Given a short movie clip, can we identify who is doing what to/with whom, where, how & why? Our latest paper at NeurIPS Conference describes an effort towards this, with an emphasis on grounding! We identify people climbing on snowy rocks, shivering, and staring at a green door! 🧵1/9

RT @[email protected] We have a research internship position open for 2023 on "Online adaptation of multi-task models". Come work with us at NAVER LABS Europe in Grenoble! More info here: europe.naverlabs.com/job/online-ada… PS: Hello world!!! sigmoid.social/@skamalas/1093…

Exploring Discrete Diffusion Models for Image Captioning abs: arxiv.org/abs/2211.11694

We are presenting our work today (11/23) at #BMVC2022 from 2:00 PM - 3:30 PM! If you are at BMVC and interested in temporal segmentation of steps in instructional videos, stop by our poster for a chat!

Have you ever noticed how Chinese and American researchers both publish at #NeurIPS, go to the same conference---and then barely cite or talk to each other? Bingchen Zhao Yuling Gu Jessica Zosa Forde & I have, and we'll be presenting on it at Global AI Cultures! arxiv.org/pdf/2211.12424…

🚨 New preprint with Tom Sherborne, alexandra birch, and Mark Steedman We evaluate segment level MT metrics on extrinsic tasks and they show a negligible correlation 😮 arxiv.org/abs/2212.10297 [1/5]

Come join us and apply to be an organizer for WiCV at #ICCV2023 #ICCV2025. Fill the form by Jan 20.

[Pls RT 📢 - DL 23/04] Fantastic 💡 **postdoc** Opportunity to join my group University of Bristol working around multimodal video understanding. Project in collab w Andrew Zisserman &others Visual Geometry Group (VGG). 26 months w student co-supervision opportunities. Email for queries or apply directly.

our 1-day BMVA symposium on vision and language is only a month away! We have 4 keynote speakers (Andrew Zisserman, Hilde Kuehne, Frank Keller, Yuki Asano), 8 oral presentations and 21 posters. Registration is now open, more info at bmva.org/meetings/24-01… Michael Wray Tengda Han

is there a bug in review system? Open Review or #CVPR2026 Received a submission to review and I try to accept it. however, it got auto-declined twice. If the assignment is done by mistake, why it says "Reviewer Declined" instead of Removed/Cancelled.

What role does 3D have in learning robust representations of the visual world and can we develop scalable ways to inject 3D priors into our 2D self-supervised learning algorithms? If you are interested in these questions, and looking for a postdoc position, please read on. #job

Our work on understanding and explaining Indian road traffic scenarios has been accepted to #ICRA2024 (CORE A*). We introduce IDD-X, a large-scale multi-view dataset. This paper is a first for my Ph.D. student Chirag Parikh. IIIT Hyderabad IHub-Data

When on the PhD market, be on the lookout for these type of supervisors, and RUN!

It was a very special moment for me to hand over wings to the four Indian astronaut-designates. They reflect the hopes, aspirations and optimism of 140 crore Indians. India is proud of Group Captain Prasanth Balakrishnan Nair, Group Captain Ajit Krishnan, Group Captain Angad

The PhD student...🤣🤣

🚨 A friendly reminder! If you’re #ECCV2024 🇮🇹, I’ll be presenting our poster (#308) at 16:30 today! If you're interested in Videos, Language, Procedural Understanding, or Efficiency, I’d love to chat. Feel free to visit the poster to learn more - looking forward to meeting you!

[**International applications are now possible!**] I'm looking for a motivated PhD student to work with me on interpretable video models at the University of Bath (UK). Start from October 2025, fully-funded for 3.5 years. Deadline 10th December 24. Info at findaphd.com/phds/project/f…

Excited to (virtually) present a new evaluation metric for VLMs: "CAST: Cross-modal Alignment Similarity Test for Vision Language Models" at COLING 2025! Paper: arxiv.org/abs/2409.11007