🌐 DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings
Code: https://github.com/voidism/diffcse
Paper: https://arxiv.org/abs/2204.10298v1
Dataset: https://paperswithcode.com/dataset/sst
@ArtificialIntelligencedl
Code: https://github.com/voidism/diffcse
Paper: https://arxiv.org/abs/2204.10298v1
Dataset: https://paperswithcode.com/dataset/sst
@ArtificialIntelligencedl
👍5🔥1
🤖 Transformer-Rankers
Transformer-rankers is a library to conduct ranking experiments with transformers.
Code: https://github.com/Guzpenha/transformer_rankers
Paper: https://arxiv.org/abs/2204.10558v1
Colab: https://colab.research.google.com/drive/1wGmaO3emC7Sg-tA7nGehIQ2vjOLN9S5e?usp=sharing
@ArtificialIntelligencedl
Transformer-rankers is a library to conduct ranking experiments with transformers.
Code: https://github.com/Guzpenha/transformer_rankers
Paper: https://arxiv.org/abs/2204.10558v1
Colab: https://colab.research.google.com/drive/1wGmaO3emC7Sg-tA7nGehIQ2vjOLN9S5e?usp=sharing
@ArtificialIntelligencedl
👍4
This media is not supported in your browser
VIEW IN TELEGRAM
🚰 Simulating Fluids in Real-World Still Images
surface-based layered representation(SLR), which decomposes the fluid and the static objects in the scene, to better synthesize the animated videos from a single fluid imagе
Code: https://github.com/generalizable-neural-performer/gnr
Paper: https://arxiv.org/abs/2204.11335
Project: https://simulatingfluids.github.io/
@ArtificialIntelligencedl
surface-based layered representation(SLR), which decomposes the fluid and the static objects in the scene, to better synthesize the animated videos from a single fluid imagе
Code: https://github.com/generalizable-neural-performer/gnr
Paper: https://arxiv.org/abs/2204.11335
Project: https://simulatingfluids.github.io/
@ArtificialIntelligencedl
🥰6👍1
⏱ Cross Pairwise Ranking for Unbiased Item Recommendation
Code: https://github.com/Qcactus/CPR
Paper: https://arxiv.org/abs/2204.12176v1
@ArtificialIntelligencedl
Code: https://github.com/Qcactus/CPR
Paper: https://arxiv.org/abs/2204.12176v1
@ArtificialIntelligencedl
🌎 Grasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-dimensional Latent Spaces from StyleGAN
Code: https://github.com/wuqiuche/micromotion-stylegan
Paper: https://arxiv.org/abs/2204.12696v1
Project: https://wuqiuche.github.io/micromotion-project-page/
@ArtificialIntelligencedl
Code: https://github.com/wuqiuche/micromotion-stylegan
Paper: https://arxiv.org/abs/2204.12696v1
Project: https://wuqiuche.github.io/micromotion-project-page/
@ArtificialIntelligencedl
👍3
🌱 NeurMips: Neural Mixture of Planar Experts for View Synthesis
A novel planar-based scene representation for modeling geometry and appearance
Code: https://github.com/zhihao-lin/neurmips
Paper: https://arxiv.org/abs/2204.13696
Project: https://zhihao-lin.github.io/neurmips/
Video: https://youtu.be/PV1dCTWL5Oo
Dataset: https://paperswithcode.com/dataset/replica
@ArtificialIntelligencedl
A novel planar-based scene representation for modeling geometry and appearance
Code: https://github.com/zhihao-lin/neurmips
Paper: https://arxiv.org/abs/2204.13696
Project: https://zhihao-lin.github.io/neurmips/
Video: https://youtu.be/PV1dCTWL5Oo
Dataset: https://paperswithcode.com/dataset/replica
@ArtificialIntelligencedl
🥰3❤1👏1
Struct-MDC: Mesh-Refined Unsupervised Depth Completion Leveraging Structural Regularities from Visual SLAM
The proposed methodology creates a convex hull region by performing constrained Delaunay triangulation with depth interpolation using line features.
Code: https://github.com/url-kaist/Struct-MDC
Paper: https://arxiv.org/abs/2204.13877v1
Dataset: https://paperswithcode.com/dataset/plad-1
@ArtificialIntelligencedl
The proposed methodology creates a convex hull region by performing constrained Delaunay triangulation with depth interpolation using line features.
Code: https://github.com/url-kaist/Struct-MDC
Paper: https://arxiv.org/abs/2204.13877v1
Dataset: https://paperswithcode.com/dataset/plad-1
@ArtificialIntelligencedl
🧷 Quality-Aware Decoding
Code: https://github.com/deep-spin/qaware-decode
Paper: https://arxiv.org/abs/2205.00978v1
@ArtificialIntelligencedl
Code: https://github.com/deep-spin/qaware-decode
Paper: https://arxiv.org/abs/2205.00978v1
@ArtificialIntelligencedl
🥰3👍2👏1
Forwarded from Machinelearning
🔝 OPT (Open Pre-trained Transformers) is a family of NLP models trained on billions of tokens of text obtained from the internet.
175B GPT-3
Github: https://github.com/facebookresearch/metaseq
Instructions: https://github.com/facebookresearch/metaseq/blob/main/docs/setup.md
Paper: https://arxiv.org/abs/2205.01068v2
Dataset: https://paperswithcode.com/dataset/superglue
@ai_machinelearning_big_data
175B GPT-3
Github: https://github.com/facebookresearch/metaseq
Instructions: https://github.com/facebookresearch/metaseq/blob/main/docs/setup.md
Paper: https://arxiv.org/abs/2205.01068v2
Dataset: https://paperswithcode.com/dataset/superglue
@ai_machinelearning_big_data
❤5👍1🔥1
📹 Deep Video Harmonization with Color Mapping Consistency
Code: https://github.com/deep-spin/qaware-decode
Paper: https://arxiv.org/abs/2205.00687v1
Dataset: https://github.com/bcmi/Video-Harmonization-Dataset-HYouTube.
@ArtificialIntelligencedl
Code: https://github.com/deep-spin/qaware-decode
Paper: https://arxiv.org/abs/2205.00687v1
Dataset: https://github.com/bcmi/Video-Harmonization-Dataset-HYouTube.
@ArtificialIntelligencedl
👍5
🔎 Cross-view Transformers for real-time Map-view Semantic Segmentation
Code: https://github.com/bradyz/cross_view_transformers
Paper: https://arxiv.org/abs/2205.02833v1
Dataset: https://paperswithcode.com/dataset/nuscenes
@ArtificialIntelligencedl
Code: https://github.com/bradyz/cross_view_transformers
Paper: https://arxiv.org/abs/2205.02833v1
Dataset: https://paperswithcode.com/dataset/nuscenes
@ArtificialIntelligencedl
❤5👍1
☑️ TorchSSL
A Pytorch-based toolbox for semi-supervised learning.
Code: https://github.com/torchssl/torchssl
Paper: https://arxiv.org/abs/2205.07246v1
Logs and weights: https://onedrive.live.com/?authkey=%21AJ%2DwKMa%2DENcbk1s&id=AF426F3217F6565A%213488&cid=AF426F3217F6565A
A Pytorch-based toolbox for semi-supervised learning.
Code: https://github.com/torchssl/torchssl
Paper: https://arxiv.org/abs/2205.07246v1
Logs and weights: https://onedrive.live.com/?authkey=%21AJ%2DwKMa%2DENcbk1s&id=AF426F3217F6565A%213488&cid=AF426F3217F6565A
👍5👎1
Python Data Driven Dynamics
A python package to discover SDE equation from time-series data.
Code: https://github.com/tee-lab/pydaddy
Paper: https://arxiv.org/abs/2205.02645v1
@ArtificialIntelligencedl
A python package to discover SDE equation from time-series data.
Code: https://github.com/tee-lab/pydaddy
Paper: https://arxiv.org/abs/2205.02645v1
@ArtificialIntelligencedl
👍7
🤖 Neural 3D Scene Reconstruction with the Manhattan-world Assumption
Code: https://github.com/zju3dv/manhattan_sdf
Paper: https://arxiv.org/abs/2205.02836
Project Page: https://zju3dv.github.io/manhattan_sdf
Video: https://www.youtube.com/watch?v=oEE7mK0YQtc
@ArtificialIntelligencedl
Code: https://github.com/zju3dv/manhattan_sdf
Paper: https://arxiv.org/abs/2205.02836
Project Page: https://zju3dv.github.io/manhattan_sdf
Video: https://www.youtube.com/watch?v=oEE7mK0YQtc
@ArtificialIntelligencedl
👍2❤1
⚡️ EmotionFlow: Capture the Dialogue Level Emotion Transitions
Code: https://github.com/fpcsong/emotionflow
Paper: https://arxiv.org/abs/2204.10298v1
Dataset: https://paperswithcode.com/dataset/meld
@ArtificialIntelligencedl
Code: https://github.com/fpcsong/emotionflow
Paper: https://arxiv.org/abs/2204.10298v1
Dataset: https://paperswithcode.com/dataset/meld
@ArtificialIntelligencedl
👍5
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
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
👍2
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
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
👍6👎1
❔ 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
Code: https://github.com/antoyang/just-ask
Paper: https://arxiv.org/abs/2205.05019v1
Dataset: https://paperswithcode.com/dataset/webvidvqa3m
@ArtificialIntelligencedl
👍1
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
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
👍5
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
Code: https://github.com/jshilong/grouprcnn
Paper: https://arxiv.org/abs/2205.05920v1
Dataset: https://paperswithcode.com/dataset/coco
@ArtificialIntelligencedl