TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

Datasets/SUN

SUN

SUN Database

ImagesIntroduced 2011-08-22

When glancing at a magazine, or browsing the Internet, we are continuously being exposed to photographs. Despite of this overflow of visual information, humans are extremely good at remembering thousands of pictures along with some of their visual details. But not all images are equal in memory. Some stitch to our minds, and other are forgotten. In this paper we focus on the problem of predicting how memorable an image will be. We show that memorability is a stable property of an image that is shared across different viewers. We introduce a database for which we have measured the probability that each picture will be remembered after a single view. We analyze image features and labels that contribute to making an image memorable, and we train a predictor based on global image descriptors. We find that predicting image memorability is a task that can be addressed with current computer vision techniques. Whereas making memorable images is a challenging task in visualization and photography, this work is a first attempt to quantify this useful quality of images.

Benchmarks

Generalized Few-Shot Learning/Per-Class Accuracy (1-shot)Generalized Few-Shot Learning/Per-Class Accuracy (2-shots)Generalized Few-Shot Learning/Per-Class Accuracy (5-shots)Generalized Few-Shot Learning/Per-Class Accuracy (10-shots)Zero-Shot Transfer Image Classification/Accuracy

Related Benchmarks

SUN - 0-Shot/Few-Shot Image Classification/AccuracySUN - 0-Shot/Image Classification/AccuracySUN Attribute/Zero-Shot Learning/Accuracy SeenSUN Attribute/Zero-Shot Learning/Accuracy UnseenSUN Attribute/Zero-Shot Learning/HSUN Attribute/Zero-Shot Learning/Harmonic meanSUN Attribute/Zero-Shot Learning/average top-1 classification accuracySUN RGB-D/16k/AP 0.5SUN RGB-D/16k/AP@0.15 (10 / NYU-37)SUN RGB-D/16k/AP@0.15 (10 / PNet-30)SUN RGB-D/16k/AP@0.15 (NYU-37)SUN RGB-D/2D Classification/AP 0.5SUN RGB-D/2D Classification/AP@0.15 (10 / NYU-37)SUN RGB-D/2D Classification/AP@0.15 (10 / PNet-30)SUN RGB-D/2D Classification/AP@0.15 (NYU-37)SUN RGB-D/2D Object Detection/AP 0.5SUN RGB-D/2D Object Detection/AP@0.15 (10 / NYU-37)SUN RGB-D/2D Object Detection/AP@0.15 (10 / PNet-30)SUN RGB-D/2D Object Detection/AP@0.15 (NYU-37)SUN RGB-D/3D/AP 0.5SUN RGB-D/3D/AP@0.15 (10 / NYU-37)SUN RGB-D/3D/AP@0.15 (10 / PNet-30)SUN RGB-D/3D/AP@0.15 (NYU-37)SUN RGB-D/3D Object Detection/AP@0.15 (10 / NYU-37)SUN RGB-D/3D Object Detection/AP@0.15 (10 / PNet-30)SUN RGB-D/3D Object Detection/AP@0.15 (NYU-37)SUN RGB-D/Object Detection/AP 0.5SUN RGB-D/Object Detection/AP@0.15 (10 / NYU-37)SUN RGB-D/Object Detection/AP@0.15 (10 / PNet-30)SUN RGB-D/Object Detection/AP@0.15 (NYU-37)SUN RGB-D/Room Layout Estimation/Camera PitchSUN RGB-D/Room Layout Estimation/Camera RollSUN RGB-D/Room Layout Estimation/IoUSUN-LT/Few-Shot Image Classification/Long-Tailed AccuracySUN-LT/Few-Shot Image Classification/Per-Class AccuracySUN-LT/Generalized Few-Shot Classification/Long-Tailed AccuracySUN-LT/Generalized Few-Shot Classification/Per-Class AccuracySUN-LT/Generalized Few-Shot Learning/Long-Tailed AccuracySUN-LT/Generalized Few-Shot Learning/Per-Class AccuracySUN-LT/Image Classification/Long-Tailed AccuracySUN-LT/Image Classification/Per-Class AccuracySUN-LT/Long-tail Learning/Long-Tailed AccuracySUN-LT/Long-tail Learning/Per-Class AccuracySUN-Mem/1 Image, 2*2 Stitchi/AP50SUN-Mem/1 Image, 2*2 Stitchi/AUPRCSUN-Mem/1 Image, 2*2 Stitchi/AUROCSUN-Mem/3D/AP50SUN-Mem/3D/AUPRCSUN-Mem/3D/AUROCSUN-Mem/3D Human Pose Estimation/AP50SUN-Mem/3D Human Pose Estimation/AUPRCSUN-Mem/3D Human Pose Estimation/AUROCSUN-Mem/Pose Estimation/AP50SUN-Mem/Pose Estimation/AUPRCSUN-Mem/Pose Estimation/AUROCSUN-RGBD/10-shot image generation/Mean IoUSUN-RGBD/10-shot image generation/Mean IoU (test)SUN-RGBD/10-shot image generation/PQSUN-RGBD/16k/Inference Speed (s)SUN-RGBD/16k/mAP@0.25SUN-RGBD/16k/mAP@0.5SUN-RGBD/2D Classification/Inference Speed (s)SUN-RGBD/2D Classification/mAP@0.25SUN-RGBD/2D Classification/mAP@0.5SUN-RGBD/2D Object Detection/Inference Speed (s)SUN-RGBD/2D Object Detection/mAP@0.25SUN-RGBD/2D Object Detection/mAP@0.5SUN-RGBD/2D Semantic Segmentation/Accuracy (%)SUN-RGBD/3D/Delta < 1.25SUN-RGBD/3D/Delta < 1.25^2SUN-RGBD/3D/Delta < 1.25^3SUN-RGBD/3D/Inference Speed (s)SUN-RGBD/3D/RMSESUN-RGBD/3D/absolute relative errorSUN-RGBD/3D/log 10SUN-RGBD/3D/mAP@0.25SUN-RGBD/3D/mAP@0.5SUN-RGBD/3D Character Animation From A Single Photo/Accuracy (%)SUN-RGBD/3D Object Detection/Inference Speed (s)SUN-RGBD/3D Object Detection/mAP@0.25SUN-RGBD/3D Object Detection/mAP@0.5SUN-RGBD/Animation/Accuracy (%)SUN-RGBD/Depth Estimation/Delta < 1.25SUN-RGBD/Depth Estimation/Delta < 1.25^2SUN-RGBD/Depth Estimation/Delta < 1.25^3SUN-RGBD/Depth Estimation/RMSESUN-RGBD/Depth Estimation/absolute relative errorSUN-RGBD/Depth Estimation/log 10SUN-RGBD/Object Detection/Inference Speed (s)SUN-RGBD/Object Detection/mAP@0.25SUN-RGBD/Object Detection/mAP@0.5SUN-RGBD/Panoptic Segmentation/PQSUN-RGBD/Scene Parsing/Accuracy (%)SUN-RGBD/Scene Segmentation/Mean IoUSUN-RGBD/Semantic Segmentation/Mean IoUSUN-RGBD/Semantic Segmentation/Mean IoU (test)SUN-RGBD/Semantic Segmentation/PQSUN-RGBD val/16k/Inference Speed (s)SUN-RGBD val/16k/MAPSUN-RGBD val/16k/mAP@0.25SUN-RGBD val/16k/mAP@0.5SUN-RGBD val/2D Classification/Inference Speed (s)SUN-RGBD val/2D Classification/MAPSUN-RGBD val/2D Classification/mAP@0.25SUN-RGBD val/2D Classification/mAP@0.5SUN-RGBD val/2D Object Detection/Inference Speed (s)SUN-RGBD val/2D Object Detection/MAPSUN-RGBD val/2D Object Detection/mAP@0.25SUN-RGBD val/2D Object Detection/mAP@0.5SUN-RGBD val/3D/Inference Speed (s)SUN-RGBD val/3D/MAPSUN-RGBD val/3D/mAP@0.25SUN-RGBD val/3D/mAP@0.5SUN-RGBD val/3D Object Detection/Inference Speed (s)SUN-RGBD val/3D Object Detection/mAP@0.25SUN-RGBD val/3D Object Detection/mAP@0.5SUN-RGBD val/Object Detection/Inference Speed (s)SUN-RGBD val/Object Detection/MAPSUN-RGBD val/Object Detection/mAP@0.25SUN-RGBD val/Object Detection/mAP@0.5SUN-RGBD-IS/Instance Segmentation/mask APSUN-SEG-Easy/Medical Image Segmentation/DiceSUN-SEG-Easy/Medical Image Segmentation/IoUSUN-SEG-Easy/Medical Image Segmentation/S measureSUN-SEG-Easy/Medical Image Segmentation/mean E-measureSUN-SEG-Easy/Medical Image Segmentation/mean F-measureSUN-SEG-Easy/Medical Image Segmentation/weighted F-measureSUN-SEG-Easy (Unseen)/Medical Image Segmentation/DiceSUN-SEG-Easy (Unseen)/Medical Image Segmentation/S measureSUN-SEG-Easy (Unseen)/Medical Image Segmentation/SensitivitySUN-SEG-Easy (Unseen)/Medical Image Segmentation/mean E-measureSUN-SEG-Easy (Unseen)/Medical Image Segmentation/mean F-measureSUN-SEG-Easy (Unseen)/Medical Image Segmentation/mean IoUSUN-SEG-Easy (Unseen)/Medical Image Segmentation/weighted F-measureSUN-SEG-Hard/Medical Image Segmentation/DiceSUN-SEG-Hard/Medical Image Segmentation/IoUSUN-SEG-Hard/Medical Image Segmentation/S-MeasureSUN-SEG-Hard/Medical Image Segmentation/mean E-measureSUN-SEG-Hard/Medical Image Segmentation/mean F-measureSUN-SEG-Hard/Medical Image Segmentation/weighted F-measureSUN-SEG-Hard (Unseen)/Medical Image Segmentation/DiceSUN-SEG-Hard (Unseen)/Medical Image Segmentation/S-MeasureSUN-SEG-Hard (Unseen)/Medical Image Segmentation/SensitivitySUN-SEG-Hard (Unseen)/Medical Image Segmentation/mean E-measureSUN-SEG-Hard (Unseen)/Medical Image Segmentation/mean F-measureSUN-SEG-Hard (Unseen)/Medical Image Segmentation/mean IoUSUN-SEG-Hard (Unseen)/Medical Image Segmentation/weighted F-measureSUN360/2D Semantic Segmentation/Median Relighting ErrorSUN360/Scene Parsing/Median Relighting ErrorSUN360/Scene Understanding/Median Relighting ErrorSUN397/2D Semantic Segmentation/AccuracySUN397/3D Character Animation From A Single Photo/AccuracySUN397/Animation/AccuracySUN397/Few-Shot Learning/Harmonic meanSUN397/Fine-Grained Image Classification/AccuracySUN397/Image Classification/AccuracySUN397/Image Clustering/AccuracySUN397/Meta-Learning/Harmonic meanSUN397/Prompt Engineering/Harmonic meanSUN397/Scene Parsing/AccuracySUN397/Zero-Shot Learning/AccuracySun80 - 4x upscaling/16k/PSNRSun80 - 4x upscaling/16k/SSIMSun80 - 4x upscaling/3D Object Super-Resolution/PSNRSun80 - 4x upscaling/3D Object Super-Resolution/SSIMSun80 - 4x upscaling/Image Super-Resolution/PSNRSun80 - 4x upscaling/Image Super-Resolution/SSIMSun80 - 4x upscaling/Super-Resolution/PSNRSun80 - 4x upscaling/Super-Resolution/SSIMSunYs/Medical Image Segmentation/Accuracy (median)SunYs/Pulmorary Vessel Segmentation/Accuracy (median)Sunspot/Time Series Analysis/RMSESunspot/Time Series Prediction/RMSE

Statistics

Papers
31
Benchmarks
5

Links

Tasks

Few-Shot Image ClassificationGeneralized Few-Shot LearningLong-tail learning with class descriptorsZero-Shot Transfer Image Classification