Unsupervised learning from videos using temporal coherency deep networks
نویسندگان
چکیده
In this work we address the challenging problem of unsupervised learning from videos. Existing methods utilize the spatio-temporal continuity in contiguous video frames as regularization for the learning process. Typically, this temporal coherence of close frames is used as a free form of annotation, encouraging the learned representations to exhibit small differences between these frames. But this type of approach fails to capture the dissimilarity between videos with different content, hence learning less discriminative features. We here propose two Siamese architectures for Convolutional Neural Networks, and their corresponding novel loss functions, to learn from unlabeled videos, which jointly exploit the local temporal coherence between contiguous frames, and a global discriminative margin used to separate representations of different videos. An extensive experimental evaluation is presented, where we validate the proposed models on various tasks. First, we show how the learned features can be used to discover actions and scenes in video collections. Second, we show the benefits of such an unsupervised learning from just unlabeled videos, which can be directly used as a prior for the supervised recognition tasks of actions and objects in images, where our results further show that our features can even surpass a traditional and heavily supervised pre-training plus fine-tunning strategy.
منابع مشابه
Incorporating Scalability in Unsupervised Spatio-temporal Feature Learning
Deep neural networks are efficient learning machines which leverage upon a large amount of manually labeled data for learning discriminative features. However, acquiring substantial amount of supervised data, especially for videos can be a tedious job across various computer vision tasks. This necessitates learning of visual features from videos in an unsupervised setting. In this paper, we pro...
متن کاملHand Gesture Recognition from RGB-D Data using 2D and 3D Convolutional Neural Networks: a comparative study
Despite considerable enhances in recognizing hand gestures from still images, there are still many challenges in the classification of hand gestures in videos. The latter comes with more challenges, including higher computational complexity and arduous task of representing temporal features. Hand movement dynamics, represented by temporal features, have to be extracted by analyzing the total fr...
متن کاملCrop Land Change Monitoring Based on Deep Learning Algorithm Using Multi-temporal Hyperspectral Images
Change detection is done with the purpose of analyzing two or more images of a region that has been obtained at different times which is Generally one of the most important applications of satellite imagery is urban development, environmental inspection, agricultural monitoring, hazard assessment, and natural disaster. The purpose of using deep learning algorithms, in particular, convolutional ...
متن کاملUnsupervised Feature Learning from Videos for Discovering and Recognizing Actions
In this work, we evaluate different unsupervised feature learning approaches using Convolutional Neural Networks (CNNs) and videos. Essentially, we experiment with a CNN feature learning model based on the Contrastive Loss function. We propose a novel Siamese-tuple network architecture trained with a new loss function which benefits from the temporal coherence present in videos as the unique fo...
متن کاملSympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition
Action recognition in videos is a challenging task due to the complexity of the spatio-temporal patterns to model and the difficulty to acquire and learn on large quantities of video data. Deep learning, although a breakthrough for image classification and showing promise for videos, has still not clearly superseded action recognition methods using hand-crafted features, even when training on m...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1801.08100 شماره
صفحات -
تاریخ انتشار 2018