places.csail.mit.edu
MIT Scene recognition demo
http://places.csail.mit.edu/demo.html
MIT Scene Recognition Demo. This demo identifies if the image is an indoor or an outdoor place, and suggests the five most likely place categories representing the image, using Places-CNN (see project page. It is made for pictures of environments, places, views on a scene and a space (as opposed to picture of an object). You also could upload image using mobile phone. Upload .jpg or jpeg image only. The heatmap is generated by the CAM.
cvcl.mit.edu
Computational Perception & Cognition
http://cvcl.mit.edu/publications.html
Principal Investigator: Aude Oliva. Zhou, B., Khosla, A., Lapedriza , A., Oliva, A., and Torralba, A. (coming soon). Places: An Image Database for Deep Scene Understanding. Bylinskii, Z., Recasens, A., Borji , A., Oliva, A., Torralba, A. and Durand, F. (in press, 2016). Where should saliency models look next? Proceedings of the European Conference in Computer Vision (ECCV), Amsterdam. Proceedings of Computer Vision and Pattern Recogntion, CVPR 2016. Bainbridge, W.A., Dilks, D., and Oliva, A&#...Khaligh-R...
places.csail.mit.edu
MIT Places Database for Scene Recognition
http://places.csail.mit.edu/index.html
By MIT Computer Science and Artificial Intelligence Laboratory. Scene Parsing Challenge 2016. Is online. Welcome to participate. Is coming at ECCV'16. We release the CNNs trained on Places365 (new Places2 data). With more categories predicted and better performance. Places205-VGG and Places205-GoogLeNet are available to download in the Places CNNs. Register to download data and submit prediction results at here. The leaderboard of Places Database is at here. Sample Code of Unit Segmentation. B Zhou, A...
