Hot off the press: the #WACV2024 proceedings is out! openaccess.thecvf.com/WACV2024 openaccess.thecvf.com/WACV2024_works…

Jens Jens Parslov and Erik Erik are ready to explain you how we deal with damage assessment in images by synthetically damaging cars #WACV2024 WACV

If you are interested in image labeling or video segmentation, Thanos Thanos Delatolas is presenting his EVA-VOS work at poster #73 #WACV2024 WACV

DTU team 🇩🇰 DTU Compute DTU at #WACV2024 🏝️ Kudos to the organizers for an amazing and very well-organized event WACV

Relieved and proud of my PhD defense !! A big thanks to the jury and it was a pleasure working under the supervision of Marc-Olivier Timsit, MD, PhD Maria Vakalopoulou Vicky Kalogeiton.

Great start for D3A 1.0!🤩500+ professionals unite for two days of inspiration on AI, data science and digitalization at Hotel Nyborg Strand. Keynote by prof. Mor Naaman highlights AI’s impact on human communication. Stay tuned for more insights! #D3A

Jens Jens Parslov is now on stage at the synthetic data generation workshop of #D3A 1.0 presenting our work on damage assessment #CrashCar101 @DataScienceDK Pioneer Centre for AI Project page: crashcar.compute.dtu.dk

Are you interested in video generation? Come intern with Xiuye Gu, Alireza Fathi and me Google AI 🇺🇸! 📨 CV + brief intro to: [email protected] 👀 Preferably PhD candidates with papers in computer vision 🗺️ Candidates from underrepresented groups, do apply!

🔍New Publication!📚Comparing our deep reinforcement learning approach with convolutional autoencoders for detecting inner ear malformations on CT, we've enhanced detection accuracy by 11.2%! Read more: doi.org/10.1016/j.comp… #MedicalImaging #DeepLearning #AnomalyDetection 🧠👂

(1) Exciting news! Our paper SPOT is selected as a Highlight at #CVPR2024, achieving a notable rate of 2.8% (324 out of 11532 submissions). Paper: arxiv.org/abs/2312.00648 Code: github.com/gkakogeorgiou/… Discover how SPOT enhances unsupervised object-centric learning. 👇

📢 We have an open PostDoc position at DTU Compute in Copenhagen in the area of computer vision with deep learning for material and computational design in collaboration with the Royal Danish Academy Det Kongelige Akademi: efzu.fa.em2.oraclecloud.com/hcmUI/Candidat… Deadline: 15 May 2024

Classifier-free guidance has been crucial in recent advancements in content generation, trading diversity for fidelity. However, can you get a better deal in this trade-off? With a simple modification, you can get more diversity while keeping a higher level of details!

🎉 Exciting news! Our paper "Collaborative Foundation Models for Domain Generalized Semantic Segmentation (CLOUDS)" has been accepted at #CVPR2024! A collaborative effort with Subhankar Roy, Vicky Kalogeiton, Slim Essid, and Stéphane LATHUILIÈRE. Read it here: arxiv.org/abs/2312.09788 🧵👇 (1/x)

Happy to present E.T. the Exceptional Trajectories: Text-to-Camera-Trajectory Generation with Character Awareness. ECCV2024 with Nicolas DUFOUR, Xi WANG, Marc Christie and Vicky Kalogeiton Paper: arxiv.org/pdf/2407.01516 Webpage: lix.polytechnique.fr/vista/projects…

(1/8) 🎬 Introducing the Short Film Dataset (SFD), a long video QA benchmark with 1k short films and 5k questions. Why another videoQA dataset? 📖 Story-level QAs 🎥 Publicly available videos 🔒 Minimal data leakage ⏳ Long temporal context questions shortfilmdataset.github.io

📢Job update: Excited to be joining the DTU Compute as an Assistant Professor (with the AI Pioneer Center in Denmark Pioneer Centre for AI) starting in January 2025! I have #PhD and #PostDoc positions available, so stay tuned for more advertisements soon!

🎥 AKiRa provides control over camera motion and optics (focal length, distortion, aperture) in video diffusion, enabling cinematic effects like fisheye, focus shifts, and dolly zoom. 📄 Paper: arxiv.org/abs/2412.14158 👉 Project Page: lix.polytechnique.fr/vista/projects… 🧵👇

🚨 Recruiting PhD students to join my team at DTU Visual Computing & Pioneer Centre for AI on 3D Vision! 🇩🇰 🚲🌊🏰 Copenhagen is an emerging hub for computer vision with a thriving community—and it’s an amazing city! 📢 Apply now: efzu.fa.em2.oraclecloud.com/hcmUI/Candidat… & please reach out with any questions!

🎉 #Interactive4D has been accepted to #ICRA2025! We’re working to simplify the accurate labeling of 4D point clouds. Give the code a try! 🚀

Movies are more than just video clips, they are stories! 🎬 We’re hosting the 1st SLoMO Workshop at #ICCV2025 to discuss Story-Level Movie Understanding & Audio Descriptions! Website: slomo-workshop.github.io Competition: huggingface.co/spaces/SLoMO-W…