3 episodes

A podcast by researchers for researchers. This podcast aims to be a new medium for disseminating research. In each episode I talk to the main author of an academic paper in the field of computer vision, machine learning, artificial intelligence, graphics and everything in between. Each episode is structured like a paper and includes a TL;DR (abstract), related work, approach, results, conclusions and a future work section. It also includes the bonus "what did reviewer 2 say" section where authors share their experience in the peer review process. Enjoy!

Talking Papers Podcast Itzik Ben-Shabat

    • Technology
    • 5.0 โ€ข 4 Ratings

A podcast by researchers for researchers. This podcast aims to be a new medium for disseminating research. In each episode I talk to the main author of an academic paper in the field of computer vision, machine learning, artificial intelligence, graphics and everything in between. Each episode is structured like a paper and includes a TL;DR (abstract), related work, approach, results, conclusions and a future work section. It also includes the bonus "what did reviewer 2 say" section where authors share their experience in the peer review process. Enjoy!

    Jing Zhang - UC-Net

    Jing Zhang - UC-Net

    ๐Ÿ’ปSUBSCRIBE AND FOLLOW:
    ๐ŸŽงSubscribe on your favourite podcast app:ย  https://talking.papers.podcast.itzikbs.com
    ๐Ÿ“งSubscribe to our mailing list: http://eepurl.com/hRznqb
    ๐ŸฆFollow us on Twitter: https://twitter.com/talking_papers
    ๐ŸŽฅYouTube Channel: https://bit.ly/3eQOgwP

    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 Barnes


    CODE:
    ๐Ÿ’ปhttps://github.com/JingZhang617/UCNet


    ABSTRACT:
    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.

    RELATED PAPERS:
    ๐Ÿ“šA probabilistic u-net for segmentation of ambiguous images
    ๐Ÿ“šLearning structured output representation using deep conditional generative models

    CONTACT:
    -----------------
    If you would like to be a guest, sponsor or just share your thoughts, feel free to reach out via email: talking.papers.podcast@gmail.com

    TIME STAMPS
    -----------------------
    00:00 | ย 
    00:02 |ย  Intro
    00:31 |ย  The Authors
    01:07 |ย  Abstract / TLDR
    02:41 |ย  Motivation
    07:18 |ย  Related Work
    09:20 |ย  Approach
    18:32 |ย  Results
    24:04 |ย  Conclusions and future work
    25:42 |ย  What did reviewer 2 say?
    29:49 |ย  Outro

    #talkingpapers #CVPR2020 #RGBDSaliency
    #machinelearning #deeplearning #AI #neuralnetworks #research #computervision #artificialintelligence

    • 30 min
    Dylan Campbell - Deep Declarative Networks

    Dylan Campbell - Deep Declarative Networks

    ๐Ÿ’ปSUBSCRIBE AND FOLLOW:
    ๐ŸŽงSubscribe on your favourite podcast app:ย  https://talking.papers.podcast.itzikbs.com
    ๐Ÿ“งSubscribe to our mailing list: http://eepurl.com/hRznqb
    ๐ŸฆFollow us on Twitter: https://twitter.com/talking_papers
    ๐ŸŽฅYouTube Channel: https://bit.ly/3eQOgwP

    PAPER TITLE:
    "Deep Declarative Networks: a new hope"

    AUTHORS:
    Stephen Gould, Richard Hartley, Dylan Campbell

    TUTORIALS AND WORKSHOPS:
    ECCV 2020 Tutorial
    CVPR 2020 Workshop

    CODE:
    ๐Ÿ’ปCodebase
    ๐Ÿ’ปJupiter notebooks

    PAPER:
    "Deep Declarative Networks: a new hope" Preprint
    "Deep Declarative Networks"

    ABSTRACT:
    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.

    RELATED PAPERS:
    ๐Ÿ“š"On differentiating parameterized argmin and argmax problems with application to bi-level optimization"
    ๐Ÿ“š"OptNet: Differentiable Optimization as a Layer in Neural Networks" :ย 

    CONTACT:
    -----------------
    If you would like to be a guest, sponsor or just share your thoughts, feel free to reach out via email: talking.papers.podcast@gmail.com

    #talkingpapers #TPAMI2021 #deepdeclarativenetworks
    #machinelearning #deeplearning #AI #neuralnetworks #research #computervision #artificialintelligenceย 

    Recorded on March, 31th 2021.

    • 29 min
    Cristian Rodriguez-Opazo - DORi

    Cristian Rodriguez-Opazo - DORi

    Paper title:
    "DORi: Discovering Object Relationships for Moment Localization of a Natural Language Query in a Video"

    Authors:ย  Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Basura Fernando, Hongdong Li, Stephen Gould

    Abstract:
    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 approach

    RESOURCES
    -----------------
    Cristian's page: https://crodriguezo.github.io/

    Code:
    https://github.com/crodriguezo/DORi

    Related papers:
    "Proposal free temporal moment localization" : https://bit.ly/3EX1qCM
    "Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs" :ย  https://bit.ly/3zt4aXA

    Subscribe to the podcast: ย 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/3eQOgwP

    CONTACT:
    -----------------
    If you would like to be a guest, sponsor or just share your thoughts, feel free to reach out via email: talking.papers.podcast@gmail.com

    Recorded on March, 26th 2021.

    • 27 min

Customer Reviews

5.0 out of 5
4 Ratings

4 Ratings

Top Podcasts In Technology

ืฆืจื•ืช ื‘ื”ื™ื™ื˜ืง
Startup for Startup โšก by monday.com
ืจื•ืŸ ื”ื’ืคื ื™, ืจื– ืžื™ืฉื•ืจื™, ืืžื™ืจ ื”ื’ืคื ื™
ืจืฉืช ืขื•ืฉื™ื ื”ื™ืกื˜ื•ืจื™ื”
ืจืฉืช ืขื•ืฉื™ื ื”ื™ืกื˜ื•ืจื™ื”
ืชื•ืžื™ ื‘ืจืื‘ ื•ื’ื™ื ืงืฆื•ื‘ื™ืฅืณ

You Might Also Like

ื ื‘ื•ืช ื•ื•ืœืง ื•ืื‘ื™ื‘ ืคืจื ืงืœ
ื›ืœื›ืœื™ืกื˜