PAPER TITLE:"UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders"AUTHORS:Jing Zhang, Deng-Ping Fan, Yuchao Dai, Saeed Anwar, Fatemeh Sadat Saleh, Tong Zhang, Nick BarnesABSTRACT:In this paper, we propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection methods treat the saliency detection task as a point estimation problem, and produce a single saliency map following a deterministic learning pipeline. Inspired by the saliency data labeling process, we propose probabilistic RGB-D saliency detection network via conditional variational autoencoders to model human annotation uncertainty and generate multiple saliency maps for each input image by sampling in the latent space. With the proposed saliency consensus process, we are able to generate an accurate saliency map based on these multiple predictions. Quantitative and qualitative evaluations on six challenging benchmark datasets against 18 competing algorithms demonstrate the effectiveness of our approach in learning the distribution of saliency maps, leading to a new state-of-the-art in RGB-D saliency detection.💻SUBSCRIBE AND FOLLOW:🎧Subscribe on your favourite podcast app:  https://talking.papers.podcast.itzikbs.com📧Subscribe to our mailing list: http://eepurl.com/hRznqb🐦Follow us on Twitter: https://twitter.com/talking_papers🎥YouTube Channel: https://bit.ly/3eQOgwPCODE:💻https://github.com/JingZhang617/UCNetRELATED PAPERS:📚A probabilistic u-net for segmentation of ambiguous images 📚Learning structured output representation using deep conditional generative modelsCONTACT:-----------------If you would like to be a guest, sponsor or just share your thoughts, feel free to reach out via email: [email protected] STAMPS-----------------------00:00 |  00:02 |  Intro00:31 |  The Authors01:07 |  Abstract / TLDR02:41 |  Motivation07:18 |  Related Work09:20 |  Approach18:32 |  Results24:04 |  Conclusions and future work25:42 |  What did reviewer 2 say?29:49 |  Outro#talkingpapers #CVPR2020 #RGBDSaliency#machinelearning #deeplearning #AI #neuralnetworks #research #computervision #artificialintelligence

PAPER TITLE:"Deep Declarative Networks: a new hope"AUTHORS:Stephen Gould, Richard Hartley, Dylan CampbellABSTRACT:We explore a new class of end-to-end learnable models wherein data processing nodes (or network layers) are defined in terms of desired behaviour rather than an explicit forward function. Specifically, the forward function is implicitly defined as the solution to a mathematical optimization problem. Consistent with nomenclature in the programming languages community, we name these models deep declarative networks. Importantly, we show that the class of deep declarative networks subsumes current deep learning models. Moreover, invoking the implicit function theorem, we show how gradients can be back-propagated through many declaratively defined data processing nodes thereby enabling end-to-end learning. We show how these declarative processing nodes can be implemented in the popular PyTorch deep learning software library allowing declarative and imperative nodes to co-exist within the same network. We also provide numerous insights and illustrative examples of declarative nodes and demonstrate their application for image and point cloud classification tasks.💻SUBSCRIBE AND FOLLOW:🎧Subscribe on your favourite podcast app:  https://talking.papers.podcast.itzikbs.com📧Subscribe to our mailing list: http://eepurl.com/hRznqb🐦Follow us on Twitter: https://twitter.com/talking_papers🎥YouTube Channel: https://bit.ly/3eQOgwPTUTORIALS AND WORKSHOPS:ECCV 2020 Tutorial CVPR 2020 WorkshopCODE:💻Codebase 💻Jupiter notebooksPAPER: "Deep Declarative Networks: a new hope" Preprint"Deep Declarative Networks"RELATED PAPERS:📚"On differentiating parameterized argmin and argmax problems with application to bi-level optimization" 📚"OptNet: Differentiable Optimization as a Layer in Neural Networks" : CONTACT:-----------------If you would like to be a guest, sponsor or just share your thoughts, feel free to reach out via email: [email protected]#talkingpapers #TPAMI2021 #deepdeclarativenetworks#machinelearning #deeplearning #AI #neuralnetworks #research #computervision #artificialintelligence Recorded on March, 31th 2021.

Paper title: "DORi: Discovering Object Relationships for Moment Localization of a Natural Language Query in a Video"Authors:  Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Basura Fernando, Hongdong Li, Stephen GouldAbstract: This paper studies the task of temporal moment localization in a long untrimmed video using natural language query. Given a query sentence, the goal is to determine the start and end of the relevant segment within the video. Our key innovation is to learn a video feature embedding through a language-conditioned message-passing algorithm suitable for temporal moment localization which captures the relationships between humans, objects and activities in the video. These relationships are obtained by a spatial subgraph that contextualized the scene representation using detected objects and human features. Moreover, a temporal sub-graph captures the activities within the video through time. Our method is evaluated on three standard benchmark datasets, and we also introduce YouCook II as a new benchmark for this task. Experiments show our method outperforms state-of-the-art methods on these datasets, confirming the effectiveness of our approachRESOURCES-----------------Cristian's page: https://crodriguezo.github.io/Code: https://github.com/crodriguezo/DORiRelated papers:"Proposal free temporal moment localization" : https://bit.ly/3EX1qCM"Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs" :  https://bit.ly/3zt4aXASubscribe to the podcast:  https://talking.papers.podcast.itzikbs.comSubscribe to our mailing list: http://eepurl.com/hRznqbFollow us on Twitter: https://twitter.com/talking_papersYouTube Channel: https://bit.ly/3eQOgwPCONTACT:-----------------If you would like to be a guest, sponsor or just share your thoughts, feel free to reach out via email: [email protected] on March, 26th 2021.