Activating More Pixels in Image Super-Resolution Transformer

A python package to discover SDE equation from time-series data.

Code: https://github.com/chxy95/hat

Paper: https://arxiv.org/abs/2205.04437v1

Dataset: https://paperswithcode.com/dataset/bsd

@ArtificialIntelligencedl

Хочешь знать, как устроена DALL-E 2?
На что способен GPT-3?
Какие нейросети используются для поиска новых лекарств?

Тогда тебе на канал DLStories!

На канале вы найдете:
- разборы новых архитектур;
- новости из мира AI и Deep Learning;
- ссылки на обучающие курсы, подкасты и статьи;

Также у автора канала есть свой подкаст Deep Learning Stories об исследованиях в сфере AI. Следите за выходом новых эпизодов на канале! 🎧⬇️

@dl_stories

❔ Just Ask: Learning to Answer Questions from Millions of Narrated Videos

Code: https://github.com/antoyang/just-ask

Paper: https://arxiv.org/abs/2205.05019v1

Dataset: https://paperswithcode.com/dataset/webvidvqa3m

@ArtificialIntelligencedl

Shadow-Aware Dynamic Convolution for Shadow Removal

Shadow-Aware Dynamic Convolution (SADC) to resolve the contradiction between the shadow region and non-shadow region for shadow removal. Please refer to the paper for details.

Code: https://github.com/xuyimin0926/sadc

Paper: https://arxiv.org/abs/2205.04908v1

Dataset: https://paperswithcode.com/dataset/istd

@ArtificialIntelligencedl

Group R-CNN for Point-based Weakly Semi-supervised Object Detection

Code: https://github.com/jshilong/grouprcnn

Paper: https://arxiv.org/abs/2205.05920v1

Dataset: https://paperswithcode.com/dataset/coco

@ArtificialIntelligencedl

Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model

Low complexity implementation of the WaveRNN-based LPCNet algorithm

Github: https://github.com/xiph/lpcnet

Paper: https://arxiv.org/abs/2205.05785v1

OpenSLR: https://www.openslr.org/

@ArtificialIntelligencedl

📝 Automated Crossword Solving

Pretrained models, precomputed FAISS embeddings, and a crossword clue-answer dataset.

Github: https://github.com/albertkx/berkeley-crossword-solver

Paper: https://arxiv.org/abs/2205.09665v1

Dataset: https://www.xwordinfo.com/JSON/

[RK-Net]Joint Representation Learning and Keypoint Detection for Cross-view Geo-localization

Github: https://github.com/AggMan96/RK-Net

Paper: https://zhunzhong.site/paper/RK_Net.pdf

Dataset: https://paperswithcode.com/dataset/university-1652

@ArtificialIntelligencedl

AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modeling

First VAE framework empowered with adaptive GPT-2s (AdaVAE).

Github: https://github.com/ImKeTT/adavae

Paper: https://arxiv.org/abs/2205.05862v1

Task: https://paperswithcode.com/task/representation-learning

@ArtificialIntelligencedl

KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning

Github: https://github.com/explainableml/kg-sp

Paper: https://arxiv.org/abs/2205.06784v1

Dataset: https://paperswithcode.com/dataset/conceptnet

@ArtificialIntelligencedl

Experiments on Generalizability of User-Oriented Fairness in Recommender Systems.

Github: https://github.com/rahmanidashti/fairrecsys

Paper: https://arxiv.org/abs/2205.08289v1

Dataset: https://paperswithcode.com/dataset/movielens

@ArtificialIntelligencedl

Towards Unified Keyframe Propagation Models

A two-stream approach, where high-frequency features interact locally and low-frequency features interact globally.

Github: https://github.com/runwayml/guided-inpainting

Paper: https://arxiv.org/abs/2205.09731v1

Dataset: https://paperswithcode.com/dataset/places

@ArtificialIntelligencedl

🖇 A graph-transformer for whole slide image classification

Graph-Transformer (GT) that fuses a graph-based representation of an WSI and a vision transformer for processing pathology images.

Github: https://github.com/vkola-lab/tmi2022

Paper: https://arxiv.org/abs/2205.09671v1

Dataset: https://paperswithcode.com/dataset/imagenet

@ArtificialIntelligencedl

RankGen - Improving Text Generation with Large Ranking Models

RankGen is a 1.2 billion encoder model which maps prefixes and generations from any language model (in continutation to the prefix) to a shared vector space.

Github: https://github.com/martiansideofthemoon/rankgen

Paper: https://arxiv.org/abs/2205.09726

Dataset: https://paperswithcode.com/dataset/imagenet

@ArtificialIntelligencedl

⚡️ Structured Attention Composition for Temporal Action Localization

Online action detection and effective and efficient exemplar-consultation mechanism

Github: https://github.com/vividle/online-action-detection

Paper: https://arxiv.org/abs/2205.09956v1

Dataset: https://paperswithcode.com/dataset/places

@ArtificialIntelligencedl

Full camouflage fixation training dataset is available!

The full camouflage fixation training dataset is available with the full fixation maps for the COD10K training dataset, which can be downloaded from: https://drive.google.com/file/d/1inb5iNTDswFPDm4SpzBbVgZdI4puAv_3/view?usp=sharing

Github: https://github.com/JingZhang617/COD-Rank-Localize-and-Segment

Paper: https://arxiv.org/abs/2205.11333v1

Dataset: https://paperswithcode.com/dataset/salicon

@ArtificialIntelligencedl

ASSET: Autoregressive Semantic Scene Editing with Transformers at High Resolutions

Github: https://github.com/difanliu/asset

Paper: https://arxiv.org/abs/2205.12231v1

Dataset: https://paperswithcode.com/dataset/ade20k

Pretrained model: https://www.dropbox.com/s/5kyov71ko340ra0/landscape.zip?dl=0

@ArtificialIntelligencedl

Recipe for a General, Powerful, Scalable Graph Transformer

Github: https://github.com/rampasek/GraphGPS

Paper: https://arxiv.org/abs/2205.12454v1

Dataset: https://paperswithcode.com/dataset/malnet

@ArtificialIntelligencedl

On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition

Github: https://github.com/KingJamesSong/DifferentiableSVD

Paper: https://arxiv.org/abs/2205.13282v1

Dataset: https://paperswithcode.com/dataset/imagenet

@ArtificialIntelligencedl

SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation

Github: https://github.com/wangzy22/SemAffiNet

Paper: https://arxiv.org/abs/2205.13490v1

Dataset: https://paperswithcode.com/dataset/cityscapes

@ArtificialIntelligencedl