文献紹介:Selective Feature Compression for Efficient Activity Recognition InferenceToru Tamaki
?
Chunhui Liu, Xinyu Li, Hao Chen, Davide Modolo, Joseph Tighe; Selective Feature Compression for Efficient Activity Recognition Inference, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 13628-13637
https://openaccess.thecvf.com/content/ICCV2021/html/Liu_Selective_Feature_Compression_for_Efficient_Activity_Recognition_Inference_ICCV_2021_paper.html
文献紹介:SegFormer: Simple and Efficient Design for Semantic Segmentation with Tr...Toru Tamaki
?
Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, Ping Luo, SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers, Advances in Neural Information Processing Systems 34 (NeurIPS 2021)
https://proceedings.neurips.cc/paper/2021/hash/64f1f27bf1b4ec22924fd0acb550c235-Abstract.html
https://arxiv.org/abs/2105.15203
論文紹介:Revealing the unseen: Benchmarking video action recognition under occlusionToru Tamaki
?
Shresth Grover, Vibhav Vineet, Yogesh S Rawat, "Revealing the unseen: Benchmarking video action recognition under occlusion" NeurIPS2023
https://openreview.net/forum?id=1jrYSOG7DR
IMAX3: Amazing Dataflow-Centric CGRA and its Applications
I present this slide to all hungry engineers who are tired of CPU, GPU, FPGA, tensor core, AI core, who want some challenging one with no black box inside, and who want to improve by themselves.
文献紹介:Deep Analysis of CNN-Based Spatio-Temporal Representations for Action Re...Toru Tamaki
?
Chun-Fu Richard Chen, Rameswar Panda, Kandan Ramakrishnan, Rogerio Feris, John Cohn, Aude Oliva, Quanfu Fan; Deep Analysis of CNN-Based Spatio-Temporal Representations for Action Recognition, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 6165-6175
https://openaccess.thecvf.com/content/CVPR2021/html/Chen_Deep_Analysis_of_CNN-Based_Spatio-Temporal_Representations_for_Action_Recognition_CVPR_2021_paper.html
文献紹介:Selective Feature Compression for Efficient Activity Recognition InferenceToru Tamaki
?
Chunhui Liu, Xinyu Li, Hao Chen, Davide Modolo, Joseph Tighe; Selective Feature Compression for Efficient Activity Recognition Inference, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 13628-13637
https://openaccess.thecvf.com/content/ICCV2021/html/Liu_Selective_Feature_Compression_for_Efficient_Activity_Recognition_Inference_ICCV_2021_paper.html
文献紹介:SegFormer: Simple and Efficient Design for Semantic Segmentation with Tr...Toru Tamaki
?
Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, Ping Luo, SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers, Advances in Neural Information Processing Systems 34 (NeurIPS 2021)
https://proceedings.neurips.cc/paper/2021/hash/64f1f27bf1b4ec22924fd0acb550c235-Abstract.html
https://arxiv.org/abs/2105.15203
論文紹介:Revealing the unseen: Benchmarking video action recognition under occlusionToru Tamaki
?
Shresth Grover, Vibhav Vineet, Yogesh S Rawat, "Revealing the unseen: Benchmarking video action recognition under occlusion" NeurIPS2023
https://openreview.net/forum?id=1jrYSOG7DR
IMAX3: Amazing Dataflow-Centric CGRA and its Applications
I present this slide to all hungry engineers who are tired of CPU, GPU, FPGA, tensor core, AI core, who want some challenging one with no black box inside, and who want to improve by themselves.
文献紹介:Deep Analysis of CNN-Based Spatio-Temporal Representations for Action Re...Toru Tamaki
?
Chun-Fu Richard Chen, Rameswar Panda, Kandan Ramakrishnan, Rogerio Feris, John Cohn, Aude Oliva, Quanfu Fan; Deep Analysis of CNN-Based Spatio-Temporal Representations for Action Recognition, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 6165-6175
https://openaccess.thecvf.com/content/CVPR2021/html/Chen_Deep_Analysis_of_CNN-Based_Spatio-Temporal_Representations_for_Action_Recognition_CVPR_2021_paper.html
公開URL:https://openaccess.thecvf.com/content/CVPR2024/papers/Li_Generative
_Image_Dynamics_CVPR_2024_paper.pdf
出典:Zhengqi Li, Richard Tucker, Noah Snavely, Aleksander Holynski: Generative Image Dynamics, Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)
概要:自然な物体の動きを学習し、静止画から動画を生成する新しいアプローチを提案しています。実際の映像から抽出した動きのパターンをフーリエ領域でモデル化し、拡散モデルを用いて予測します。単一の画像から、周波数調整された拡散サンプリングプロセスを使用してスペクトル体積を予測し、これを動画全体をカバーする動きのテクスチャに変換します。この手法により、静止画からシームレスにループする動画を作成したり、実際の画像内のオブジェクトとインタラクティブに動きを生成したりすることが可能になります。
【DLゼミ】XFeat: Accelerated Features for Lightweight Image Matchingharmonylab
?
公開URL:https://arxiv.org/pdf/2404.19174
出典:Guilherme Potje, Felipe Cadar, Andre Araujo, Renato Martins, Erickson R. ascimento: XFeat: Accelerated Features for Lightweight Image Matching, Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)
概要:リソース効率に優れた特徴点マッチングのための軽量なアーキテクチャ「XFeat(Accelerated Features)」を提案します。手法は、局所的な特徴点の検出、抽出、マッチングのための畳み込みニューラルネットワークの基本的な設計を再検討します。特に、リソースが限られたデバイス向けに迅速かつ堅牢なアルゴリズムが必要とされるため、解像度を可能な限り高く保ちながら、ネットワークのチャネル数を制限します。さらに、スパース下でのマッチングを選択できる設計となっており、ナビゲーションやARなどのアプリケーションに適しています。XFeatは、高速かつ同等以上の精度を実現し、一般的なラップトップのCPU上でリアルタイムで動作します。
A Study on Decision Support System for Snow Removal Dispatch using Road Surfa...harmonylab
?
This study focuses on addressing the challenges associated with decision-making in winter road snow removal operations, aiming to alleviate the burden on snow removal personnel. Specifically, we propose an approach to develop a system that collects and visualizes information on road snow conditions and weather data to support decision-making by personnel. Additionally, by sharing the collected information, we aim to facilitate the sharing of premonitions about changes in decision-making among snow removal personnel, reducing the need for physical inspections.We have validated the effectiveness of the system and confirmed its efficacy.
DLゼミ: MobileOne: An Improved One millisecond Mobile Backboneharmonylab
?
公開URL:https://openaccess.thecvf.com/content/CVPR2023/html/Vasu_MobileOne_An_Improved_One_Millisecond_Mobile_Backbone_CVPR_2023_paper.html
出典:Vasu, Pavan Kumar Anasosalu, et al.: MobileOne: An Improved One Millisecond Mobile Backbone, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2023)
概要:モバイル端末向けのニューラルネットワークは多くの場合、FLOPsやパラメータ数で最適化されています。しかし、これらの最適化は実際のモバイルデバイスで実行した場合のネットワークの応答時間に相関しない場合があります。我々は昨今のニューラルネットワークの最適化のボトルネックを特定?分析し、その結果をもとにした新たな効率的なバックボーンMobileOneを設計しました。結果はMobileFormerと同等の性能を得ながら、38倍高速であり、最先端の効率性を達成しました。
2. 研究背景
Deep Q-Network(1
Deep LearningをQ学習に適用したもの
? 先行研究
Preferred Networks” Autonomous robot car control
demonstration in CES2016”(2
? 複数ロボットの学習
? 複雑な環境の学習
1)Volodymyr Mnih, Koray Kavukcuoglu, David Silver,at el,
“Human-level control through deep reinforcement learning” Nature, 14236, pp.529—533
2)Preferred Reserch “CES2016でロボットカーのデモを展示してきました”
https://research.preferred.jp/2016/01/ces2016/
複数のRCカーが衝突しないで走行
指定ルートの走行
2