ShortScience.org

A platform for post-publication discussion aiming to improve accessibility and reproducibility of research ideas.
Directed by @josephpaulcohen

[ShortScience.org @shortscienceorg]

Object-Centric Learning with Slot Attention (Summary by ngthanhtinqn) https://t.co/jrKrAwYfZ6 #shortscience

[ShortScience.org @shortscienceorg]

CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition (Summary by ngthanhtinqn) https://t.co/v7SDuUObJ9 #shortscience

[ShortScience.org @shortscienceorg]

Women also Snowboard: Overcoming Bias in Captioning Models (Extended Abstract) (Summary by ngthanhtinqn) https://t.co/3L80yvRvT0 #shortscience

[ShortScience.org @shortscienceorg]

FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations (Summary by ngthanhtinqn) https://t.co/BJfU6QLB4v #shortscience

[ShortScience.org @shortscienceorg]

Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification (Summary by ngthanhtinqn) https://t.co/I1o2SDCoEw #shortscience

[ShortScience.org @shortscienceorg]

Do Vision-Language Pretrained Models Learn Composable Primitive Concepts? (Summary by ngthanhtinqn) https://t.co/cWdAClaIKL #shortscience

[ShortScience.org @shortscienceorg]

BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models (Summary by ngthanhtinqn) https://t.co/rYRFcVJOCt #shortscience

[ShortScience.org @shortscienceorg]

Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition (Summary by ngthanhtinqn) https://t.co/DBAkgyZdRZ #shortscience

[ShortScience.org @shortscienceorg]

Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP (Summary by ngthanhtinqn) https://t.co/cyreQZR1Ly #shortscience

[ShortScience.org @shortscienceorg]

Learning to Count Objects in Natural Images for Visual Question Answering (Summary by ngthanhtinqn) https://t.co/5smVPA9c6Y #shortscience

[ShortScience.org @shortscienceorg]

Global Context Vision Transformers (Summary by ngthanhtinqn) https://t.co/6kuEJIi6Kn #shortscience

[ShortScience.org @shortscienceorg]

CLIP-Event: Connecting Text and Images with Event Structures (Summary by ngthanhtinqn) https://t.co/Po1D7tWJXt #shortscience

[ShortScience.org @shortscienceorg]

UNITER: UNiversal Image-TExt Representation Learning (Summary by ngthanhtinqn) https://t.co/GW4k5hHkWD #shortscience

[ShortScience.org @shortscienceorg]

STAIR: Learning Sparse Text and Image Representation in Grounded Tokens (Summary by ngthanhtinqn) https://t.co/1chEGYNhOk #shortscience

[ShortScience.org @shortscienceorg]

Compressive Transformers for Long-Range Sequence Modelling (Summary by CodyWild) https://t.co/HWw11WgBXm #shortscience

[ShortScience.org @shortscienceorg]

Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity (Summary by CodyWild) https://t.co/AJ7THjb8WN #shortscience

[ShortScience.org @shortscienceorg]

View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose (Summary by CodyWild) https://t.co/X5JnhYwAx7 #shortscience

[ShortScience.org @shortscienceorg]

Communication-Efficient Learning of Deep Networks from Decentralized Data (Summary by CodyWild) https://t.co/Aaak4wrXX0 #shortscience

[ShortScience.org @shortscienceorg]

VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text (Summary by CodyWild) https://t.co/PwOkw0eQlH #shortscience

[ShortScience.org @shortscienceorg]

Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation (Summary by CodyWild) https://t.co/5SA0RcFoTA #shortscience