Ali Farhadi, Roozbeh Mottaghi, Kiana Ehsani, Daniel Gordon, Thomas Nguyen
We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| ehsanik/muscleTorch | — | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| FeatureLearnerModule | Ran | ehsanik/muscleTorch/models/feature_learning.py pointer only (licence: NONE) · get_code("e0742f6c18dac9e8") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Learning effective representations of visual data that generalize to a variety of downstream tasks has been a long quest for computer vision. Most representation learning approaches rely solely on visual data such as images or videos. In this paper, we explore a novel approach, where we use human interaction and attention cues to investigate whether we can learn better representations compared to visualonly representations. For this study, we collect a dataset of human interactions capturing body part movements and gaze in their daily lives. Our experiments show that our "muscly-supervised" representation that encodes interaction and attention cues outperforms a visual-only state-of-the-art method MoCo (He et al., 2020), on a variety of target tasks: scene classification (semantic), action recognition (temporal), depth estimation (geometric), dynamics prediction (physics) and walkable surface estimation (affordance). Our code and dataset are available at: https://github.com/ehsanik/muscleTorch.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2010.08539")
get_code_for_paper("2010.08539")
have("2010.08539")
Connect an agent — have() is free.