Aggregating Frame-level Features for Large-Scale Video Classification

2017-07-04 · Shaoxiang Chen, Xi Wang, Yongyi Tang, Xinpeng Chen, Zuxuan Wu, Yu-Gang Jiang

This paper introduces the system we developed for the Google Cloud & YouTube-8M Video Understanding Challenge, which can be considered as a multi-label classification problem defined on top of the large scale YouTube-8M Dataset. We employ a large set of techniques to aggregate the provided frame-level feature representations and generate video-level predictions, including several variants of recurrent neural networks (RNN) and generalized VLAD. We also adopt several fusion strategies to explore the complementarity among the models. In terms of the official metric GAP@20 (global average precision at 20), our best fusion model attains 0.84198 on the public 50\% of test data and 0.84193 on the private 50\% of test data, ranking 4th out of 650 teams worldwide in the competition.

📄 PDF Abstract BibTeX arXiv:1707.00803

Code (0)

등록된 구현이 없습니다.

Tasks

Classification General Classification Multi-Label Classification MUlTI-LABEL-ClASSIFICATION Video ClassificationVideo Understanding

NeXtVLAD: An Efficient Neural Network to Aggregate Frame-level Features for Large-scale Video Classification

2018-11-12 · Rongcheng Lin, Jing Xiao, Jianping Fan

This paper introduces a fast and efficient network architecture, NeXtVLAD, to aggregate frame-level features into a compact feature vector for large-scale video classification. Briefly speaking, the basic idea is to deco…

Efficient Neural Network General Classification Video Classification Video Understanding

Fully Motion-Aware Network for Video Object Detection

2018-09-01 · ECCV 2018 9 · Shiyao Wang, Yucong Zhou, Junjie Yan, Zhidong Deng

Video objection detection is challenging in the presence of appearance deterioration in certain video frames. One of typical solutions is to enhance per-frame features through aggregating neighboring frames. But the fea…

Object object-detection Object Detection Video Object Detection

Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection

2017-08-07 · ICCV 2017 10 · Pingping Zhang, Dong Wang, Huchuan Lu, Hongyu Wang 외

Fully convolutional neural networks (FCNs) have shown outstanding performance in many dense labeling problems. One key pillar of these successes is mining relevant information from features in convolutional layers. Howev…

Object object-detection Object Detection RGB Salient Object Detection+1

Learnable pooling with Context Gating for video classification

2017-06-21 · Antoine Miech, Ivan Laptev, Josef Sivic

Current methods for video analysis often extract frame-level features using pre-trained convolutional neural networks (CNNs). Such features are then aggregated over time e.g., by simple temporal averaging or more sophist…

Classification Clustering General Classification Video Classification+1

Simultaneous Feature Aggregating and Hashing for Large-scale Image Search

2017-04-04 · CVPR 2017 7 · Thanh-Toan Do, Dang-Khoa Le Tan, Trung T. Pham, Ngai-Man Cheung

In most state-of-the-art hashing-based visual search systems, local image descriptors of an image are first aggregated as a single feature vector. This feature vector is then subjected to a hashing function that produces…

Image Retrieval Retrieval