Zilong Guo, Yi Luo, Long Sha, Dongxu Wang, Panqu Wang, Chenyang Xu, Yi Yang
2nd Place Solution for CVPR2024 E2E Challenge: End-to-End Autonomous Driving Using Vision Language Model
https://arxiv.org/abs/2509.02659
2nd Place Solution for CVPR2024 E2E Challenge: End-to-End Autonomous Driving Using Vision Language Model
https://arxiv.org/abs/2509.02659
September 4, 2025 at 8:00 AM
Zilong Guo, Yi Luo, Long Sha, Dongxu Wang, Panqu Wang, Chenyang Xu, Yi Yang
2nd Place Solution for CVPR2024 E2E Challenge: End-to-End Autonomous Driving Using Vision Language Model
https://arxiv.org/abs/2509.02659
2nd Place Solution for CVPR2024 E2E Challenge: End-to-End Autonomous Driving Using Vision Language Model
https://arxiv.org/abs/2509.02659
Zilong Guo, Yi Luo, Long Sha, Dongxu Wang, Panqu Wang, Chenyang Xu, Yi Yang: 2nd Place Solution for CVPR2024 E2E Challenge: End-to-End Autonomous Driving Using Vision Language Model https://arxiv.org/abs/2509.02659 https://arxiv.org/pdf/2509.02659 https://arxiv.org/html/2509.02659
September 4, 2025 at 6:30 AM
Zilong Guo, Yi Luo, Long Sha, Dongxu Wang, Panqu Wang, Chenyang Xu, Yi Yang: 2nd Place Solution for CVPR2024 E2E Challenge: End-to-End Autonomous Driving Using Vision Language Model https://arxiv.org/abs/2509.02659 https://arxiv.org/pdf/2509.02659 https://arxiv.org/html/2509.02659
Nice closing note for my #CVPR2024 lead GC journey: the conference just won the IEEE iCON award for outstanding achievement in conference innovation at IEEE Convene 2025. We had an exceptionally excellent organizing committee last year, and this award is a testament to that!
August 1, 2025 at 3:30 PM
Nice closing note for my #CVPR2024 lead GC journey: the conference just won the IEEE iCON award for outstanding achievement in conference innovation at IEEE Convene 2025. We had an exceptionally excellent organizing committee last year, and this award is a testament to that!
After #CVPR2024, we further investigate beyond-Euclidean computer vision and extend the fundamental task of dimensionality reduction to the largely uncharted Finsler manifolds, with core applications in data analysis and visualisation!
March 25, 2025 at 7:32 AM
After #CVPR2024, we further investigate beyond-Euclidean computer vision and extend the fundamental task of dimensionality reduction to the largely uncharted Finsler manifolds, with core applications in data analysis and visualisation!
Motivation: after Denys exploited issues in our S23DR #CVPR2024 competition metric -- wireframe edit distance (WED), we decided to study it systematically.
We asked 3D modelers, CV people (us)and normal people to rank many wireframes.
Designing the labeling setup is not easy.
2/
We asked 3D modelers, CV people (us)and normal people to rank many wireframes.
Designing the labeling setup is not easy.
2/
March 12, 2025 at 8:29 AM
Motivation: after Denys exploited issues in our S23DR #CVPR2024 competition metric -- wireframe edit distance (WED), we decided to study it systematically.
We asked 3D modelers, CV people (us)and normal people to rank many wireframes.
Designing the labeling setup is not easy.
2/
We asked 3D modelers, CV people (us)and normal people to rank many wireframes.
Designing the labeling setup is not easy.
2/
March 2, 2025 at 7:41 PM
Continual Forgetting for Pre-trained Vision Models (CVPR2024) #DL #AI #ML #DeepLearning #ArtificialIntelligence #MachineLearning #ComputerVision #AutonomousVehicles #Robotics #LLM #VLM #LVLM
https://buff.ly/4h5Lrq9
https://buff.ly/4h5Lrq9
January 25, 2025 at 9:00 PM
Continual Forgetting for Pre-trained Vision Models (CVPR2024) #DL #AI #ML #DeepLearning #ArtificialIntelligence #MachineLearning #ComputerVision #AutonomousVehicles #Robotics #LLM #VLM #LVLM
https://buff.ly/4h5Lrq9
https://buff.ly/4h5Lrq9
🧵 1/3 Many at #CVPR2024 & #ECCV2024 asked what would be next in our workshop series.
We're excited to announce "How to Stand Out in the Crowd?" at #CVPR2025 Nashville - our 4th community-building workshop featuring this incredible speaker lineup!
🔗 sites.google.com/view/standou...
We're excited to announce "How to Stand Out in the Crowd?" at #CVPR2025 Nashville - our 4th community-building workshop featuring this incredible speaker lineup!
🔗 sites.google.com/view/standou...
January 13, 2025 at 4:16 PM
🧵 1/3 Many at #CVPR2024 & #ECCV2024 asked what would be next in our workshop series.
We're excited to announce "How to Stand Out in the Crowd?" at #CVPR2025 Nashville - our 4th community-building workshop featuring this incredible speaker lineup!
🔗 sites.google.com/view/standou...
We're excited to announce "How to Stand Out in the Crowd?" at #CVPR2025 Nashville - our 4th community-building workshop featuring this incredible speaker lineup!
🔗 sites.google.com/view/standou...
Where do we get data for training relighting models? 🤔
We used our good old StyLitGAN from #CVPR2024 to generate diverse training data and filter it to get the top 1000 using CLIP. We combine this with the existing MIT Multi-Illum & Big Time datasets. About ~2500 unique images make our training set
We used our good old StyLitGAN from #CVPR2024 to generate diverse training data and filter it to get the top 1000 using CLIP. We combine this with the existing MIT Multi-Illum & Big Time datasets. About ~2500 unique images make our training set
December 5, 2024 at 3:58 PM
Where do we get data for training relighting models? 🤔
We used our good old StyLitGAN from #CVPR2024 to generate diverse training data and filter it to get the top 1000 using CLIP. We combine this with the existing MIT Multi-Illum & Big Time datasets. About ~2500 unique images make our training set
We used our good old StyLitGAN from #CVPR2024 to generate diverse training data and filter it to get the top 1000 using CLIP. We combine this with the existing MIT Multi-Illum & Big Time datasets. About ~2500 unique images make our training set
ScaLR is making one step toward 3D foundational models! 🙌 The self-supervised features it learns are quite close to fully-supervised 3D semantic segmentation methods. Still more to do, but quite excited about the progress! 🌟 #CVPR2024
📢 Relive the #CVPR2024 poster ScaLR w/ Gilles Puy. It's a Lidar pretrained model distilled from vision foundation models w/o any labels.
💪 Our best ScaLR is publicly available & well suited for semantic tasks w/ few or no labels & still SoTA results on linear probing
www.linkedin.com/posts/andrei...
💪 Our best ScaLR is publicly available & well suited for semantic tasks w/ few or no labels & still SoTA results on linear probing
www.linkedin.com/posts/andrei...
Andrei Bursuc on LinkedIn: #cvpr2024 #cvpr
📢 Re-live the poster presentation of ScaLR at #CVPR2024 by the lead author Gilles Puy.
The ScaLR family consists of our latest Lidar pretrained models…
www.linkedin.com
November 27, 2024 at 10:13 AM
ScaLR is making one step toward 3D foundational models! 🙌 The self-supervised features it learns are quite close to fully-supervised 3D semantic segmentation methods. Still more to do, but quite excited about the progress! 🌟 #CVPR2024
📢 Relive the #CVPR2024 poster ScaLR w/ Gilles Puy. It's a Lidar pretrained model distilled from vision foundation models w/o any labels.
💪 Our best ScaLR is publicly available & well suited for semantic tasks w/ few or no labels & still SoTA results on linear probing
www.linkedin.com/posts/andrei...
💪 Our best ScaLR is publicly available & well suited for semantic tasks w/ few or no labels & still SoTA results on linear probing
www.linkedin.com/posts/andrei...
Andrei Bursuc on LinkedIn: #cvpr2024 #cvpr
📢 Re-live the poster presentation of ScaLR at #CVPR2024 by the lead author Gilles Puy.
The ScaLR family consists of our latest Lidar pretrained models…
www.linkedin.com
November 27, 2024 at 9:22 AM
📢 Relive the #CVPR2024 poster ScaLR w/ Gilles Puy. It's a Lidar pretrained model distilled from vision foundation models w/o any labels.
💪 Our best ScaLR is publicly available & well suited for semantic tasks w/ few or no labels & still SoTA results on linear probing
www.linkedin.com/posts/andrei...
💪 Our best ScaLR is publicly available & well suited for semantic tasks w/ few or no labels & still SoTA results on linear probing
www.linkedin.com/posts/andrei...
Get your method on the #BOP leaderboard and let citations go brrrr.
The deadline of this year's challenge was intentionally put after the #CVPR2024 deadline, so the latest and greatest methods can participate.
The deadline of this year's challenge was intentionally put after the #CVPR2024 deadline, so the latest and greatest methods can participate.
Submitted a 6D Object Pose Estimation method at CVPR? 📝
Show the world that it actually works in practice and join the BOP challenge. 🦾
7 days left to win the BOP 2024 awards in the model-based and model-free tracks. 🏆
Show the world that it actually works in practice and join the BOP challenge. 🦾
7 days left to win the BOP 2024 awards in the model-based and model-free tracks. 🏆
BOP: Benchmark for 6D Object Pose Estimation
bop.felk.cvut.cz
November 22, 2024 at 7:37 PM
ICYMI our PointBeV #CVPR2024 poster here's a quick talk by lead author Loïck Chambon.
It brings a change of paradigm in multi-camera bird's-eye-view (BeV) segmentation via a flexible mechanism to produce sparse BeV points that can adapt to situation, task, compute
www.linkedin.com/posts/andrei...
It brings a change of paradigm in multi-camera bird's-eye-view (BeV) segmentation via a flexible mechanism to produce sparse BeV points that can adapt to situation, task, compute
www.linkedin.com/posts/andrei...
Andrei Bursuc on LinkedIn: #cvpr2024 #cvpr
In case you missed our PointBeV poster at #CVPR2024 here's a quick presentation by the lead author Loïck C..
PointBEV brings a change of paradigm in…
www.linkedin.com
November 22, 2024 at 11:18 AM
ICYMI our PointBeV #CVPR2024 poster here's a quick talk by lead author Loïck Chambon.
It brings a change of paradigm in multi-camera bird's-eye-view (BeV) segmentation via a flexible mechanism to produce sparse BeV points that can adapt to situation, task, compute
www.linkedin.com/posts/andrei...
It brings a change of paradigm in multi-camera bird's-eye-view (BeV) segmentation via a flexible mechanism to produce sparse BeV points that can adapt to situation, task, compute
www.linkedin.com/posts/andrei...
Nice CVPR pump up video from the IEEE Computer Society highlighting #CVPR2024:
www.youtube.com/watch?v=8B-L...
www.youtube.com/watch?v=8B-L...
CVPR 2024 Recap and Highlights
YouTube video by IEEEComputerSociety
www.youtube.com
November 21, 2024 at 1:46 AM
Nice CVPR pump up video from the IEEE Computer Society highlighting #CVPR2024:
www.youtube.com/watch?v=8B-L...
www.youtube.com/watch?v=8B-L...
One more for @alfcnz.bsky.social. What do you think about this poster? The backstory is #CVPR2024 lost their poster 😱
November 19, 2024 at 2:43 AM
One more for @alfcnz.bsky.social. What do you think about this poster? The backstory is #CVPR2024 lost their poster 😱
Asra Aslam, Sachini Herath, Ziqi Huang, Estefania Talavera, Deblina Bhattacharjee, Himangi Mittal, Vanessa Staderini, Mengwei Ren, Azade Farshad
WiCV@CVPR2024: The Thirteenth Women In Computer Vision Workshop at the Annual CVPR Conference
https://arxiv.org/abs/2411.02445
WiCV@CVPR2024: The Thirteenth Women In Computer Vision Workshop at the Annual CVPR Conference
https://arxiv.org/abs/2411.02445
November 6, 2024 at 5:01 AM
Asra Aslam, Sachini Herath, Ziqi Huang, Estefania Talavera, Deblina Bhattacharjee, Himangi Mittal, Vanessa Staderini, Mengwei Ren, Azade Farshad
WiCV@CVPR2024: The Thirteenth Women In Computer Vision Workshop at the Annual CVPR Conference
https://arxiv.org/abs/2411.02445
WiCV@CVPR2024: The Thirteenth Women In Computer Vision Workshop at the Annual CVPR Conference
https://arxiv.org/abs/2411.02445
JDLA主催「CVPR2024技術報告会」発表資料 | Morpho Tech Blog
JDLA主催「CVPR2024技術報告会」発表資料 - Morpho Tech Blog
先日、日本ディープラーニング協会主催（JDLA）の「CVPR2024技術報告会」にてモルフォの技術者が登壇いたしました。 www.morphoinc.com 昨年に引き続きまして、CVPRという国際学会の重要性や、今年のトレンドの分析、モルフォの技術者が注目した分野や論文について紹介しました。 当日の発表資料を共有させていただきます。 JDLA主催CVPR2024技術報告会 ー コンピュータビジョン技術の最前線 ー by @Morpho 発表動画については是非以下のリンクからご視聴ください。 https://www.youtube.com/live/uic0Z-Gk7ac
techblog.morphoinc.com
October 2, 2024 at 1:16 PM
JDLA主催「CVPR2024技術報告会」発表資料 | Morpho Tech Blog
JDLA主催「CVPR2024技術報告会」発表資料 | Morpho Tech Blog
JDLA主催「CVPR2024技術報告会」発表資料 - Morpho Tech Blog
先日、日本ディープラーニング協会主催（JDLA）の「CVPR2024技術報告会」にてモルフォの技術者が登壇いたしました。 www.morphoinc.com 昨年に引き続きまして、CVPRという国際学会の重要性や、今年のトレンドの分析、モルフォの技術者が注目した分野や論文について紹介しました。 当日の発表資料を共有させていただきます。 JDLA主催CVPR2024技術報告会 ー コンピュータビジョン技術の最前線 ー by @Morpho 発表動画については是非以下のリンクからご視聴ください。 https://www.youtube.com/live/uic0Z-Gk7ac
techblog.morphoinc.com
September 23, 2024 at 6:09 PM
JDLA主催「CVPR2024技術報告会」発表資料 | Morpho Tech Blog
CVPR2024 で "YolOOD: Utilizing Object Detection Concepts for Multi-Label Out-of-Distribution Detection" について発表しました | fltech - 富士通研究所の技術ブログ
CVPR2024 で "YolOOD: Utilizing Object Detection Concepts for Multi-Label Out-of-Distribution Detection" について発表しました - fltech - 富士通研究所の技術ブログ
こんにちは、人工知能研究所の江田です。富士通では、AIの安全な利用を可能にする技術の開発を行っています。 この度研究成果の一つを、機械学習・コンピュータビジョンの最難関会議の一つであるCVPRにて発表しましたので、その内容を紹介します。
blog.fltech.dev
August 11, 2024 at 6:10 PM
CVPR2024 で "YolOOD: Utilizing Object Detection Concepts for Multi-Label Out-of-Distribution Detection" について発表しました | fltech - 富士通研究所の技術ブログ
画像認識世界最高峰の学会、CVPR2024のコンペ「Ego4D EgoSchema Challenge」でパナソニック コネクトが世界で... - パナソニックグループ https://prtimes.jp/main/html/rd/p/000005803.000003442.html
July 16, 2024 at 2:52 AM
画像認識世界最高峰の学会、CVPR2024のコンペ「Ego4D EgoSchema Challenge」でパナソニック コネクトが世界で... - パナソニックグループ https://prtimes.jp/main/html/rd/p/000005803.000003442.html
ZOZOの新卒1年目MLエンジニアが行くCVPR 2024 参加レポート - ZOZO TECH BLOG
https://techblog.zozo.com/entry/cvpr2024-report
https://techblog.zozo.com/entry/cvpr2024-report
ZOZOの新卒1年目MLエンジニアが行くCVPR 2024 参加レポート - ZOZO TECH BLOG
6/17-6/21にシアトルで開催されたコンピュータビジョン・パターン認識分野の国際会議CVPR 2024の参加レポートです。
techblog.zozo.com
July 11, 2024 at 3:04 AM
ZOZOの新卒1年目MLエンジニアが行くCVPR 2024 参加レポート - ZOZO TECH BLOG
https://techblog.zozo.com/entry/cvpr2024-report
https://techblog.zozo.com/entry/cvpr2024-report
Proud to share our new #CVPR2024 paper! Discover how RIOS and ANU improve NeRF by modeling transparent objects with our innovative neural surface refinement technique. #NeRF #AI #3DVision
Project page
tnsr.rios.ai
Project page
tnsr.rios.ai
July 4, 2024 at 9:49 PM
Proud to share our new #CVPR2024 paper! Discover how RIOS and ANU improve NeRF by modeling transparent objects with our innovative neural surface refinement technique. #NeRF #AI #3DVision
Project page
tnsr.rios.ai
Project page
tnsr.rios.ai
今日のZennトレンド
第3世代の自動運転@CVPR2024
この記事は、CVPR 2024 で発表された自動運転に関する最新研究を紹介しています。
特に、LLM や VLM といった基盤モデルを活用した第3世代の自動運転技術に焦点を当て、具体的な論文とその内容、成果などを解説しています。
さらに、自動運転データセットの進化や、カメラ画像のみで運転を実現した CarLLaVA のような革新的な研究成果も紹介しています。
第3世代の自動運転@CVPR2024
この記事は、CVPR 2024 で発表された自動運転に関する最新研究を紹介しています。
特に、LLM や VLM といった基盤モデルを活用した第3世代の自動運転技術に焦点を当て、具体的な論文とその内容、成果などを解説しています。
さらに、自動運転データセットの進化や、カメラ画像のみで運転を実現した CarLLaVA のような革新的な研究成果も紹介しています。
第3世代の自動運転@CVPR2024
はじめにTuring 生成AIチームの佐々木 (kento_sasaki1)です。生成AIチームでは、完全自動運転の実現に向けてマルチモーダル基盤モデルの開発に取り組んでいます。先日、6月17日から6月21日にシアトルで開催されたコンピュータビジョン・機械学習系のトップカンファレンスCVPR 2024に参加し、Vision Language Model (VLM)のワークショップThe 3rd
zenn.dev
July 1, 2024 at 9:16 PM
今日のZennトレンド
第3世代の自動運転@CVPR2024
この記事は、CVPR 2024 で発表された自動運転に関する最新研究を紹介しています。
特に、LLM や VLM といった基盤モデルを活用した第3世代の自動運転技術に焦点を当て、具体的な論文とその内容、成果などを解説しています。
さらに、自動運転データセットの進化や、カメラ画像のみで運転を実現した CarLLaVA のような革新的な研究成果も紹介しています。
第3世代の自動運転@CVPR2024
この記事は、CVPR 2024 で発表された自動運転に関する最新研究を紹介しています。
特に、LLM や VLM といった基盤モデルを活用した第3世代の自動運転技術に焦点を当て、具体的な論文とその内容、成果などを解説しています。
さらに、自動運転データセットの進化や、カメラ画像のみで運転を実現した CarLLaVA のような革新的な研究成果も紹介しています。