Weidi Xie @WeidiXie Twitter profile

Last Seen Profiles

@chvl_louis

@kbm08_

@bakuro9213

@Gi__1994

@pengen_stw

@EHS_FB

@Francimramba

@SheStillResists

@hubilo

@leratotheboBTC

@OVTeUruFkILFJdm

@OMATSU_UG

@AdrienGombeaud

@Benjaminn_95

@Astriikz

@DegenFN

@Tiagobrandao_8

@emmaaalm___

@nanochaaaaa

@KIT_TIK910

@muratbardakci

@inpic0

@PremierCapper

@editingemily

@serreaumatis2

@L_Suertes

@MrTwistedhumor

@Yasirkh62371454

@SoukupDavid

@GlobalBioImage

@anngiangrave

@NikonImagingHMS

@MrKing173953916

@EPascalPeters

@jandakembangstw

@JelliesOnBlast

Weidi Xie

@WeidiXie

5 years

Check We are excited to share code & model for Self-supervised Correspondence Flow (BMVC 2019 Oral) @bmvc2019 , State-of-the-art performance on video segmentation and pose tracking. @Oxford_VGG

2

110

423

Weidi Xie

@WeidiXie

2 years

Personal update: After spending seven wonderful years at Oxford, I've decided to take new adventure. I'm joining Shanghai Jiao Tong University from this year 🐯.

23

1

295

Weidi Xie

@WeidiXie

4 years

Tracking objects is among the first skills human infants learn, surely this must be a task without semantic understanding. We present a SOTA self-supervised tracking approach, all you need is just 10min raw videos, zero annotations required. @Oxford_VGG

1

50

195

Weidi Xie

@WeidiXie

2 months

A tiny milestone in my academic journey. I know these metrics do not carry much significance in today's academic landscape. Nevertheless, they serve as a personal gauge, allowing me to assess the papers' impact and reflect on if I've contributed something meaningful.

12

0

143

Weidi Xie

@WeidiXie

3 years

Code: Self-supervised Video Object Segmentation by Motion Grouping: We show that self-supervised segmentation can be done purely motions.

0

24

107

Weidi Xie

@WeidiXie

11 months

ICCV23 work on Open-vocabulary Object Segmentation with Diffusion Models - we do visual instruction tuning on pre-trained diffusion model, to simultaneously generate image and open-vocabulary masks. - it can create synthetic datasets for training discriminative model for free.

1

19

101

Weidi Xie

@WeidiXie

9 months

Can GPT-4V(vision) serve medical applications? We present recent efforts on assessing GPT-4V for multimodal medical diagnosis, by case studies, covering 17 human body systems, across 8 clinical imaging modalities, e.g., radiology, pathology. 🔥Report:

6

23

101

Weidi Xie

@WeidiXie

1 year

Just read Med-PaLM 2, the progress of LLMs in medical question answering is incredible ! but, I think multimodal medical question answering is quite far behind, here I present you, PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering:

4

17

91

Weidi Xie

@WeidiXie

2 years

Happy to share the work, "Visual-Language Models for Efficient Video Understanding" at ECCV2022. We benchmark 10 different datasets for various tasks, it turns out that, simply prompting CLIP can achieve comparable or sota results on many video tasks already. #ECCV2022

1

13

93

Weidi Xie

@WeidiXie

4 years

We are releasing the code and model for #VGGSound A new large-scale audio-visual dataset, it was collected with audio-visual correspondence, accessible via: codes & model:

2

26

75

Weidi Xie

@WeidiXie

5 years

We investigate self-supervised learning on video correspondence flow. If done properly, the self-supervised learning can be surprisingly powerful (closing the gap to supervised learning). We demonstrate state-of-the-art results on video segmentation.

0

24

71

Weidi Xie

@WeidiXie

4 years

We are presenting our new paper at LUV2020 workshop today at 16:15 - 16:30pm. MAST: A Memory-Augmented Self-Supervised Tracker, by @LaiZihang , @erika_lu_ , @Oxford_VGG . A strong tracking model trained with no manual annotation. Code: #VGGatCVPR2020

1

19

69

Weidi Xie

@WeidiXie

3 years

Also best paper on CVPR RVSU Workshop. TL;DR: We propose a self-supervised learning approach for segmentation based on motions, ie, Gestalt Principle. Achieve strong performance to strong supervision on several popular benchmarks, e.g. DAVIS2016, MoCA (camouflage detection).

charig yang

@chaaarig

3 years

Check out our paper at @ICCV_2021 ! Self-supervised Video Object Segmentation by Motion Grouping (w/ @hala_lamdouar , @erika_lu_ , Andrew Zisserman & @WeidiXie ) Project page (paper+video+code):

1

23

122

0

6

60

Weidi Xie

@WeidiXie

1 year

Happy to share the paper of "Self-supervised Tumor Segmentation with Sim2Real Adaptation" published in IEEE Journal of Biomedical and Health Informatics. The model enables zero-shot tumor segmentation with Sim2Real training, requiring zero/few annotation from physicians.

1

7

57

Weidi Xie

@WeidiXie

1 year

Sharing the work "PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents", - A large-scale image-caption datasets collected from biomedical papers, - A CLIP-style model, that can be transfered to various downstream tasks with comparable or sota results.

2

8

54

Weidi Xie

@WeidiXie

1 year

I won't be able to attend the CVPR due to visa reasons, though I applied it over two months ago. Found an interesting workshop, around 4AM in China time, and it's promised to be NOT recorded. Honestly, I don't understand the point. Have we decided to go CloseAI ? #CVPR2023

4

1

54

Weidi Xie

@WeidiXie

11 months

We present you our new efforts on building medical generalist foundation models for radiology: Arxiv: Website: Hope this can promote the development of medical foundation models ！ (1/5)

5

10

54

Weidi Xie

@WeidiXie

6 years

VGGFace2 is a large-scale face recognition dataset. Over 9000 identities, 3M images, are downloaded from Google Image Search and have large variations in pose, age, illumination, ethnicity and profession. Dataset: Github:

1

30

51

Weidi Xie

@WeidiXie

10 months

Our recent work to initiate the open-vocab video instance segmentation (ICCV23 Oral): - we collect a large-vocabulary video instance dataset (LV-VIS), with over 1196 categories. - we propose an Transformer-based architecture, OV2Seg, proposing, segmenting objects through time.

1

14

50

Weidi Xie

@WeidiXie

3 years

Great, finally, some work tries to solve the trivial solution problem, we didn't manage to make it work and had to take another path .....

AK

@_akhaliq

3 years

Dense Unsupervised Learning for Video Segmentation abs: github:

3

100

498

0

48

Weidi Xie

@WeidiXie

4 months

We present you our recent work on developing open-source, multilingual language model for medicine, that the benefits a wider, linguistically diverse audience from different regions. All codes, models are available at @huggingface

2

10

49

Weidi Xie

@WeidiXie

1 year

Models for perception understanding are developing rapidly, thanks for the SAM model, however, can the model infer visual attributes under open-vocabulary setting ? Here, we develop a model for open-vocabulary object detection and attribute recognition. #CVPR2023

2

11

44

Weidi Xie

@WeidiXie

5 years

Self-supervised Video Representation Learning with Dense Predictive Coding. State-of-the-art RGB-stream action classification accuracy, better than ImageNet pretrained weights! @Oxford_VGG Paper: ; Code: ( @PyTorch )

0

19

47

Weidi Xie

@WeidiXie

10 months

Our recent work on AI4Medicine: visual-language representation learning in radiology, it will be presented on ICCV2023. MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology: Our contributions include (1/4):

1

9

46

Weidi Xie

@WeidiXie

6 months

Excited to share our new effort on large-scale long-tailed disease diagnosis on radiology images. This is more feasible playground for academic labs, to explore sophisticated algorithms, which is impractical in developing generalist foundation model, due to computational costs.

2

9

45

Weidi Xie

@WeidiXie

2 years

The human visual system is amazing at many tasks, however, it is particularly weak for objects counting. In fact, one can only make a rapid, accurate and confident judgement if the number of items is below five. We can augment the ability with a CounTR:

0

7

45

Weidi Xie

@WeidiXie

3 years

I feel extremely disappointed while reading papers with incomplete literature review. To me, this should be the MOST important thing, as it clearly shows you understand what has been done and what is the remaining challenge and your contribution, instead of over-claiming.

3

1

43

Weidi Xie

@WeidiXie

1 year

Recent advances in AI, e.g. nlp, visual perception have revealed the power of supervised training on massive data, e.g. chatGPT, SAM. From a product perspective, this is great. However, from a research view, the dream remains to be training models with zero/cheap annotations.

2

5

41

Weidi Xie

@WeidiXie

4 years

Check out our #BMVC2020 paper: “Inducing Predictive Uncertainty Estimation for Face Recognition” @Oxford_VGG A simple approach for estimating the predictive confidence for face recognition systems. Q&A session Tuesday at 10:00-11:00 and 16:00-17:00 UK

2

12

39

Weidi Xie

@WeidiXie

5 months

I do think training with synthetic data will become the next thing in computer vision !! Thanks for the repost @_akhaliq 😁

AK

@_akhaliq

5 months

InstaGen Enhancing Object Detection by Training on Synthetic Dataset paper page: introduce a novel paradigm to enhance the ability of object detector, e.g., expanding categories or improving detection performance, by training on synthetic dataset

2

33

114

0

38

Weidi Xie

@WeidiXie

11 months

Can we stop over-claiming, and be realistic ? Processing X-ray images doesn't make it generalist biomedical AI .......

Shek Azizi

@AziziShekoofeh

11 months

Meet Med-PaLM Multimodal (Med-PaLM M), the first demonstration of "Generalist Biomedical AI"!

15

130

703

2

1

36

Weidi Xie

@WeidiXie

1 year

Yet another medical-related report: - we finetuning LLaMA on 4.8 million biomedical papers from Pubmed, after several epochs, it has already enhanced capabilities in the medical domain - the proposed model, PMC-LLaMA, achieves high performance on biomedical QA benchmarks.

2

7

36

Weidi Xie

@WeidiXie

3 months

I'd like to share a latest work from the group, accepted at #CVPR2024 ! Grounded Question-Answering in Long Egocentric Videos, by Shangzhe Di. It explores grounded question-answering in long, egocentric videos, enabling individuals to inquire about their past visual experiences.

1

7

36

Weidi Xie

@WeidiXie

5 months

I recently saw many Mamba models for medical segmentation, generally inserted at the bottleneck of UNet, and claim to model long-term dependency at resolution of 9x9 or 7x7... This is such an odd atmosphere in AI, whenever something new comes out, people use it for EVERYTHING !!

3

1

33

Weidi Xie

@WeidiXie

2 months

🚀 Excited to introduce RadGenome-Chest CT, a comprehensive, large-scale, and fine-grained visual-language dataset for 3D CT scans. It includes: - Organ-level segmentation for 197 categories; - 665K multi-granularity grounded reports; - 1.3M grounded VQA pairs.

2

6

35

Weidi Xie

@WeidiXie

5 years

The Pytorch models for VGGFace2 are fully available online now: @Oxford_VGG

0

13

31

Weidi Xie

@WeidiXie

10 months

We have updated the PMC-LLaMA model: Compared with the former versions, we have: (i) upscaled the model size to 13B; (ii) added 30K medical books into the knowledge injection stage; (iii) done instruction tuning on a large-scale dataset with 202M tokens.

PMC-LLaMA: Towards Building Open-source Language Models for Medicine

Recently, Large Language Models (LLMs) have showcased remarkable capabilities in natural language understanding. While demonstrating proficiency in everyday conversations and question-answering...

arxiv.org

1

7

33

Weidi Xie

@WeidiXie

11 months

New paper on open-vocabulary detection. We aim to tackle two problems in existing work: (1) lexical ambiguity, (2) visual granularity. We demonstrate great results, that use text, visual or both ways to generate classifier. Please check the threads from @pranna for details.

Prannay Kaul @ CVPR

@PrannayKaul

11 months

[1/8] In Hawaii(!) for #ICML2023 to present "Multi-Modal Classifiers for Open-Vocabulary Object Detection" Joint with @WeidiXie and Andrew Zisserman 🕸️🏗️ 📑 🖥️ Poster #413 , Thursday 1:30-3pm Exhibit Hall 1

1

10

28

0

6

31

Weidi Xie

@WeidiXie

1 year

Recently, I'm quite interested in the deploying AI tools for medical applications, here are a series of our recent work, the list is growing continuously, please stay tuned.

2

0

30

Weidi Xie

@WeidiXie

4 months

This originally aims to generate comic books for my daughter with diffusion models, i.e., continuous image sequences with consistent characters, storylines, etc. Well, I guess now we have #SORA 🤣..... Still, it is good to get it accepted on #CVPR2024 , congrats the team !!

HaoningWu___

@HaoningWu_

4 months

Thrilled to share that our exciting project, [StoryGen] (with @liu_chang666 and @WeidiXie ), has been accepted by #CVPR2024 !!!🥳 Check out our paper, code and dataset at: Title: Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models

1

4

11

0

2

29

Weidi Xie

@WeidiXie

6 years

@Oxford_VGG Our new ACCV2018 paper on Class-Agnostic Counting is now online:

1

8

27

Weidi Xie

@WeidiXie

7 months

Would like to share fun work, which has shown to be functional to entertain my daughter ! It can generate coherent image sequences based on the stories you give, or those written by GPTs ! Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models.

2

0

27

Weidi Xie

@WeidiXie

2 years

@TansuYegen We actually collected a dataset of these amazing camouflage......

1

6

27

Weidi Xie

@WeidiXie

5 years

Our work on self-supervised learning for the problem of Geometric Alignment based on noisy annotation. Geometric consistency is applied, that is to say all possible perturbed label must be transformed back the unique ground-truth position. @Oxford_VGG

0

13

26

Weidi Xie

@WeidiXie

5 years

State-of-the-art Speaker Recognition with VLAD and GhostVLAD aggregation. "Utterance-level Aggregation For Speaker Recognition In The Wild", to appear in @icassp2019 , for Oral Presentation. Project page (models & code):

1

11

25

Weidi Xie

@WeidiXie

2 years

Remind me this paper, actually the first time I realise videos are not like I used to imagine ...... Analysing Gait with Spatiotemporal Surfaces,

Kitasenju Design

@kitasenjudesign

2 years

structure of slit-scan スリットスキャンの構造

55

3K

18K

1

3

23

Weidi Xie

@WeidiXie

10 months

We have updated the manuscript : - more recent models as baselines, - better model performance, - more comprehensive evaluation, including both machine and human scoring. Arxiv: Website:

1

2

23

Weidi Xie

@WeidiXie

6 months

We have made the first release of SAT-Nano, with model and inference code. The SAT-Ultra will be released soon as well. Stay tuned ! Webpage: Code & Model:

0

5

23

Weidi Xie

@WeidiXie

7 months

I'm not going to NeurIPS, but Fatma does, please go chat with her about the great work, that has been done by @gorkaydemir . 😎

F. Güney

@ftm_guney

7 months

I’m presenting our paper with @gorkaydemir and @WeidiXie tomorrow at Poster Session 2* at #NeurIPS2023 : with SOLV; “Self-supervised Object Centric Learning for Videos”, we can discover multiple objects in real-world video sequences without using additional modalities like depth

1

15

123

0

1

17

Weidi Xie

@WeidiXie

5 years

@Oxford_VGG Code for the paper on "Class-Agnostic Counting" by Erika Lu, Weidi Xie, Andrew Zisserman :

0

7

17

Weidi Xie

@WeidiXie

1 year

🚀 The source code and pre-trained model for PMC-VQA is officially released at: We will update the model continuously. Stay tuned !

0

4

16

Weidi Xie

@WeidiXie

1 year

📢 Our #PMC -VQA dataset: is now live on @huggingface datasets 🤗 , and officially benchmarked on @paperswithcode Looking forward the progress in this domain !!!

0

2

17

Weidi Xie

@WeidiXie

5 years

I will present the recent work @Oxford_VGG with @NagraniArsha , Joon Son Chung, and Andrew Zisserman on Speaker Recognition @icassp2019 on Thursday (May 16), 09:20 - 09:40. Project page (models & code):

0

6

17

Weidi Xie

@WeidiXie

1 year

PMC-CLIP accepted by #MICCAI2023 !!! Congrats Weixiong, Ziheng, @XiaomanZhang99 , @chaoyiwu4 Webpage:

chaoyi-wu

@chaoyiwu4

1 year

Our paper on the medical foundation model, PMC-CLIP, has been accepted by MICCAI2023. Congratulations to all co-authors.😆 In PMC-CLIP, we collected 1.6M medical image-text caption pairs. All meta reviewers rank it first. Thanks for their recognition.👏

1

3

0

16

Weidi Xie

@WeidiXie

5 months

Check this out ! Nice work on audio-visual synchronisation, also won the challenge on WACV.

vladimir iashin

@_iashin

5 months

📢 Thrilled to share that our paper on "Synchformer: Efficient Synchronization from Sparse Cues" got accepted at #ICASSP24 ! 🎉 Huge shoutout to the amazing team: @WeidiXie , Esa Rahtu, and Andrew Zisserman! Code: arXiv:

0

1

21

0

15

Weidi Xie

@WeidiXie

3 years

Use motion to train segmentation model, again, use common fate principle, similar to the motion grouping paper. Simple simulation in flow field turns out generalising extremely well.

Hala

@hala_lamdouar

3 years

Check out our latest work on “Segmenting Invisible Moving Objects” at @BMVCconf (w/ @WeidiXie and Andrew Zisserman) Project page:

0

14

58

0

14

Weidi Xie

@WeidiXie

2 years

Existing super-resolution (SR) model often specialized for one scale, limiting their use in practise. We develop a general plugin module, can be injected to any existing SR models, to augment their ability for arbitrary-scale super-resolution. Webpage:

0

2

14

Weidi Xie

@WeidiXie

9 months

This will be present today afternoon(Friday 6th) @ICCVConference Work by @chaoyiwu4 , @XiaomanZhang99

Weidi Xie

@WeidiXie

10 months

Our recent work on AI4Medicine: visual-language representation learning in radiology, it will be presented on ICCV2023. MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology: Our contributions include (1/4):

1

9

46

0

14

Weidi Xie

@WeidiXie

6 years

Recent work on Multi-view Cardiac MR Detection, Orientation, and Segmentation has been published at Medical Image Analysis, "Ω-Net (Omega-Net): Fully automatic, multi-view cardiac MR detection, orientation, and segmentation with deep neural networks", .

0

4

11

Weidi Xie

@WeidiXie

1 year

thanks for the tweet.

AK

@_akhaliq

1 year

Multi-Modal Classifiers for Open-Vocabulary Object Detection paper page: The goal of this paper is open-vocabulary object detection (OVOD) x2013 building a model that can detect objects beyond the set of categories seen at training, thus enabling the

5

63

279

0

11

Weidi Xie

@WeidiXie

9 months

Now also available on arxiv 🔥:

Can GPT-4V(ision) Serve Medical Applications? Case Studies on...

Driven by the large foundation models, the development of artificial intelligence has witnessed tremendous progress lately, leading to a surge of general interest from the public. In this study,...

arxiv.org

Weidi Xie

@WeidiXie

9 months

Can GPT-4V(vision) serve medical applications? We present recent efforts on assessing GPT-4V for multimodal medical diagnosis, by case studies, covering 17 human body systems, across 8 clinical imaging modalities, e.g., radiology, pathology. 🔥Report:

6

23

101

0

2

11

Weidi Xie

@WeidiXie

3 years

Will present in this workshop on self-supervised video representation learning.

Jonathon Luiten

@JonathonLuiten

3 years

Starting in 5 minutes!

0

1

0

1

10

Weidi Xie

@WeidiXie

1 year

Webpage: Datasets: Code:

0

2

10

Weidi Xie

@WeidiXie

5 months

Following my previous tweet, - Our team decide to run thorough comparison between nnUNet and Mamba-based model for medical segmentation. - We will conduct experiment on over 60 public segmentation datasets, and provide complete comparison. (1/n)

1

0

10

Weidi Xie

@WeidiXie

5 months

I think the key problem is, this community is not tolerant to failure !! So whenever something comes out, people can always do hyper-parameter tuning or compare to low baselines, to show its effectiveness. This is misleading the entire community for huge waste of resource.

2

0

10

Weidi Xie

@WeidiXie

11 months

New paper on Nature Communications, where we investigate knowledge-enhanced multimodal representation learning with chest X-rays and radiology reports.

1

9

Weidi Xie

@WeidiXie

5 years

VGGFace2 Keras + Tensorflow model:

GitHub - WeidiXie/Keras-VGGFace2-ResNet50

Contribute to WeidiXie/Keras-VGGFace2-ResNet50 development by creating an account on GitHub.

github.com

0

1

9

Weidi Xie

@WeidiXie

6 years

#ECCV2018 Comparator Networks.

0

9

Weidi Xie

@WeidiXie

1 year

Please volunteer to be a reviewer for #NeurIPS2023 ! Message me if you are not invited yet.

NeurIPS Conference

@NeurIPSConf

1 year

Our past conferences wouldn't have been possible without our many reviewers. If you have at least 2 papers in top peer-reviewed confs or journals, with at least one in an ML venue (eg NeurIPS ICML ICLR), we’d be v grateful if you reviewed for #NeurIPS2023

5

66

160

0

9

Weidi Xie

@WeidiXie

7 months

Thank you for the invitation. It's an honour to attend this event. Will present some recent work on Developing Foundation Models for Healthcare.

Jeya Maria Jose

@jeyamariajose

7 months

Excited for the session and panel discussion with @vivnat , @pranavrajpurkar , and @WeidiXie on "Building and Evaluating Foundation Models for Healthcare" at AI+Health 2023 conference organized by Stanford University @StanfordAIMI @StanfordHAI

1

23

0

9

Weidi Xie

@WeidiXie

1 year

Will cover ideas for discovering objects without manual annotations from images, videos ! Looking forward to the tutorial.

valeo.ai

@valeoai

1 year

Don't miss the "Object localization for free: Going beyond self-supervised learning" @CVPR tutorial (by @oriane_simeoni @WeidiXie @tkipf P. Pérez) for an in-depth coverage of different angles on object localization with no human supervision #cvpr2023

1

13

46

0

8

Weidi Xie

@WeidiXie

2 years

When trained at a sufficient scale, self-supervised learning has exhibited a notable ability to solve a wide range of visual-language tasks. It turns out that we can adapt pre-trained foundation models to open-vocabulary semantic segmentation, by training very few parameters.

1

0

8

Weidi Xie

@WeidiXie

9 months

Use computer vision tools, to create a large-scale audio-language dataset.

AK

@_akhaliq

9 months

A Large-scale Dataset for Audio-Language Representation Learning paper page: The AI community has made significant strides in developing powerful foundation models, driven by large-scale multimodal datasets. However, in the audio representation learning

1

41

174

1

0

7

Weidi Xie

@WeidiXie

1 year

- a strong generative model for medVQA - a scalable pipeline for collecting large-scale dataset - a significantly more challenging benchmark than all existing ones, strong visual-language models fail miserably, e.g. BLIP2, Open-Flamingo. Would like to see the progress on medVQA!

1

7

Weidi Xie

@WeidiXie

1 year

CVPR work on automatically generating audio descriptions.

Imagine-ENPC

@ImagineEnpc

1 year

#CVPR2023 June 22, Thu AM (Highlight, Poster 234) AutoAD: Movie Description in Context @TengdaHan , @maxhbain , @NagraniArsha , @gulvarol , @WeidiXie , and Andrew Zisserman ( @Oxford_VGG ) pdf: web: code:

1

5

18

1

0

7

Weidi Xie

@WeidiXie

10 months

Our final model outperforms ChatGPT and LLaMA-2 on multiple Medical QA benchmarks ! Open-source materials: Code: Model: DATA: Hope this can promote the development of open-source LLM for healthcare.

1

6

Weidi Xie

@WeidiXie

5 years

Model and Code:

0

1

5

Weidi Xie

@WeidiXie

1 year

"Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision." #CVPR2023 We aim to train an open-vocab segmentation model with image caption, explicitly exploiting the visual invariance between images. Project Page:

1

6

Weidi Xie

@WeidiXie

2 years

Collaboration with Chen Ju, @TengdaHan , @KunhaoZ , Ya Zhang, Project page: GitHub: We are gradually releasing the codes for reproducing all the benchmark results.

GitHub - ju-chen/Efficient-Prompt

Contribute to ju-chen/Efficient-Prompt development by creating an account on GitHub.

github.com

0

1

6

Weidi Xie

@WeidiXie

6 months

Arxiv: Website: HuggingFace: Hope this work on general disease diagnosis will spur interests from the AI4Health community.

Large-scale Long-tailed Disease Diagnosis on Radiology Images

Developing a generalist radiology diagnosis system can greatly enhance clinical diagnostics. In this paper, we introduce RadDiag, a foundational model supporting 2D and 3D inputs across various...

arxiv.org

0

2

6

Weidi Xie

@WeidiXie

1 year

Same.......

hardmaru

@hardmaru

1 year

I’m so tired of AI hype tweets. They’re all over my Twitter feed these days.

40

141

1K

0

6

Weidi Xie

@WeidiXie

4 years

I've got asked for the code of an old paper, may be too late 😂, but in case someone else is interested: "Multicolumn Networks for Face Recognition", BMVC2018. The idea is to compute set representation by aggregating images based on the importances.

0

5

Weidi Xie

@WeidiXie

6 months

- We present a novel architecture that enables to process arbitrary number of input scans, from various imaging modalities, and trained by leveraging the rich domain knowledge.

1

0

5

Weidi Xie

@WeidiXie

11 months

This is a work questioned by the reviewer for its value....... To be honest, I'm not sure if the idea will be adopted by the community or not, but I think it's COOL ! Webpage: Arxiv: Code & Model:

GitHub - Lipurple/Grounded-Diffusion: Open-vocabulary Object Segmentation with Diffusion Models

Open-vocabulary Object Segmentation with Diffusion Models - Lipurple/Grounded-Diffusion

github.com

0

5

Weidi Xie

@WeidiXie

1 year

Looking forward to it😎

Oriane Siméoni

@oriane_simeoni

1 year

Our @CVPR tutorial about "object localization for free" is today room East 11 starting at 8:30am PDT time (with @WeidiXie , @tkipf and P. Pérez). Come and join us if you want to hear/discuss about different successful approaches to object localization with no annotation!

1

6

18

0

5

Weidi Xie

@WeidiXie

4 years

This is today !

Weidi Xie

@WeidiXie

4 years

Check out our #BMVC2020 paper: “Inducing Predictive Uncertainty Estimation for Face Recognition” @Oxford_VGG A simple approach for estimating the predictive confidence for face recognition systems. Q&A session Tuesday at 10:00-11:00 and 16:00-17:00 UK

2

12

39

0

5

Weidi Xie

@WeidiXie

1 year

Webpage: Arxiv:

OvarNet: Towards Open-vocabulary Object Attribute Recognition

In this paper, we consider the problem of simultaneously detecting objects and inferring their visual attributes in an image, even for those with no manual annotations provided at the training...

arxiv.org

0

5

Weidi Xie

@WeidiXie

11 months

Check out our recent work in diagnosing human-object interaction detectors.

Huaizu Jiang

@HuaizuJiang

11 months

Overwhelmed by the progress of human-object interaction (HOI) detection? Ever wondered why one HOI model performs better than another? Check out our recent work in diagnosing human-object interaction detectors. Paper: Code: 🛢️ 1/N

1

5

28

0

4

Weidi Xie

@WeidiXie

1 year

Thanks for the invitation, had really enjoyed the workshop, and learnt a lot.😁

F. Güney

@ftm_guney

1 year

videos of invited talks from our ECCV22 workshop on "What is motion for?" is available on youtube (thanks to Deqing):

0

7

27

0

4

Weidi Xie

@WeidiXie

9 months

joint work with a wonderful team, @XiaomanZhang99 , @chaoyiwu4 , and more.....

0

4

Weidi Xie

@WeidiXie

1 year

1) multimodal biomedical dataset: PMC-OA, 1.6M image-caption pairs collected from PubMedCentral, covering diverse modalities or diseases, with majority of the image-caption samples aligned at finer-grained level, i.e., subfigure and subcaption.

1

0

4

Weidi Xie

@WeidiXie

4 years

@strangecosmos @ylecun may be this is related ? 😂

0

4

Weidi Xie

@WeidiXie

6 months

@gdb Right. I think this is exactly what we would expect a AI4Health model to have, some 'emerging abilities', to discover some hidden factors behind the disease itself, being able to make diagnosis by combining all information source, with the ability of top level clinicians.

1

0

4

Weidi Xie

@WeidiXie

7 months

cool stuff !

Pika

@pika_labs

7 months

Introducing Pika 1.0, the idea-to-video platform that brings your creativity to life. Create and edit your videos with AI. Rolling out to new users on web and discord, starting today. Sign up at

1K

5K

26K

0

3

Weidi Xie

@WeidiXie

9 months

We assess GPT-4V's capabilities in tasks like anatomy recognition, disease diagnosis, report generation, and disease localization.

1

0

2

Weidi Xie

@WeidiXie

7 months

Fantastic !

Zeming Chen

@eric_zemingchen

7 months

We present MEDITRON, a set of new open-access #LLMs (70B & 7B) adapted to the medical domain, achieving new SoTA open-source performance on common medical benchmarks, outperforming #GPT -3.5 and Med-PaLM, and coming within 5% of #GPT4 Find out how we did this ⬇️

25

136

610

0

3

Weidi Xie

@WeidiXie

6 months

- The cases cover 9 diverse imaging modalities (CT, MRI, X-ray, Ultrasound, Fluoroscopy, Nuclear medicine, Mammography, DSA, Barium Enema) and 7 human anatomy regions (head and neck, spine, chest, breast, abdomen and pelvis, upper limb, lower limb).

1

0

3

Weidi Xie

@WeidiXie

6 months

- We build up an large-scale diagnostic dataset that encompasses 5568 disorders linked with 930 unique ICD-10-CM codes, containing 39,026 cases (192,675 scans).

1

0

3

Weidi Xie

@WeidiXie

10 months

Here are the paper, code, model, join us on this challenging problem💪 paper: dataset & code:

GitHub - haochenheheda/LVVIS: Large-Vocabulary Video Instance Segmentation dataset

Large-Vocabulary Video Instance Segmentation dataset - haochenheheda/LVVIS

github.com

0

3