Tengda Han
@TengdaHan
Followers
1K
Following
596
Media
23
Statuses
122
Research Scientist @ Google DeepMind. Previously PhD @Oxford_VGG
Oxford, England
Joined March 2019
Project page for more details and qualitative examples: https://t.co/E8BDGIM0w0 Sherry will be at @NeurIPSConf this week! Catch her to chat more!
sites.google.com
Video A 5-minute silent video designed to supplement the paper
0
0
2
Can you tell which action corresponds to which camera trajectory in the video above? Check out our paper for answers! Work done by our great intern Sherry Xue @sherryx90099597 at @GoogleDeepMind, and with Kristen Grauman, @dimadamen and Andrew Zisserman. https://t.co/ukbMRfAkZk
arxiv.org
Can one perceive a video's content without seeing its pixels, just from the camera trajectory-the path it carves through space? This paper is the first to systematically investigate this seemingly...
1
1
4
Human perception is active: we move around to see, and we see with intention. In our latest work "Seeing without Pixels", we find "how you see" (how the camera moves) roughly reveals "what you do" or "what you observe" -- and this connection can be easily learned from data.
1
8
45
A belated post for our ACMMM paper: we recognize and track animated characters for movie understanding tasks. Great work from Zhongrui Gui, also with @JunyuXieArthur @WeidiXie and Andrew Zisserman from @Oxford_VGG . Project page with code and dataset:
0
0
1
Animated movies can be effortlessly understood by young minds, but appear to be challenging for video-language models, why? The key problem is the huge diversity of animated characters -- their appearance ranges from human-like faces, to cars, fish, blobs, etc.
1
3
9
The SLoMo workshop on "Story-level Movie Understanding & Audio Description" will be on #ICCV2025 day-1 morning, starting at 8:40 AM at Room 327! @JunyuXieArthur, @maxhbain and Xi will be there in person. See you tomorrow @ICCVConference !! #iccv25
Being able to understand, describe and even enjoy movies is one of the pinnacles of computer vision. Interested in movie understanding and audio description? Check out our SLoMo workshop at @ICCVConference #ICCV2025!!
1
7
47
Being able to understand, describe and even enjoy movies is one of the pinnacles of computer vision. Interested in movie understanding and audio description? Check out our SLoMo workshop at @ICCVConference #ICCV2025!!
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: https://t.co/k1hDRCFjjd Competition: https://t.co/JseLilr6oc
0
2
20
You will find the great @dimadamen presenting our Orthogonal Optimizer now! It’s a simple modification on standard optimizers for streaming video learning. We have code available at
sites.google.com
Abstract 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...
Now @CVPR poster session 3 #286 Our @GoogleDeepMind paper: Learning from Streaming Video with Orthogonal Gradients As @TengdaHan couldn’t make it for visa reasons, you’ll have the second best option of me presenting our work 😅 See you there #CVPR2025
1
5
40
Many Congratulations to @jianyuan_wang, @MinghaoChen23, @n_karaev, Andrea Vedaldi, Christian Rupprecht and @davnov134 for winning the Best Paper Award @CVPR for "VGGT: Visual Geometry Grounded Transformer" 🥇🎉 🙌🙌 #CVPR2025!!!!!!
17
70
493
Check out our CVPR 2025 paper: https://t.co/0nq7i9fpqe. Work with Dilara Gokay, Joseph Heyward, @ChuhanZhang5 , @DanielZoran_ , Viorica Pătrăucean, @joaocarreira , @dimadamen and Andrew Zisserman, @GoogleDeepMind
arxiv.org
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...
0
3
31
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!
2
9
72
I was recently really excited to find out many people have been successfully using our CountGD model (NeurIPS'24) for products, open-source tools and science applications.
2
1
6
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!
4
33
118
We are happy to announce a new vacancy for a PDRA position in Computer Vision to work with Prof. Andrew Zisserman; more info here - https://t.co/8ekIxXZWTr Application deadline is 17th March at 12 noon. Good luck!
0
12
50
[Pls RT] Assistant Professor (Lecturer) in Computer Vision @BristolUni is now open [DL 6 Jan] This is a research+teaching permanent post within MaVi [ https://t.co/DVRS9hAkj0] in Computer Science. Suitable for strong postdocs or exceptional PhD graduates. https://t.co/Fo7FGnMAge
uob-mavi.github.io
Applications to the 2025 Summer of Research @MaVi have now closed. Machine Learning and Computer Vision Research Group Core faculty ...
1
15
31
I was not there @NeurIPSConf but I watched the recording. I feel this is an explicit bias on nationality. It’s indeed very ironic that this happened during a talk about ethics. As a community we should stop this behaviour. Kudos to the researcher who spoke up at the Q&A session!
It is just so sad that the #NeurIPS2024 main conference ended with such a racist remark by a faculty when talking about ethics. How ironic! I also want to commend the Chinese student who spoke up right on spot. She was respectful, decent, and courageous. Her response was
0
0
27
🚨Join us at the NeurIPS2024 Workshop on Self-Supervised Learning - Theory and Practice! Featuring talks from leading researchers at UC Berkeley, MIT, UW, FAIR, DeepMind, MILA, AI2, NTU, JHU, Brown, and UofBonn! 🗓️ Sat, Dec 14, 2024 📍 West Meeting Room 202-204 🧭
1
15
81
Very excited to know our paper "It's Just Another Day" won the best paper award at @ACCVConf. Big congratulations to Toby ( https://t.co/mEf3ffvRdD), who leads this project and did most of the great work! Toby is in Hanoi, presenting this work, feel free to say hi!!
📢 Our @ACCVConf Oral It’s Just Another Day: Unique Video Captioning by Discriminitive Prompting is now on ArXiv https://t.co/x0krwFBepO For challenging ego &timeloop movies, uniquely caption ev clip, including those near identical ones, w/out re-training captioning model 1/N
7
6
63
LoRA et al. enable personalised model generation and serving, which is crucial as finetuned models still outperform general ones in many tasks. However, serving a base model with many LoRAs is very inefficient! Now, there's a better way: enter Prompt Generation Networks,
1
9
91
📢 Our @ACCVConf Oral It’s Just Another Day: Unique Video Captioning by Discriminitive Prompting is now on ArXiv https://t.co/x0krwFBepO For challenging ego &timeloop movies, uniquely caption ev clip, including those near identical ones, w/out re-training captioning model 1/N
4
9
41