We lifted 2 functions out of this paper's own repositories and ran 0 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 |
|---|---|---|
| mengyuest/AR-Net | canonical | 0 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| cal_eff | Not yet run | mengyuest/AR-Net/main_base.py code served (permissive licence) · get_code("4aee3a031e58edff") |
| reverse_onehot | Not yet run | mengyuest/AR-Net/main_base.py code served (permissive licence) · get_code("c7ad8599cf77128d") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Action recognition is an open and challenging problem in computer vision. While current state-of-the-art models offer excellent recognition results, their computational expense limits their impact for many real-world applications. In this paper, we propose a novel approach, called AR-Net (Adaptive Resolution Network), that selects on-the-fly the optimal resolution for each frame conditioned on the input for efficient action recognition in long untrimmed videos. Specifically, given a video frame, a policy network is used to decide what input resolution should be used for processing by the action recognition model, with the goal of improving both accuracy and efficiency. We efficiently train the policy network jointly with the recognition model using standard back-propagation. Extensive experiments on several challenging action recognition benchmark datasets well demonstrate the efficacy of our proposed approach over state-of-the-art methods. The project page can be found at https://mengyuest.github.io/AR-Net
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2007.15796")
get_code_for_paper("2007.15796")
have("2007.15796")
Connect an agent — have() is free.