Saftie Camera

100+
ଡାଉନଲୋଡଗୁଡ଼ିକ
ବିଷୟବସ୍ତୁ ମୂଲ୍ୟାଙ୍କନ
ସମସ୍ତେ
ସ୍କ୍ରିନସଟ୍ ଛବି
ସ୍କ୍ରିନସଟ୍ ଛବି

ଏହି ଆପ୍ ବିଷୟରେ

This app is an effort to reduce deaths related to selfies. This
camera does a real-time analysis of the image it's seeing and nudges a
user if it infers a scene to be dangerous. The app does this inference
using deep learning techniques. We do not recommend any user to go
solely on the basis of the nudge shown by the app. Instead the nudge
is supposed to augment the user's awareness. Though we have made our
inference model to be robust to perturbations, there are bound to be
both false positives and false negatives in our inferences. We suggest
the user act responsibly in such cases. If you feel the nudge is
bothering you, click on ignore and the app won't nudge you again. Stay
safe while clicking selfies. This work is based on our research work:
+ Nanda, V., Lamba, H., Agarwal, D., Arora, M., Sachdeva, N., and Kumaraguru, P. Stop the Killfies! Using Deep Learning to Identify Dangerous Selfies. Accepted at the 9th International Workshop on Modeling Social Media (MSM'2018) Applying Machine Learning and AI for Modeling Social Media. http://precog.iiitd.edu.in/pubs/stop-killfies-webconf18.pdf
+ Lamba, H., Bharadhwaj, V., Vachher, M., Agarwal, D., Arora, M., Sachdeva, N., Kumaraguru, P. From Camera to Deathbed: Understanding Dangerous Selfies on Social Media. Accepted as Poster at the 11th International Conference on Web and Social Media (ICWSM), 2017. Poster. http://precog.iiitd.edu.in/pubs/camera-to-deathbed-icwsm2017.pdf
+ Lamba, H., Bharadhwaj, V., Vachher, M., Agarwal, D., Arora, M., and Kumaraguru, P. Me, Myself and My Killfie: Characterizing and Preventing Selfie Deaths. Nov 2016. Technical Report. http://precog.iiitd.edu.in/Publications_files/HL-et.al.KillFie.pdf
ଗତ ଅପଡେଟର ସମୟ
ଅକ୍ଟୋବର 24, 2018

ଡାଟା ସୁରକ୍ଷା

ଡେଭେଲପରମାନେ, ଆପଣଙ୍କ ଡାଟାକୁ ସେମାନଙ୍କ ଆପ କିପରି ସଂଗ୍ରହ ଓ ବ୍ୟବହାର କରେ ସେହି ସୂଚନା ଏଠାରେ ଦେଖାଇପାରିବେ। ଡାଟା ସୁରକ୍ଷା ବିଷୟରେ ଅଧିକ ଜାଣନ୍ତୁ
କୌଣସି ସୂଚନା ଉପଲବ୍ଧ ନାହିଁ

ନୂଆ କଣ ଅଛି

This is the first release of the app.