Xiang Li

Assistant Professor at University of Reading

[Xiang Li @lix709]

RT @Tianjinhuang1: 🚀 Excited to launch our REOBench — the first comprehensive benchmark for evaluating the robustness of Earth Observation…

[Habib Slim @habib__slim]

📢 We have extended our archival papers submission deadline to March 24th!
If you have any 3D project fresh-off-the-hook, consider submitting to our workshop 🧐

https://t.co/9pqAjFm3HR
@CVPR #CVPR2024

[Habib Slim @habib__slim]

Join us for the Workshop on Compositional 3D Vision (C3DV) #CVPR2024 @CVPR

🏆 Challenges: https://t.co/Z8z71q5PpO
📢 Call for Papers: https://t.co/3qBGZ2qIKe

C3DV will host two challenges this year, and an amazing set of speakers!

🧵👇

[Jun Garvin Chen @garvinchen2]

🚀Excited to share our MiniGPT-v2.
It can perform many complex vision-language and visual grounding  tasks with simple interaction

🔗Demo & Project: https://t.co/lZk9F40sHO

@tikgiau @xiaoqian_shen @lix709 @zechunliu @PengchuanZ  Raghuraman @vikasc @YoungXiong1 @moElhoseiny

[Mohamed Elhoseiny @moElhoseiny]

@elluba kicks off the second day of the SAAI AI Art History symposium.

Livestream:
https://t.co/5CbeXKSXUC

Program: https://t.co/vVeY1cb5Ie

[Habib Slim @habib__slim]

Thrilled to announce the release of 3DCoMPaT++: a richly annotated, multimodal 2D/3D dataset of more than 10 million stylized 3D shapes!🎉

🏆Challenge @CVPR 2023: https://t.co/BxX4x9q1K8
📚Doc: https://t.co/yRiLGduuYC
💻Code: https://t.co/l8nyyXn5Y9

🧵👇

[Deyao Zhu @tikgiau]

🚀 Excited to share MiniGPT-4, an open-sourced model performing complex vision-language tasks like GPT-4!

✍️ Write poems for photos
🔍 Pinpoint problems & offers solutions
🌐 Draft ➡️ Website
and more!

🔗 @Gradio Demo & Project: https://t.co/m3D0sZ6pzO

[Jun Garvin Chen @garvinchen2]

We are excited to share our new work, Video ChatCaptioner, which can generate the enriched video spatiotemporal description through the conversation between ChatGPT and BLIP-2.

Preprint: https://t.co/UE5ZX7E0FA
Code: https://t.co/WCML08clVh

@tikgiau @KAUSTVisionCAIR

[AK @_akhaliq]

SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections

abs: https://t.co/ysWVHyrGiV
project page: https://t.co/oCvEqSLEEy

[Mohamed Elhoseiny @moElhoseiny]

@CVPR accepted the paper (code released).
MoStGAN-V: Video Generation with Temporal Motion Styles
@xiaoqian_shen, Xiang Li, Mohamed Elhoseiny

paper: https://t.co/DFeNbXNfZH

Website,Code,Videos: https://t.co/IvANemJDzx

Congrats, @xiaoqian_shen on her first CVPR paper!