts in the sidebar to complete your resume. It doesn’t get any easier! You’ll see examples for various types of jobs and other fields that might be similar to your own.

Use stock images and crop and edit photos

Seeking out some additional images for your document in Word? Don’t go to Google! Word can pull and handle photos from the web.

You can actually insert photos in Word directly from the web. Just click the Insert tab, and then choose Pictures. From there, choose Stock Images. You’ll then be able to search for a specific stock photo that you can use in your document. Use the tab along the top to filter different types, stickers, illustrations, and more.

Once you insert an image into Word, you can alter the image directly. Just click it, and bring the Picture Format tab up. There will be tabs for Corrections, Color, Cropping, Adding Alt Text, and so much more. The sky is the limit!

Use Quick Parts

Our final trick on the list is a Word feature known as Quick Part. This feature helps you insert some standard elements of text in your document, without having to manually type things out. Quick Part examples include your name, an abstract, company address, and more. You can see the full list by clicking the Insert tab and then choosing Quick Parts.

Editors’ Choice

Repost: Original Source and Author Link


Indie Game Developers Are Redefining the Word Cinematic

Over the past decade, the word cinematic has become a cliché in video games. It’s a term that’s come to describe big-budget studio games like The Last of Us Part 2. Have a big action set piece? That’s cinematic. Expensive cutscenes that look like a Michael Bay movie? Cinematic. Characters with any semblance of depth. Pure cinema!

The word has lost its meaning, transforming into a genre label that describes a very specific type of Hollywood-sized action game. But film is a wide media that encompasses much more than just blockbusters. There are plenty of other elements that video games can borrow from movies to create richer storytelling experiences.

While A-list games continue to build spectacle, indie developers are reaching deeper into the moviemaking toolkit to create more diverse storytelling experiences. In the process, they’re breaking down some long-standing barriers between the gaming and film world.

Playing with form

Ten years ago, it was a big deal when a video game looked or sounded like a movie. PlayStation 3 title Heavy Rain made a major impact in 2010 because no one had quite seen anything like it at the time. It felt like a playable film and offered an emotionally challenging (at least by 2010 standards) experience.

That’s changed significantly over the past decade. Now, it’s more common to see video games tell scripted stories rather than delivering interactivity with a narrative backdrop to drive the action. Those strides toward storytelling have been especially notable in the independent scene, which has steadily changed the definition of what a game even is over the years.

There are plenty of examples of that in 2021’s upcoming slate of releases. Take Last Stop, for instance. The adventure game comes from developer Variable State, best known for its mystery game Virginia. Upon its release, Virginia was unique for using film editing techniques. Last Stop uses similar ideas, with deliberate cuts and camera angles sprinkled in during the conversation-heavy gameplay.

In a press event for the game, Variable State developers discussed film as a driving inspiration for the title. They specifically cited the works of Robert Altman, a director known for creating large ensemble films with multiple character-driven story lines, as a key influence for the project.

Last Stop borrows that same idea to create an interwoven mystery. Players control three seemingly unrelated London residents whose paths cross throughout the game. It’s an anthology tale, which isn’t something we normally associate with video games. Surprisingly, Last Stop’s closest gaming equivalent might be Rockstar’s Grand Theft Auto V, where players control three Los Santos criminals.

For cinephiles who crave these type of stories, there’s bolder work being done in the gaming scene today than there is in Hollywood.

Rethinking genre

Indie studios aren’t just experimenting with film structure; they’re also rethinking what kinds of genres into which games can fit. While publishers like Bethesda heavily draw on science fiction and high fantasy, smaller studios tend to showcase more flexibility. That goes for both style and subject matter.

To see that in action, look to Hazelight Studios. Led by the ever-eclectic Josef Fares (a former filmmaker), the indie studio has built its name on pushing video game storytelling by playing with genre. Its 2018 multiplayer game A Way Out drew from prison escape movies to tell a dramatic story grounded in realism.

This year, it went in the opposite direction with It Takes Two, but the game still follows a similar philosophy. While it’s more of a magical realist fantasy, Fares uses the term “romantic comedy” to describe the game. That’s territory where major game studios have feared to tread over the medium’s life span.

That shyness toward certain genres limits what kinds of stories games can tell. By pulling from the traditional rom-com structure, Hazelight is able to tell a story about a couple on the verge of divorce that emphasizes the importance of collaboration in a relationship. That idea might sound pretty normal for a movie, but it’s weirdly uncharted territory in video games.

The scope of video game storytelling is constantly widening thanks to games like It Takes Two, and it’s not the only example. Eliza is an excellent visual novel about a woman working for a morally questionable tech company that has automated talk therapy. Last year’s standout If Found… is a striking game about a transgender woman struggling to gain her family’s acceptance. One of this year’s best games so far, Before Your Eyes, is a tearjerking drama about a person at the end of their life reliving their memories, with the entire game controlled by players’ blinks, which are tracked through a webcam.

They may not have multimillion dollar budgets, but they’re no less “cinematic” than The Last of Us.

Welcome to the club

The film world is taking not,e and that’s a significant change compared to where the industry was a decade ago. In 2010, late film critic Roger Ebert famously penned an article declaring “video games can never be art.” It was a contentious take that divided the film and gaming worlds.

The scene looks much different in 2021. Just look at this year’s Tribeca Film Festival, which will feature eight indie games as official selections alongside films. The first-of-its-kind decision is a sort of existential victory for a medium that’s long been painted as inferior to cinema. They’re slowly becoming equals, overcoming decades of cinephile stigma.

The gaming industry is particularly ready for that change. EA Originals Vice President Rob Letts shared his perspective on the age-old debate with Digital Trends. The EA Originals label published It Takes Two, which is part of  its deliberate strategy to support story-driven indie games that take cues from the film world. Letts sees a world where the two mediums happily coexist.

“Overall, I’m not a fan of the movies-versus-games debate,” Letts tells Digital Trends. “They live in harmony with one another, not in conflict. Films and video games are both impressive immersive experiences. The line between game, social network, and content channel is becoming increasingly blurred – and as a result, the two mediums are creating different types of experiences in different ways.”

By learning from other art forms, games are evolving in a way that’s only expanding what they’re capable of. There’s a good chance that ends up going the other way soon, with filmmakers looking to indie game experiences to pick up some new tricks.

Editors’ Choice

Repost: Original Source and Author Link


Google tests smart displays that activate without a wake word

A new feature being internally tested at Google could remove the need to say “Hey Google” before voicing commands to Nest Hub smart displays, Android Central reports. Instead, the feature codenamed “Blue Steel” could allow the device to simply sense your presence, and proactively listen for commands without first needing to hear the wake word.

The functionality has been shown off in a video posted to YouTube by Jan Boromeusz, who Android Central notes previously leaked features like the Nest Hub’s new dark mode prior to its official announcement. In the video, Boromeusz can be seen asking for a variety of information, all without once uttering the words “Hey Google.” His Nest Hub Max smart display is reportedly running leaked internal firmware meant for testing within Google, and it’s unclear if the company has any plans to release the functionality publicly.

The speculation is that the Nest Hub Max is using its existing ultrasound sensing to sense a person’s presence and start listening. At the moment, the smart display uses this to simply adjust the information it shows. However, in the future, this same technology could allow it to listen out for voice commands when it knows you’re nearby. Ars Technica speculates that it could also use its camera’s Face Match feature to get a better idea of who’s speaking. Boromeusz shows an option to turned Blue Steel on and off in the smart display’s settings menu.

If released to the public, Blue Steel could raise privacy concerns. A key element of current smart speakers and displays is that they only pay attention to what you’re saying after they hear the wake word. Relying upon proximity detection alone increases the risk of the devices hearing something they’re not supposed to, at the expense of your privacy.

That said, “Blue Steel” could make for a useful optional feature for some. Having to repeatedly say “Hey Google” or “Ok Google” before every voice command can be a pain, and this potentially makes accessing information you need far quicker.

Repost: Original Source and Author Link


How to Delete a Page in Word

Blank pages in a document can make an unprofessional impression on editors or potential employers. Microsoft Word is known to create blank pages in a document. Before you hit the send button, you should make sure to delete them whenever possible.

Our goal is to help others avoid the frustration associated with blank pages. Since Microsoft Word is the most used document creator out there, we have created the following guide to help you delete those unwanted pages should they crop up in this particular word processor.

How to delete a page in Word that has text and graphics in it

Step 1: Select the page you want to delete

The first step in deleting a page is making sure it’s selected. The last thing you want to do is delete the wrong one. Either scroll to the page or use the Go To function (Ctrl + G in Windows, Option + CMD + G in MacOS).

When you’ve found the page, click or tap anywhere on it to select it.

Step 2: Select the whole page

It might sound like you’ve already done this step, but this is so that Word knows that you want to delete the whole page, not just some of the content on it. Open the Go To function (Ctrl + G, or Option + CMD + G if you’re on a Mac) and type page in the Enter Page Number box. Then select Go To (or press Enter on your keyboard) followed by Close.

Step 3: Delete the page

Microsoft Word doesn’t have a dedicated page deletion tool, but now that we’ve selected the whole page, we can delete it very easily. Double-check that you’ve selected the entirety of the page you want to delete, and then press the Delete key.

How to delete a blank page in Word

Most text editors, Word included, have a habit of creating blank pages at the end of your document for seemingly no reason. Deleting those before you fire it off to your boss (here’s how to recall it if you didn’t) or the printer is usually a good idea. To make the process as fast as possible, you can use a couple of quick methods.

Step 1: To find the blank page(s), open up the Navigation pane. You can do so by selecting View from the top menu and making sure that the Navigation Pane box is ticked. That should open up a new column on the left-hand side, showing all the pages in your document. If it doesn’t, make sure to select the Pages tab in it.

Delete a page

Step 2: Scroll through the list to find the blank page(s) you want to delete. Pick one and double click or tap it to jump straight to it.

Step 3: Hold Ctrl + Shift + 8 on Windows or Command + 8 if you’re using a Mac to make the paragraph markers visible. This command will ensure that, despite a page having no content on it, paragraph markers will still function as if there were.

Step 4: Select the paragraph markers by clicking and dragging, or use the arrow keys and hold down the Shift key. You can eliminate the paragraph markers by pressing the Delete key, but this will also close out the blank page altogether. 

You can place the paragraph markers at the bottom of your document if you think you will use them again later. When you have reached proper placement for your paragraph markers, you can alter them by increasing or decreasing font size. Click on the Home tab and put “1” in the Font Size box, and press Enter to lock in the size. After you’ve made all necessary changes, you can hide the paragraph markers again by holding Ctrl + Shift + 8 on Windows or Command + 8 on a Mac.

Change paragraph font size

Editors’ Choice

Repost: Original Source and Author Link


Microsoft’s new image-captioning AI will help accessibility in Word, Outlook, and beyond

Microsoft has developed a new image-captioning algorithm that exceeds human accuracy in certain limited tests. The AI system has been used to update the company’s assistant app for the visually impaired, Seeing AI, and will soon be incorporated into other Microsoft products like Word, Outlook, and PowerPoint. There, it will be used for tasks like creating alt-text for images — a function that’s particularly important for increasing accessibility.

“Ideally, everyone would include alt text for all images in documents, on the web, in social media — as this enables people who are blind to access the content and participate in the conversation,” said Saqib Shaikh, a software engineering manager with Microsoft’s AI team in a press statement. “But, alas, people don’t. So, there are several apps that use image captioning as way to fill in alt text when it’s missing.”

These apps include Microsoft’s own Seeing AI, which the company first released in 2017. Seeing AI uses computer vision to describe the world as seen through a smartphone camera for the visually impaired. It can identify household items, read and scan text, describe scenes, and even identify friends. It can also be used to describe images in other apps, including email clients, social media apps, and messaging apps like WhatsApp.

Microsoft does not disclose user numbers for Seeing AI, but Eric Boyd, corporate vice president of Azure AI, told The Verge the software is “one of the leading apps for people who are blind or have low vision.” Seeing AI has been voted best app or best assistive app three years in a row by AppleVis, a community of blind and low-vision iOS users.

Microsoft’s new image-captioning algorithm will improve the performance of Seeing AI significantly, as it’s able to not only identify objects but also more precisely describe the relationship between them. So, the algorithm can look at a picture and not just say what items and objects it contains (e.g., “a person, a chair, an accordion”) but how they are interacting (e.g., “a person is sitting on a chair and playing an accordion”). Microsoft says the algorithm is twice as good as its previous image-captioning system, in use since 2015.

The algorithm, which was described in a pre-print paper published in September, achieved the highest ever scores on an image-captioning benchmark known as “nocaps.” This is an industry-leading scoreboard for image captioning, though it has its own constraints.

The nocaps benchmark consists of more than 166,000 human-generated captions describing some 15,100 images taken from the Open Images Dataset. These images span a range of scenarios, from sports to holiday snaps to food photography and more. (You can get an idea of the mixture of images and captions by exploring the nocaps dataset here or looking at the gallery below.) Algorithms are tested on their ability to create captions for these pictures that match those from humans.

It’s important to note, though, that the nocaps benchmarks capture only a tiny sliver of the complexity of image captioning as a general task. Although Microsoft claims in a press release that its new algorithm “describes images as well as people do,” this is only true insomuch as it applies to a very small subset of images contained within nocaps.

As Harsh Agrawal, one of the creators of the benchmark, told The Verge over email: “Surpassing human performance on nocaps is not an indicator that image captioning is a solved problem.” Argawal noted that the metrics used to evaluate performance on nocaps “only roughly correlate with human preferences” and that the benchmark itself “only covers a small percentage of all the possible visual concepts.”

“As with most benchmarks, [the] nocaps benchmark is only a rough indicator of the models’ performance on the task,” said Argawal. “Surpassing human performance on nocaps by no means indicates that AI systems surpass humans on image comprehension.”

This problem — assuming that performance on a specific benchmark can be extrapolated as performance on the underlying task more generally — is a common one when it comes to exaggerating the ability of AI. Indeed, Microsoft has been criticized by researchers in the past for making similar claims about its algorithms’ ability to comprehend the written word.

Nevertheless, image captioning is a task that has seen huge improvements in recent years thanks to artificial intelligence, and Microsoft’s algorithms are certainly state-of-the-art. In addition to being integrated into Word, Outlook, and PowerPoint, the image-captioning AI will also be available as a standalone model via Microsoft’s cloud and AI platform Azure.

Repost: Original Source and Author Link

Tech News

“Hey, Facebook” wake word lands on Oculus Quest 2 and Portal

Almost all the Big Tech companies have smart assistants these days except for Facebook. There have been rumors and signs that the social media giant would be coming out with its own but nothing has materialized so far. It might, however, be taking another step in that direction by pushing its own trigger phrase to activate voice commands not only on its Portal smart display but even on the Oculus Quest 2 VR headset.

Although it didn’t make sense years ago, Facebook was time and again rumored or even confirmed to be working on one form of AI-powered assistant or another. Those included the “M” assistant on Messenger but that was mostly intended to assist in shopping activities. With Facebook dipping its fingers in almost everything, it would only be a matter of time before it started making bigger steps in that direction.

To be clear, the Oculus Quest 2 has long had voice commands that could be triggered through physical controls. What Facebook is doing is to allow for complete hands-free operation by simply uttering the magic phrase “Hey, Facebook”. The announcement makes it clear that it is an optional feature that is disabled by default and users have to explicitly toggle that switch if they want to experience it.

Less obvious is the silent change spotted by The Verge where the Portal smart display will also start responding to “Hey, Facebook”. Previously, it was only “Hey, Portal” that could be used but now Facebook’s name will also be able to start video calls.

It isn’t really a surprising step given Facebook’s expansion of its brand to Oculus. It may even make sense in the smart display’s case where “Portal” is as impersonal as it can be. It may, however, suggest that Facebook is already starting the journey that would push the “Hey, Facebook” wake word on the same level as “OK, Google”, “Hey, Siri”, and “Alexa”.

Repost: Original Source and Author Link