Tasks SotA Datasets Papers Methods Submit About

NJU2K

ImagesIntroduced 2014-01-01

NJU2K is a large RGB-D dataset containing 1,985 image pairs. The stereo images were collected from the Internet and 3D movies, while photographs were taken by a Fuji W3 camera.

Source: Bifurcated Backbone Strategy for RGB-D Salient Object Detection Image Source: Depth saliency based on anisotropic center-surround difference

Benchmarks

16k/S-Measure 16k/Average MAE 16k/max E-Measure 16k/max F-Measure 2D Classification/S-Measure 2D Classification/Average MAE 2D Classification/max E-Measure 2D Classification/max F-Measure 2D Object Detection/S-Measure 2D Object Detection/Average MAE 2D Object Detection/max E-Measure 2D Object Detection/max F-Measure 3D/S-Measure 3D/Average MAE 3D/max E-Measure 3D/max F-Measure Object Detection/S-Measure Object Detection/Average MAE Object Detection/max E-Measure Object Detection/max F-Measure

Statistics

Papers: 52
Benchmarks: 20

Links

Homepage

Tasks

16k 2D Classification 2D Object Detection 3D Object Detection RGB-D Salient Object Detection

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/NJU2K