Baidu-UTS Submission to the EPIC-Kitchens Action Recognition Challenge 2019
arXiv:1906.09383
Abstract
In this report, we present the Baidu-UTS submission to the EPIC-Kitchens Action Recognition Challenge in CVPR 2019. This is the winning solution to this challenge. In this task, the goal is to predict verbs, nouns, and actions from the vocabulary for each video segment. The EPIC-Kitchens dataset contains various small objects, intense motion blur, and occlusions. It is challenging to locate and recognize the object that an actor interacts with. To address these problems, we utilize object detection features to guide the training of 3D Convolutional Neural Networks (CNN), which can significantly improve the accuracy of noun prediction. Specifically, we introduce a Gated Feature Aggregator module to learn from the clip feature and the object feature. This module can strengthen the interaction between the two kinds of activations and avoid gradient exploding. Experimental results demonstrate our approach outperforms other methods on both seen and unseen test set.
References in corpus (8)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Two-Stream Convolutional Networks for Action Recognition in Videos
- YouTube-8M: A Large-Scale Video Classification Benchmark
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
- Learnable pooling with Context Gating for video classification
- Object Level Visual Reasoning in Videos
- FASTER Recurrent Networks for Efficient Video Classification
Cited by in corpus (7)
- Video Action Understanding
- What Makes Training Multi-Modal Classification Networks Hard?
- Video Understanding as Machine Translation
- In the Eye of the Beholder: Gaze and Actions in First Person Video
- Symbiotic Attention with Privileged Information for Egocentric Action Recognition
- Supervision Levels Scale (SLS)
- A Prospective Study on Sequence-Driven Temporal Sampling and Ego-Motion Compensation for Action Recognition in the EPIC-Kitchens Dataset