DiffusionDB
DiffusionDB is the first large-scale text-to-image prompt dataset.
Github: https://github.com/poloclub/diffusiondb
🗒 Paper: https://arxiv.org/abs/2210.14896v1
Dataset: https://huggingface.co/datasets/poloclub/diffusiondb
👉 @bigdata_1
DiffusionDB is the first large-scale text-to-image prompt dataset.
Github: https://github.com/poloclub/diffusiondb
🗒 Paper: https://arxiv.org/abs/2210.14896v1
Dataset: https://huggingface.co/datasets/poloclub/diffusiondb
👉 @bigdata_1
❤1🔥1
Highly Efficient Real-Time Streaming and Fully On-Device Speaker Diarization with Multi-Stage Clustering
pip3 install spectralcluster==0.1.0
Github: https://github.com/wq2012/SpectralCluster
🗒 Paper: https://arxiv.org/abs/2210.13690v1
Speaker Diarization with LSTM: https://google.github.io/speaker-id/publications/LstmDiarization/
👉 @bigdata_1
pip3 install spectralcluster==0.1.0
Github: https://github.com/wq2012/SpectralCluster
🗒 Paper: https://arxiv.org/abs/2210.13690v1
Speaker Diarization with LSTM: https://google.github.io/speaker-id/publications/LstmDiarization/
👉 @bigdata_1
⚡1
NNSVS: A Neural Network-Based Singing Voice Synthesis Toolkit
Neural network-based singing voice synthesis library for research
Docs: https://nnsvs.github.io/
Github: https://github.com/nnsvs/nnsvs
📄Paper: https://arxiv.org/abs/2210.15987v1
Samples by r9y9: https://soundcloud.com/r9y9/sets/dnn-based-singing-voice
Demo: https://www.youtube.com/watch?time_continue=1&v=0sSd31TUVCU&feature=emb_logo&ab_channel=DYVAUX
👉 @bigdata_1
Neural network-based singing voice synthesis library for research
Docs: https://nnsvs.github.io/
Github: https://github.com/nnsvs/nnsvs
📄Paper: https://arxiv.org/abs/2210.15987v1
Samples by r9y9: https://soundcloud.com/r9y9/sets/dnn-based-singing-voice
Demo: https://www.youtube.com/watch?time_continue=1&v=0sSd31TUVCU&feature=emb_logo&ab_channel=DYVAUX
👉 @bigdata_1
⚡2👍1
QuEst: Graph Transformer for Quantum Circuit Reliability Estimation
A PyTorch Library for Quantum Simulation and Quantum Machine Learning.
pip install torchquantum
🖥 Github: https://github.com/mit-han-lab/torchquantum
🗒 Paper: https://arxiv.org/abs/2210.16724v1
➡️ More: https://news.mit.edu/2022/quantum-circuits-robust-noise-0321
👉 @bigdata_1
A PyTorch Library for Quantum Simulation and Quantum Machine Learning.
pip install torchquantum
🖥 Github: https://github.com/mit-han-lab/torchquantum
🗒 Paper: https://arxiv.org/abs/2210.16724v1
➡️ More: https://news.mit.edu/2022/quantum-circuits-robust-noise-0321
👉 @bigdata_1
⚡2👍1
Text-Only Training for Image Captioning using Noise-Injected CLIP
git clone https://github.com/DavidHuji/CapDec && cd CapDec
conda env create -f others/environment.yml
conda activate CapDec
🖥 Github: https://github.com/davidhuji/capdec
🗒 Paper: https://arxiv.org/abs/2211.00575v1
➡️ Dataset: https://paperswithcode.com/dataset/flickrstyle10k
👉 @bigdata_1
git clone https://github.com/DavidHuji/CapDec && cd CapDec
conda env create -f others/environment.yml
conda activate CapDec
🖥 Github: https://github.com/davidhuji/capdec
🗒 Paper: https://arxiv.org/abs/2211.00575v1
➡️ Dataset: https://paperswithcode.com/dataset/flickrstyle10k
👉 @bigdata_1
⚡2👍2
TSM: Temporal Shift Module for Efficient Video Understanding
Github: https://github.com/princeton-nlp/made
Website: https://hanlab.mit.edu/projects/tsm/
Paper: https://arxiv.org/abs/1811.08383
Dataset: https://paperswithcode.com/dataset/squad
👉 @bigdata_1
Github: https://github.com/princeton-nlp/made
Website: https://hanlab.mit.edu/projects/tsm/
Paper: https://arxiv.org/abs/1811.08383
Dataset: https://paperswithcode.com/dataset/squad
👉 @bigdata_1
Competition-Level Code Generation with AlphaCode
Github: https://github.com/deepmind/code_contests
Paper: https://storage.googleapis.com/deepmind-media/AlphaCode/competition_level_code_generation_with_alphacode.pdf
Dataset: https://paperswithcode.com/dataset/humaneval
👉 @bigdata_1
Github: https://github.com/deepmind/code_contests
Paper: https://storage.googleapis.com/deepmind-media/AlphaCode/competition_level_code_generation_with_alphacode.pdf
Dataset: https://paperswithcode.com/dataset/humaneval
👉 @bigdata_1
DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
🖥 Github: https://github.com/luchengthu/dpm-solver
🗒 Paper: https://arxiv.org/abs/2211.01095v1
➡️ Stable-Diffusion: https://github.com/LuChengTHU/dpm-solver/tree/main/example_v2/stable-diffusion
👉 @bigdata_1
🖥 Github: https://github.com/luchengthu/dpm-solver
🗒 Paper: https://arxiv.org/abs/2211.01095v1
➡️ Stable-Diffusion: https://github.com/LuChengTHU/dpm-solver/tree/main/example_v2/stable-diffusion
👉 @bigdata_1
⚡2
AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time
🖥 Github: https://github.com/MVIG-SJTU/AlphaPose
📝 Colab: https://colab.research.google.com/drive/1c7xb_7U61HmeJp55xjXs24hf1GUtHmPs?usp=sharing
🗒 Paper: https://arxiv.org/abs/2211.03375v1
➡️ Dataset: https://paperswithcode.com/dataset/hico-det
👉 @bigdata_1
🖥 Github: https://github.com/MVIG-SJTU/AlphaPose
📝 Colab: https://colab.research.google.com/drive/1c7xb_7U61HmeJp55xjXs24hf1GUtHmPs?usp=sharing
🗒 Paper: https://arxiv.org/abs/2211.03375v1
➡️ Dataset: https://paperswithcode.com/dataset/hico-det
👉 @bigdata_1
⚡2👍1
Media is too big
VIEW IN TELEGRAM
Вы инженер связи, слаботочник или ИТ-шник, или безопасник? Обратите внимание на эту выставку, не пропускаю ее никогда. Мало вообще посещаю мероприятия не-онлайн, но тут делаю исключения.
Точка притяжения для телеком-специалистов, инженеров и сисадминов. Связь, телеком, интернет вещей, ЦОДы и оборудование.
На @sviaz_expocentr вход свободный по электронной регистрации на сайте.
Если ИТ и телекоммуникации ваша работа, увидимся на "Связи" 2024.
👉 @bigdata_1
Точка притяжения для телеком-специалистов, инженеров и сисадминов. Связь, телеком, интернет вещей, ЦОДы и оборудование.
На @sviaz_expocentr вход свободный по электронной регистрации на сайте.
Если ИТ и телекоммуникации ваша работа, увидимся на "Связи" 2024.
👉 @bigdata_1
⚡2
This media is not supported in your browser
VIEW IN TELEGRAM
TAP-Vid: A Benchmark for Tracking Any Point in a Video
🖥 Github: https://github.com/deepmind/tapnet
▶️ Examples: https://github.com/google-research/kubric/tree/main/challenges/point_tracking
🗒 Paper: https://arxiv.org/abs/2211.03726v1
➡️ Dataset: https://paperswithcode.com/dataset/tap-vid
👉 @bigdata_1
🖥 Github: https://github.com/deepmind/tapnet
▶️ Examples: https://github.com/google-research/kubric/tree/main/challenges/point_tracking
🗒 Paper: https://arxiv.org/abs/2211.03726v1
➡️ Dataset: https://paperswithcode.com/dataset/tap-vid
👉 @bigdata_1
⚡1👍1
Unifying Flow, Stereo and Depth Estimation
Model for three motion and 3D perception tasks
conda env create -f conda_environment.yml
conda activate unimatch
🖥 Github: https://github.com/autonomousvision/unimatch
✏️ Project: https://haofeixu.github.io/unimatch/
🔑 Colab: https://colab.research.google.com/drive/1r5m-xVy3Kw60U-m5VB-aQ98oqqg_6cab?usp=sharing
🗒 Paper: https://arxiv.org/abs/2211.05783v1
➡️ Dataset: https://paperswithcode.com/dataset/scannet
👉 @bigdata_1
Model for three motion and 3D perception tasks
conda env create -f conda_environment.yml
conda activate unimatch
🗒 Paper: https://arxiv.org/abs/2211.05783v1
👉 @bigdata_1
Please open Telegram to view this post
VIEW IN TELEGRAM
👍3
Robust Point Cloud Registration Framework Based on Deep Graph Matching(TPAMI Version)
git clone https://github.com/fukexue/RGM.git
conda create -n RGM
conda activate RGM
pip install -r requirements.txt
🖥 Github: https://github.com/fukexue/RGM
🗒 Paper: https://arxiv.org/abs/2211.04696v1
➡️ Dataset: https://paperswithcode.com/dataset/modelnet
👉 @bigdata_1
git clone https://github.com/fukexue/RGM.git
conda create -n RGM
conda activate RGM
pip install -r requirements.txt
🗒 Paper: https://arxiv.org/abs/2211.04696v1
👉 @bigdata_1
Please open Telegram to view this post
VIEW IN TELEGRAM
👍1
DOVER: the Disentangled Objective Video Quality Evaluator
git clone https://github.com/teowu/DOVER.git
cd DOVER
pip install .
🖥 Github: https://github.com/teowu/dover
🗒 Paper: https://arxiv.org/abs/2211.04894v1
➡️ Dataset: https://paperswithcode.com/dataset/youtube-ugc
👉 @bigdata_1
git clone https://github.com/teowu/DOVER.git
cd DOVER
pip install .
🖥 Github: https://github.com/teowu/dover
🗒 Paper: https://arxiv.org/abs/2211.04894v1
➡️ Dataset: https://paperswithcode.com/dataset/youtube-ugc
👉 @bigdata_1
👍2
This media is not supported in your browser
VIEW IN TELEGRAM
Peacasso — это инструмент UI, помогающий создавать изображения из текста с помощью моделей ИИ.
pip install peacasso
Github: https://github.com/victordibia/peacasso
Colab: https://arxiv.org/abs/2211.04894v1
👉 @bigdata_1
pip install peacasso
Github: https://github.com/victordibia/peacasso
Colab: https://arxiv.org/abs/2211.04894v1
👉 @bigdata_1
👍2
Paella
Минималистичная модель генерации изображений из текста, модель позволяет лееегко выполнять различные манипуляции с изображениями.
Github: https://github.com/dome272/paella
Colab: https://colab.research.google.com/drive/1HH5Fey_mTiz29l9dGmHGqZqdzwLpLrxj?usp=sharing
Paper: https://arxiv.org/abs/2211.07292v1
👉 @bigdata_1
Минималистичная модель генерации изображений из текста, модель позволяет лееегко выполнять различные манипуляции с изображениями.
Github: https://github.com/dome272/paella
Colab: https://colab.research.google.com/drive/1HH5Fey_mTiz29l9dGmHGqZqdzwLpLrxj?usp=sharing
Paper: https://arxiv.org/abs/2211.07292v1
👉 @bigdata_1
⚡1👍1
SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observation
Датасет наблюдение за Землей и преобученнная модель из 251 079 мест по всему миру.
Github: https://github.com/zhu-xlab/ssl4eo-s12
📝 Paper: https://arxiv.org/abs/2211.07044v1
Dataset: https://mediatum.ub.tum.de/1660427
👉 @bigdata_1
Датасет наблюдение за Землей и преобученнная модель из 251 079 мест по всему миру.
Github: https://github.com/zhu-xlab/ssl4eo-s12
📝 Paper: https://arxiv.org/abs/2211.07044v1
Dataset: https://mediatum.ub.tum.de/1660427
👉 @bigdata_1
⚡1
Easy Start
On Analyzing the Role of Image for Visual-enhanced Relation Extraction
git clone https://github.com/zjunlp/DeepKE.git
cd DeepKE/example/re/multimodal
Github: https://github.com/zjunlp/DeepKE/tree/main/example/re/multimodal
🗒 Paper: https://arxiv.org/abs/2211.07504v1
Dataset: https://github.com/thecharm/Mega
Pretrained model: https://huggingface.co/openai/clip-vit-base-patch32
👉 @bigdata_1
On Analyzing the Role of Image for Visual-enhanced Relation Extraction
git clone https://github.com/zjunlp/DeepKE.git
cd DeepKE/example/re/multimodal
Github: https://github.com/zjunlp/DeepKE/tree/main/example/re/multimodal
🗒 Paper: https://arxiv.org/abs/2211.07504v1
Dataset: https://github.com/thecharm/Mega
Pretrained model: https://huggingface.co/openai/clip-vit-base-patch32
👉 @bigdata_1
⚡2
Versatile Diffusion: Text, Images and Variations All in One Diffusion Model
VD поддерживает преобразование изображения в текст, изменение изображения, преобразование текста в изображение и генерацию текста Будущие версии будут поддерживать речь, музыку, видео и 3D. Универсальная диффузия: текст, изображения и вариации — все в одной модели.
Github: https://github.com/shi-labs/versatile-diffusion
🗒 Paper: https://arxiv.org/abs/2211.08332v1
Demo: https://huggingface.co/spaces/shi-labs/Versatile-Diffusion
Dataset: https://github.com/rom1504/img2dataset
👉 @bigdata_1
VD поддерживает преобразование изображения в текст, изменение изображения, преобразование текста в изображение и генерацию текста Будущие версии будут поддерживать речь, музыку, видео и 3D. Универсальная диффузия: текст, изображения и вариации — все в одной модели.
Github: https://github.com/shi-labs/versatile-diffusion
🗒 Paper: https://arxiv.org/abs/2211.08332v1
Demo: https://huggingface.co/spaces/shi-labs/Versatile-Diffusion
Dataset: https://github.com/rom1504/img2dataset
👉 @bigdata_1
⚡2🔥1
ActionFormer: Localizing Moments of Actions with Transformers
Github: https://github.com/happyharrycn/actionformer_release
Features and Annotations: https://drive.google.com/file/d/1JKh3w14ngAjgzuuP22BnjhkhIcBSqteJ/view?usp=sharing
🗒 Pre-trained Model: https://arxiv.org/abs/2211.09074v1
Dataset: https://paperswithcode.com/dataset/kinetics
👉 @bigdata_1
Github: https://github.com/happyharrycn/actionformer_release
Features and Annotations: https://drive.google.com/file/d/1JKh3w14ngAjgzuuP22BnjhkhIcBSqteJ/view?usp=sharing
🗒 Pre-trained Model: https://arxiv.org/abs/2211.09074v1
Dataset: https://paperswithcode.com/dataset/kinetics
👉 @bigdata_1
⚡2👍1