Can you tell if a Neural Net contains a Backdoor Attack? Try this demo for "Dual-Key Multimodal Backdoors for Visual Question Answering" (CVPR 2022) created using Gradio huggingface.co/spaces/CVPR/Du… Karan Sikka Indranil Sur Abhinav Shrivastava Susmit Jha UMD Department of Computer Science UMIACS SRI Hugging Face Gradio

Today we’re presenting our poster for “Dual Key Multimodal Backdoors for Visual Question Answering” at #cvpr2022 Afternoon poster session, 201b You can also test out some backdoored for yourself models with our demo: huggingface.co/spaces/CVPR/Du…

Before I forget, I'd like to summarize some interesting papers that I found at #CVPR2022. Dual-key multimodal backdoors for visual question answering arxiv.org/abs/2112.07668 1. This paper proposes an interesting Trojan attack method. To start, what exactly is a Trojan attack?

Excited to share our work "Teaching Matters: Investigating the Role of Supervision in Vision Transformers" which has been accepted to #CVPR2023! Work done with: Matthew Walmer, Kamal Gupta and Abhinav Shrivastava Website: cs.umd.edu/~sakshams/vit_… Code: github.com/mwalmer-umd/vi…

Just a reminder we’ll be presenting this evening at the Tuesday 4:30pm poster session at #CVPR2023. Hope to see you there!

We introduce LiFT, an easy to train, lightweight, and efficient feature upsampler to get dense ViT features without the need to retrain the ViT. Visit our poster European Conference on Computer Vision #ECCV2026 #eccv2024 in Milan on Oct 1st (Tuesday), 16:30 (local), Poster: 79. Project Page: cs.umd.edu/~sakshams/LiFT

We are happy to release our LiFT code and pretrained models! 📢 Code: github.com/saksham-s/lift Project Page: cs.umd.edu/~sakshams/LiFT Here are some super spooky super resolved feature visualizations to make the season scarier 🎃 Coauthors: Matthew Walmer Kamal Gupta Abhinav Shrivastava

🎉 Excited to share our paper "Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition" has been accepted to #ICCV2025! Equally co-led with Shuaiyi Huang — we advance few-shot action recognition via smart point tracking. 🔗 trokens-iccv25.github.io 🧵👇