Sign in

Tengda Han

@tengda.bsky.social
73 followers 55 following 10 posts

Researcher at Google DeepMind. Computer vision and machine learning.

PostsRepliesMedia
Tengda Han @tengda.bsky.social · 10/07/2025
Organized by: Junyu Xie, Ridouane Ghermi, @tengda.bsky.social, Max Bain, Arsha Nagrani, @vickykalogeiton.bsky.social, @gulvarol.bsky.social, Weidi Xie, Ivan Laptev and Andrew Zisserman. See you in Hawaii! 🌺
010
Tengda Han @tengda.bsky.social · 10/07/2025
As a part of the workshop, we have a MovieQA competition based on the SF20K dataset and hosted on HuggingFace @hf.co Main Track: huggingface.co/spaces/SLoMO... Plus, we have a special track for small models (< 8B)! huggingface.co/spaces/SLoMO...
huggingface.co
SF20KCompetition - a Hugging Face Space by SLoMO-Workshop
This application allows users to view competition information, dataset details, leaderboards, and submission statuses. Users can fetch and manage their submissions, view rules, and check login stat...
100
Tengda Han @tengda.bsky.social · 10/07/2025
We’re excited to have a fantastic lineup of speakers: @amypavel.bsky.social, Anna Rohrbach, Mike Zheng Shou, Makarand Tapaswi. We’ll also host a panel discussion with the organizers!
121
Tengda Han @tengda.bsky.social · 10/07/2025
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...
141
Tengda Han @tengda.bsky.social · 14/06/2025
Thank @dimadamen.bsky.social for presenting our Orthogonal Optimizer! It’s a simple modification on standard optimizers for streaming video learning. We have code available at sites.google.com/view/orthogo...
041
Tengda Han @tengda.bsky.social · 09/04/2025
Check out our CVPR 2025 paper: arxiv.org/abs/2504.01961. Work with Dilara Gokay, Joseph Heyward, Chuhan Zhang, Daniel Zoran, Viorica Pătrăucean, João Carreira, Dima Damen and Andrew Zisserman, from Google DeepMind
arxiv.org
Learning from Streaming Video with Orthogonal Gradients
We address the challenge of representation learning from a continuous stream of video as input, in a self-supervised manner. This differs from the standard approaches to video learning where videos ar...
020
Tengda Han @tengda.bsky.social · 09/04/2025
Humans learn from one continuous visual stream, but large video models have to be trained on billions of web videos. We found that learning from such sequential streams is challenging for video models—and we introduce a family of "orthogonal optimizers" to bridge the gap!
161
Tengda Han @tengda.bsky.social · 17/03/2025
It's interesting to see that visual counting remains to be quite challenging for generalist AI models. But this specialist model counts very well. Nice work from @nikigoliai.bsky.social last year!
010
Tengda Han @tengda.bsky.social · 05/03/2025
We are looking for a student researcher to work on video understanding plus 3D, in Google DeepMind London. DM/Email me or pass it to someone if you feel it may be a good fit!
0206
Tengda Han @tengda.bsky.social · 25/01/2025
How do you know he is not 🤔😆
100
Reposted by Tengda Han
Dima Damen @ECCV 2026 @dimadamen.bsky.social · 13/12/2024
From an award candidate... to best paper #ACCV2024 Glad to share that "It's Just Another Day" received the top award at the conference. @bristoluni.bsky.social @ox.ac.uk This paper is worth reading :-) based on the reviewers, AC and awards committee. We thank them for their time and effort.
6362