Search Results for author:
Found 10 papers, 5 papers with code
Dr$^2$Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning
We use two coefficients on either type of residual connections respectively, and introduce a dynamic training strategy that seamlessly transitions the pretrained model to a reversible network with much higher numerical precision.
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
In this paper, we reduce the memory consumption for end-to-end training, and manage to scale up the TAD backbone to 1 billion parameters and the input video to 1, 536 frames, leading to significant detection performance.
Ranked #1 on
Temporal Action Localization
on EPIC-KITCHENS-100
Mindstorms in Natural Language-Based Societies of Mind
What should be the social structure of an NLSOM?
Boundary-Denoising for Video Activity Localization
To alleviate the boundary ambiguity, we propose to study the video activity localization problem from a denoising perspective.
Ranked #1 on
Video Grounding
on MAD
Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition
Although backdoor attacks have been extensively studied in the image domain, there are very few works that explore such attacks in the video domain, and they tend to conclude that image backdoor attacks are less effective in the video domain.
Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization
Temporal action localization (TAL) requires long-form reasoning to predict actions of various durations and complex content.
Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization
Temporal action localization (TAL) requires long-form reasoning to predict actions of various durations and complex content.
ETAD: Training Action Detection End to End on a Laptop
We propose to sequentially forward the snippet frame through the video encoder, and backward only a small necessary portion of gradients to update the encoder.
Hybrid Attention Networks for Flow and Pressure Forecasting in Water Distribution Systems
Specifically, a hybrid spatial attention mechanism that employs inputs along temporal and spatial axes is proposed.
Multi-Granularity Fusion Network for Proposal and Activity Localization: Submission to ActivityNet Challenge 2019 Task 1 and Task 2
This technical report presents an overview of our solution used in the submission to ActivityNet Challenge 2019 Task 1 (\textbf{temporal action proposal generation}) and Task 2 (\textbf{temporal action localization/detection}).
