Investigating Memorability of Dynamic Media

The Predicting Media Memorability task in MediaEval’20 has some challenging aspects compared to previous years. In this paper we identify the high-dynamic content in videos and dataset of limited size as the core challenges for the task, we propose directions to overcome some of these challenges and we present our initial result in these directions.

[1]  Minh-Triet Tran,et al.  Predicting Media Memorability Using Deep Features with Attention and Recurrent Network , 2019, MediaEval.

[2]  Mats Sjöberg,et al.  The Predicting Media Memorability Task at MediaEval 2019 , 2019, MediaEval.

[3]  Lorenzo Torresani,et al.  Learning Spatiotemporal Features with 3D Convolutional Networks , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[4]  Bogdan Ionescu,et al.  Using Aesthetics and Action Recognition-Based Networks for the Prediction of Media Memorability , 2019, MediaEval.

[5]  Roberto Leyva,et al.  Multimodal Deep Features Fusion for Video Memorability Prediction , 2019, MediaEval.

[6]  Martin Engilberge,et al.  VideoMem: Constructing, Analyzing, Predicting Short-Term and Long-Term Video Memorability , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[7]  Alan F. Smeaton,et al.  Predicting Media Memorability Using Ensemble Models , 2019, MediaEval.

[8]  Antonio Torralba,et al.  Understanding the Intrinsic Memorability of Images , 2011, NIPS.

[9]  Alan F. Smeaton,et al.  Overview of MediaEval 2020 Predicting Media Memorability Task: What Makes a Video Memorable? , 2020, ArXiv.

[10]  Jonathan G. Fiscus,et al.  TRECVID 2019: An evaluation campaign to benchmark Video Activity Detection, Video Captioning and Matching, and Video Search & retrieval , 2019, TRECVID.

[11]  Nicu Sebe,et al.  Increasing Image Memorability with Neural Style Transfer , 2019, ACM Trans. Multim. Comput. Commun. Appl..

[12]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[13]  Jorma Laaksonen,et al.  Combining Textual and Visual Modeling for Predicting Media Memorability , 2019, MediaEval.

[14]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[15]  Aude Oliva,et al.  Multimodal Memorability: Modeling Effects of Semantics and Decay on Video Memorability , 2020, ECCV.

[16]  Bogdan Ionescu,et al.  Computational Understanding of Visual Interestingness Beyond Semantics , 2019, ACM Comput. Surv..