2020/10/10に開催された第4回全日本コンピュータビジョン勉強会「人に関する認識・理解論文読み会」発表資料です。
以下の2本を読みました
Harmonious Attention Network for Person Re-identification. (CVPR2018)
Weekly Supervised Person Re-Identification (CVPR2019)
Paper reading - Dropout as a Bayesian Approximation: Representing Model Uncer...Akisato Kimura
Introducing the paper "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning" presented in ICML2016 (in Japanese).
Updated version of https://www.slideshare.net/akisatokimura/paper-reading-dropout-as-a-bayesian-approximation-representing-model-uncertainty-in-deep-learning
Paper reading - Dropout as a Bayesian Approximation: Representing Model Uncer...Akisato Kimura
A stale version, please check https://www.slideshare.net/akisatokimura/paper-reading-dropout-as-a-bayesian-approximation-representing-model-uncertainty-in-deep-learning-166237519 for a new version.
Introducing the paper "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning" presented in ICML2016 (in Japanese).
NIPS2015 reading - Learning visual biases from human imaginationAkisato Kimura
1) The document discusses a paper on improving visual recognition systems by leveraging human visual biases and generating images from random features.
2) It describes estimating visual biases from human psychophysics experiments, then using those biases to reconstruct images from random features. The reconstructed images can then be used to train machine learning models.
3) The document outlines experiments showing that incorporating estimated human visual biases into machine learning models, such as SVMs, can help improve visual recognition performance compared to models trained without biases.
CVPR2015 reading "Global refinement of random forest"Akisato Kimura
- A method is presented for refining a pre-trained random forest by optimizing the leaf weights while keeping the tree structures fixed.
- This reformulates the random forest as a linear classification/regression problem where samples are represented by sparse indicator vectors.
- The optimization can be performed efficiently and the refined forest has comparable or better accuracy than the original forest, but with significantly fewer trees/nodes.
- Experiments on classification and regression datasets demonstrate the proposed method outperforms other random forest techniques while accelerating training and testing.
Computational models of human visual attention driven by auditory cuesAkisato Kimura
This document summarizes a presentation on computational models of human visual attention driven by auditory cues. It discusses how auditory information can modulate visual attention by selecting visual features that are synchronized with detected auditory events. The proposed model uses Bayesian surprise to detect transient events in visual and auditory streams separately, then correlates the two to select synchronized visual features. An evaluation of the model on video clips found it outperformed baseline models at predicting eye movements.
Brief description of the paper "Large-scale visual sentiment ontology and detectors using adjective noun pairs" presented in ACM Multimedia 2013 as a full paper.
Briefly reviews International Conference on Weblogs and Social Media (ICWSM12) from my perspective.
The latter part written in Japanese, sorry for that.
2020/10/10に開催された第4回全日本コンピュータビジョン勉強会「人に関する認識・理解論文読み会」発表資料です。
以下の2本を読みました
Harmonious Attention Network for Person Re-identification. (CVPR2018)
Weekly Supervised Person Re-Identification (CVPR2019)
Paper reading - Dropout as a Bayesian Approximation: Representing Model Uncer...Akisato Kimura
Introducing the paper "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning" presented in ICML2016 (in Japanese).
Updated version of https://www.slideshare.net/akisatokimura/paper-reading-dropout-as-a-bayesian-approximation-representing-model-uncertainty-in-deep-learning
Paper reading - Dropout as a Bayesian Approximation: Representing Model Uncer...Akisato Kimura
A stale version, please check https://www.slideshare.net/akisatokimura/paper-reading-dropout-as-a-bayesian-approximation-representing-model-uncertainty-in-deep-learning-166237519 for a new version.
Introducing the paper "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning" presented in ICML2016 (in Japanese).
NIPS2015 reading - Learning visual biases from human imaginationAkisato Kimura
1) The document discusses a paper on improving visual recognition systems by leveraging human visual biases and generating images from random features.
2) It describes estimating visual biases from human psychophysics experiments, then using those biases to reconstruct images from random features. The reconstructed images can then be used to train machine learning models.
3) The document outlines experiments showing that incorporating estimated human visual biases into machine learning models, such as SVMs, can help improve visual recognition performance compared to models trained without biases.
CVPR2015 reading "Global refinement of random forest"Akisato Kimura
- A method is presented for refining a pre-trained random forest by optimizing the leaf weights while keeping the tree structures fixed.
- This reformulates the random forest as a linear classification/regression problem where samples are represented by sparse indicator vectors.
- The optimization can be performed efficiently and the refined forest has comparable or better accuracy than the original forest, but with significantly fewer trees/nodes.
- Experiments on classification and regression datasets demonstrate the proposed method outperforms other random forest techniques while accelerating training and testing.
Computational models of human visual attention driven by auditory cuesAkisato Kimura
This document summarizes a presentation on computational models of human visual attention driven by auditory cues. It discusses how auditory information can modulate visual attention by selecting visual features that are synchronized with detected auditory events. The proposed model uses Bayesian surprise to detect transient events in visual and auditory streams separately, then correlates the two to select synchronized visual features. An evaluation of the model on video clips found it outperformed baseline models at predicting eye movements.
Brief description of the paper "Large-scale visual sentiment ontology and detectors using adjective noun pairs" presented in ACM Multimedia 2013 as a full paper.
Briefly reviews International Conference on Weblogs and Social Media (ICWSM12) from my perspective.
The latter part written in Japanese, sorry for that.
Generating Automatic Feedback on UI Mockups with Large Language Models
CVPR2011祭り 発表スライド
1. CVPR2011 Paper Digest
(1) Interactive building a discriminative
vocabulary of nameable attributes
(2) Recognition using visual phrases
Akisato Kimura @ NTT CS Labs
Twitter ID: @_akisato
2. なぜこの2本を選んだのか?
「画像を理解する」をどう問題に落とす?
物体認識…? Person
Horse
[ Full description ]
A woman wearing a blue cloth and gray tights is riding on a galloping
white horse at a beautiful sandy beach under a clear sky.
物体認識をしただけでは,
実は何も理解できていない!
(物体だけを認識する一般物体認識の終焉)
2 CVPR2011祭り (July 31, 2011)
3. 何が足りないのか? (1)
物体などの属性が足りない
でも画像だけで Sky: clear Person: female
全部できる気がしない Horse: white
[ Full description ] Beach: beautiful, sandy
A woman wearing a blue cloth and gray tights is riding on a galloping
white horse at a beautiful sandy beach under a clear sky.
第1論文の主題: 属性辞書をインタラクティブに学習
3 CVPR2011祭り (July 31, 2011)
4. 何が足りないのか? (2)
物体間の関係性が足りない
A person is wearing clothes.
[ Full description ] A person is riding on a horse.
A woman wearing a blue cloth and gray tights is riding on a white horse
at a beautiful sandy beach under a clear sky.
第2論文の主題: 物体とその関係性をクラスと見なす認識
4 CVPR2011祭り (July 31, 2011)
5. Interactively building a
discriminative vocabulary of
nameable attributes
D. Parikh @ Toyota Technological Institute, Chicago
K. Grauman @ University of Texas at Austin
14. Recognition
using visual phrases
M.A. Sadeghi @ Institute for Research in Fundamental Science
A. Farhadi @ University of Illinois at Urbana-Champaign