Search Results
Adaptive Computation with Elastic Input Sequence
However, most standard neural networks have the same function type and fixed computation budget on different samples regardless of their nature and difficulty.
Token Turing Machines
google-research/scenic
•
•
CVPR 2023
The model's memory module ensures that a new observation will only be processed with the contents of the memory (and not the entire history), meaning that it can efficiently process long sequences with a bounded computational cost at each step.
Ranked #1 on
Action Detection
on Charades
Multiview Transformers for Video Recognition
google-research/scenic
•
•
CVPR 2022
Video understanding requires reasoning at multiple spatiotemporal resolutions -- from short fine-grained motions to events taking place over longer durations.
Ranked #2 on
Action Recognition
on EPIC-KITCHENS-100
(using extra training data)
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
In this paper, we introduce a novel visual representation learning which relies on a handful of adaptively learned tokens, and which is applicable to both image and video understanding tasks.
Ranked #1 on
Action Classification
on Charades
ViViT: A Video Vision Transformer
google-research/scenic
•
•
ICCV 2021
We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification.
Ranked #8 on
Action Classification
on Moments in Time
(Top 5 Accuracy metric, using extra
training data)
Location-Aware Self-Supervised Transformers for Semantic Segmentation
Pixel-level labels are particularly expensive to acquire.
Learning with Neighbor Consistency for Noisy Labels
google-research/scenic
•
•
CVPR 2022
Recent advances in deep learning have relied on large, labelled datasets to train high-capacity models.
SCENIC: A JAX Library for Computer Vision Research and Beyond
google-research/scenic
•
•
CVPR 2022
Scenic is an open-source JAX library with a focus on Transformer-based models for computer vision research and beyond.
