Webly-Supervised Video Recognition by Mutually Voting for Relevant Web Images and Web Video Frames

By Chuang Gan, Chen Sun, Lixin Duan, Boqing Gong. 2016

103 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning Video Representations from Textual Web Supervision (2020, methodology): “The most commonly-used approach is to use image search results, and to label each image with the query that was used to ﬁnd it [65, 15, 56, 6, 11, 13, 21, 10, 18, 35].”
TSM: Temporal Shift Module for Efficient Video Understanding (2018, methodology): “Some works use LSTM [19] to aggregate the 2D CNN features [54, 7, 41, 10, 12].”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “268, 269, 270, 95] or multi-view embedding [93, 110, 99, 111, 112, 113]. Hence, HDA/HTL can strongly beneﬁt from such cross-modal data representations. In the same spirit, webly supervised approaches [271, 272, 273, 274, 158, 159, 275] are also related to DA and HDA as is these approaches rely on co”
NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning (2018, background): “In [30, 8, 9], web images are used to guide video learning in a weakly supervised fashion.”
RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning (2020, unknown): “How to learn effective video representations with a few annotations even without annotations is an important yet challenging task [13, 11, 10].”
UntrimmedNets for Weakly Supervised Action Recognition and Detection (2017, methodology): “ning in videos. Weakly supervised learning was extensively studied in object recognition and detection [1,4,9,34], and there were several works adapting this method to learn action models from videos [28,8,2,3,17,26,12,13]. The ﬁrst type of weak supervision is movie script, which provides uncertain ”
Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition (2019, background): “Existing research efforts [45, 36, 12, 10, 13, 7, 11, 41, 3, 52, 33, 47, 8, 1, 16, 29, 35, 42, 44, 56, 5, 20] mainly focus on building effective and efficient video modeling networks.”
W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection (2018, background): “We would like to emphasize that our framework does not need an extra dataset, and the only training data needed is images with image-level labels (possibly crawled from online sources as in [36, 3, 10, 9], or from a standard object detection dataset [8, 6]).”
Temporal Shift Module for Efficient Video Understanding (2018, background): “Some works introduced LSTM [16] to aggregate the CNN features for video recognition [47, 5, 35, 8, 10].”
Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization (2019, background): “Researchers have also studied action localization with other types of weak supervision, such as movies scripts [13], ordered action lists [11], and web images [14].”
Attention Transfer from Web Images for Video Recognition (2017, methodology): “Ma et al. spatial [23] and Webly-supervised [10] are the two methods that most relate to ours.”
Weakly Supervised Action Learning with RNN Based Fine-to-Coarse Modeling (2017, background): “[8] show an approach to learn action classes from web images and videos retrieved by specific search queries.”