Back to all discussions

Manager   •   about 4 years ago

Accenture Problem Statements

Prize: Hiring Opportunities Mentor: Priyanka Shah - http://www.linkedin.com/in/compuwizpiyu
Resources available here - https://1drv.ms/w/s!AvJxssZTO60yeU3k3F7U-IsZ7_M?e=YGdK3n

Problem Statements:

1. Speech to sign language conversion
AI for community initiative. Help the hearing impaired. Participants are expected to train an AI model that can convert text from videos/ presentations to Sign language (using the American Sign language data set)

2. Personalized Gym TrAIner
Get FIT with AI. Build your own AI powered GYM trainer that analyzes your exercise form and reps and tells us if you are really hitting it correctly. Analyze form and count of reps done via exercise classification and pose detection. Open data set available for this. Participants are expected to train a model based on certain exercise postures (yoga, for easier pose detection and availability of dataset).

3. AI SPY : AI powered image caption generation
AI “sees” an image and generates a caption. This is commonly used for auto tagging and generating metadata for images to organize and search images. Also used for marketing campaigns, generating tag lines for products etc. Participants are expected to train a custom vision model trained on available open image sets.

4. Vision COP: image search engine
Build an image search engine for identifying real source of images and searching images based on visual cues instead of text, tags. Content-based image retrieval (CBIR) is a system for retrieving relevant images based on a given image. The system consists of an image query and an image database. This is Heavily used for fake images/news tracking. It is also the basis of recommendations or “images like this… similar images to what you searched” kind of functionality. Participants are expected to take a test image and show similar images to the test item.

5. AI Professor
Search for documents that talk about the same thing contextually from a set of documents. Participants will be given a data set of some open-source categories (BBC news items). The BBC News Data set can be found here: http://mlg.ucd.ie/files/datasets/bbc-fulltext.zip Participants have to classify the above news articles belonging to certain themes

6. Movies semantic search
Build a knowledge graph based in WIKI music open data set to related to movies. Data set : https://www.kaggle.com/jrobischon/wikipedia-movie-plots The dataset contains descriptions of 34,886 movies from around the world.

Resources available here - https://1drv.ms/w/s!AvJxssZTO60yeU3k3F7U-IsZ7_M?e=YGdK3n

  • 7 comments

  •   •   about 4 years ago

    Hi Elizabete, I seem to cannot view the resources from the link given https://1drv.ms/w/s!AvJxssZTO60yeU3k3F7U-IsZ7_M?e=YGdK3n. Can I get another link for this?

  • Manager   •   about 4 years ago

    Hi! What seems to be the problem? There are github, kaggle and zip download links within the document. Can you see them? Which Problem Statement's resources can you not find?

  •   •   about 4 years ago

    I cannot see them unfortunately, it directs me to the one drive web page but it is blank. I didn't see any of the GitHub, kaggle and zip download links. I am interested in the Problem Statement 1 but from the resources link, I am unable to view anything.

  • Manager   •   about 4 years ago

    1. driveSpeech to sign language conversion.

    · AI for community initiative. Help the hearing impaired.

    · Participants are expected to train an AI model that can convert text from videos/ presentations to Sign language (using the American Sign language data set)

    · The ASL data set has hand gestures for each English language alphabet.

    · The working model should be able to transcribe speech from a video/ audio stream and convert it in to corresponding sign language hand gestures.

    · Demo can be done on simple speech/ audio lines spoken with clarity…

    o “Hello, Welcome to the hackathon”

    o “Good morning”

    · Participants can have a look at the following video to get an idea of the output : Multilingual Speech to Sign Language Translator - YouTube · Data set available here https://www.kaggle.com/grassknoted/asl-alphabet

    · Participants can use any programming language, any platform (cloud, on-premise), can use any out of the box cloud AI offerings (for example Microsoft Cognitive services, AutoML)

    · Deployment of the model needs to be on cloud.

    · Solutions will be judged on scalability, completeness, framework usability, model portability, participant’s understanding of the problem/solution and the approach.

  •   •   about 4 years ago

    Thank you very much Elizabete

  • Manager   •   about 4 years ago

    Recording is available here - https://itraingroup-my.sharepoint.com/:v:/g/personal/elizabete_itraingroup_onmicrosoft_com/EQU3TX-pTw9MqvDJ4HmZh2QBmo81sBFnI9HsStGN1aW_ww?e=piM37d

  •   •   about 4 years ago

    Hello ,is this hiring oppurtunities are only for women? And solving one problem statement is enough or need to work on all of them.
    Thanks.

Comments are closed.