Artificial Intelligence
16.3K subscribers
1.09K photos
7 videos
1 file
1.95K links
Artificial Intelligence

admin - @haarrp

@itchannels_telegram - 🔥 best it channels

@ai_machinelearning_big_data - Machine learning channel

@pythonl - Our Python channel

@pythonlbooks- python книги📚

@datascienceiot - ml 📚

РКН: clck.ru/3FmwZw
Download Telegram
Robust Reflection Removal with Reflection-free Flash-only Cues (RFC)

conda env create -f environment.yml
conda activate flashrr-rfc
bash download.sh
python test.py


🖥 Github: https://github.com/ChenyangLEI/flash-reflection-removal

🗒 Paper: https://arxiv.org/abs/2211.02914v1

⭐️ Project: https://chenyanglei.github.io/flashrr_rfc/index.html

➡️ Dataset: https://hkustconnect-my.sharepoint.com/:u:/g/personal/cleiaa_connect_ust_hk/EWv1afaxrhFKlbT7iX0b8FMB8R1ZeNyUWRQM__A_SPkVGQ?e=8IbhE6

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
👍63🔥1
💬 MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation

🖥 Github: https://github.com/victorsungo/mmdialog

🗒 Paper: https://arxiv.org/abs/2211.05719v1

➡️ Dataset: https://paperswithcode.com/dataset/openvidial

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
4👍3🔥1
⭐️ MACSum: Controllable Summarization with Mixed Attributes

MACSum is the first human-annotated summarization dataset for controlling mixed attributes.

🖥 Github: https://github.com/psunlpgroup/macsum

🗒 Paper: https://arxiv.org/abs/2211.05041v1

➡️ Dataset: https://paperswithcode.com/dataset/macsum

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
👍42🔥1
✔️ PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping

🖥 Github: https://github.com/mindslab-ai/phaseaug

🗒 Paper: https://arxiv.org/abs/2211.04610v1

➡️ Dataset: https://keithito.com/LJ-Speech-Dataset/

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
👍43🔥1
⭐️ Nebullvm

nebullvm is an open-source tool designed to speed up AI inference in just a few lines of code.

🖥 Github: https://github.com/nebuly-ai/nebullvm

🗒 Docs: https://nebuly.gitbook.io/nebuly/nebullvm/installation

➡️ Notebooks: https://github.com/nebuly-ai/nebullvm/tree/main/notebooks

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
5🔥3👍2
⭐️ MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction

🖥 Github: https://paperswithcode.com/paper/maven-ere-a-unified-large-scale-dataset-for

🗒 Paper: https://arxiv.org/abs/2211.07342v1

➡️ Dataset: https://paperswithcode.com/dataset/maven

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
👍6🔥31
MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets

git clone https://github.com/pytorch/fairseq
cd fairseq
pip install --editable ./
git clone https://github.com/ddlBoJack/MT4SSL


🖥 Github: https://github.com/ddlbojack/mt4ssl

🗒 Paper: https://arxiv.org/abs/2211.07321v1

➡️ Dataset: https://paperswithcode.com/dataset/librispeech

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
👍61🔥1
🖥 MAGE PyTorch Implementation

git clone https://github.com/LTH14/mage.git
cd mage


🖥 Github: https://github.com/lth14/mage

🗒 Paper: https://arxiv.org/abs/2211.09117v1

➡️ Dataset: https://image-net.org/download

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
5👍3🔥1
🖥 Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks

🖥 Github: https://github.com/fundamentalvision/Uni-Perceiver

🗒 Paper: https://arxiv.org/abs/2211.09808v1

➡️ Data: https://github.com/fundamentalvision/Uni-Perceiver/blob/main/data/prepare_data.md

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
5👍1🥰1
⭐️UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer

🖥 Github: https://github.com/OpenGVLab/UniFormerV2

🗒 Paper: https://arxiv.org/abs/2211.09552v1

➡️ Dataset: https://paperswithcode.com/dataset/hacs
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
4👍2🥰1
✔️ CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval

🖥 Github: https://github.com/facebookresearch/dpr-scale

🗒 Paper: https://arxiv.org/abs/2211.10411v1

➡️ Dataset: https://paperswithcode.com/dataset/ms-marco

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
👍51👎1🔥1🥰1
⭐️ Traffic4cast 2022 Competition: from few public vehicle counters to entire city-wide traffic

🖥 Github: https://github.com/iarai/neurips2022-traffic4cast

🗒 Paper: https://arxiv.org/abs/2211.09984v1

➡️ Dataset: https://developer.here.com/sample-data

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
4👍2👎1🔥1
Please open Telegram to view this post
VIEW IN TELEGRAM
3👍2🥰1
Please open Telegram to view this post
VIEW IN TELEGRAM
5👍2🔥2
На международной онлайн-конфереции про искусственный интеллек AI Journey ученые и эксперты области обсуждают самые разные темы. Одна из них — применение нелинейных ядер.

Интересное мнение по этому поводу высказал Дмитрий Девяткин, научный сотрудник Института системного программирования РАН:

«Эксперименты показали, что применение нелинейных ядер позволяет на ряде наборов данных улучшить качество классификации. Используемый метод усиления и снижения сложности ансамбля деревьев решений показал свою применимость для улучшения ансамблей деревьев решений с линейными и нелинейными разделителями. Тем не менее было отмечено, что при построении нелинейных разделителей на больших наборах данных скорость всё-таки недостаточная для анализа больших данных, поэтому актуальной осталась задача разработки вычислительно эффективных методов двойственной оптимизации при условии масштабирования переменных невязки».
👍4
Please open Telegram to view this post
VIEW IN TELEGRAM
👍6🔥21
👣 Flow: Joint Semantic and Style Editing of Facial Images

git clone https://github.com/visinf/s2-flow.git
cd s2-flow/


🖥 Github: https://github.com/visinf/s2-flow

🗒 Paper: https://arxiv.org/abs/2211.12209

➡️ Dataset: https://drive.google.com/drive/folders/1nZ_U0qCFFwBM9L_h9mmV9W0axFt4Xd-N?usp=sharing


@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
4👍1🔥1
⭐️ Texts as Images in Prompt Tuning for Multi-Label Image Recognition

🖥 Github: https://github.com/guozix/tai-dpt

🗒 Paper: https://arxiv.org/abs/2211.12739v1

➡️ Dataset: https://paperswithcode.com/dataset/nus-wide

@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
👍31🔥1