اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدLearning long-term dependencies for action recognition with a biologically-inspired deep network
140
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Despite a lot of research efforts devoted in recent years, how to efficiently learn long-term dependencies from sequences still remains a pretty challenging task. As one of the key models for sequence learning, recurrent neural network (RNN) and its variants such as long short term memory (LSTM) and gated recurrent unit (GRU) are still not powerful enough in practice. One possible reason is that they have only feedforward connections, which is different from the biological neural system that is typically composed of both feedforward and feedback connections. To address this problem, this paper proposes a biologically-inspired deep network, called shuttleNetfootnote{Our code is available at url{https://github.com/shiyemin/shuttlenet}}. Technologically, the shuttleNet consists of several processors, each of which is a GRU while associated with multiple groups of cells and states. Unlike traditional RNNs, all processors inside shuttleNet are loop connected to mimic the brains feedforward and feedback connections, in which they are shared across multiple pathways in the loop connection. Attention mechanism is then employed to select the best information flow pathway. Extensive experiments conducted on two benchmark datasets (i.e UCF101 and HMDB51) show that we can beat state-of-the-art methods by simply embedding shuttleNet into a CNN-RNN framework.
قيم البحث
اقرأ أيضاً
Spatial and temporal relationships, both short-range and long-range, between objects in videos, are key cues for recognizing actions. It is a challenging problem to model them jointly. In this paper, we first present a new variant of Long Short-Term
Memory, namely Relational LSTM, to address the challenge of relation reasoning across space and time between objects. In our Relational LSTM module, we utilize a non-local operation similar in spirit to the recently proposed non-local network to substitute the fully connected operation in the vanilla LSTM. By doing this, our Relational LSTM is capable of capturing long and short-range spatio-temporal relations between objects in videos in a principled way. Then, we propose a two-branch neural architecture consisting of the Relational LSTM module as the non-local branch and a spatio-temporal pooling based local branch. The local branch is utilized for capturing local spatial appearance and/or short-term motion features. The two branches are concatenated to learn video-level features from snippet-level ones which are then used for classification. Experimental results on UCF-101 and HMDB-51 datasets show that our model achieves state-of-the-art results among LSTM-based methods, while obtaining comparable performance with other state-of-the-art methods (which use not directly comparable schema). Further, on the more complex large-scale Charades dataset, we obtain a large 3.2% gain over state-of-the-art methods, verifying the effectiveness of our method in complex understanding.
Computational neuroscience studies that have examined human visual system through functional magnetic resonance imaging (fMRI) have identified a model where the mammalian brain pursues two distinct pathways (for recognition of biological movement tas
ks). In the brain, dorsal stream analyzes the information of motion (optical flow), which is the fast features, and ventral stream (form pathway) analyzes form information (through active basis model based incremental slow feature analysis ) as slow features. The proposed approach suggests the motion perception of the human visual system composes of fast and slow feature interactions that identifies biological movements. Form features in the visual system biologically follows the application of active basis model with incremental slow feature analysis for the extraction of the slowest form features of human objects movements in the ventral stream. Applying incremental slow feature analysis provides an opportunity to use the action prototypes. To extract the slowest features episodic observation is required but the fast features updates the processing of motion information in every frames. Experimental results have shown promising accuracy for the proposed model and good performance with two datasets (KTH and Weizmann).
Most of the Zero-Shot Learning (ZSL) algorithms currently use pre-trained models as their feature extractors, which are usually trained on the ImageNet data set by using deep neural networks. The richness of the feature information embedded in the pr
e-trained models can help the ZSL model extract more useful features from its limited training samples. However, sometimes the difference between the training data set of the current ZSL task and the ImageNet data set is too large, which may lead to the use of pre-trained models has no obvious help or even negative impact on the performance of the ZSL model. To solve this problem, this paper proposes a biologically inspired feature enhancement framework for ZSL. Specifically, we design a dual-channel learning framework that uses auxiliary data sets to enhance the feature extractor of the ZSL model and propose a novel method to guide the selection of the auxiliary data sets based on the knowledge of biological taxonomy. Extensive experimental results show that our proposed method can effectively improve the generalization ability of the ZSL model and achieve state-of-the-art results on three benchmark ZSL tasks. We also explained the experimental phenomena through the way of feature visualization.
The goal of continuous emotion recognition is to assign an emotion value to every frame in a sequence of acoustic features. We show that incorporating long-term temporal dependencies is critical for continuous emotion recognition tasks. To this end,
we first investigate architectures that use dilated convolutions. We show that even though such architectures outperform previously reported systems, the output signals produced from such architectures undergo erratic changes between consecutive time steps. This is inconsistent with the slow moving ground-truth emotion labels that are obtained from human annotators. To deal with this problem, we model a downsampled version of the input signal and then generate the output signal through upsampling. Not only does the resulting downsampling/upsampling network achieve good performance, it also generates smooth output trajectories. Our method yields the best known audio-only performance on the RECOLA dataset.
Symmetric positive definite (SPD) matrices (e.g., covariances, graph Laplacians, etc.) are widely used to model the relationship of spatial or temporal domain. Nevertheless, SPD matrices are theoretically embedded on Riemannian manifolds. In this pap
er, we propose an end-to-end deep manifold-to-manifold transforming network (DMT-Net) which can make SPD matrices flow from one Riemannian manifold to another more discriminative one. To learn discriminative SPD features characterizing both spatial and temporal dependencies, we specifically develop three novel layers on manifolds: (i) the local SPD convolutional layer, (ii) the non-linear SPD activation layer, and (iii) the Riemannian-preserved recursive layer. The SPD property is preserved through all layers without any requirement of singular value decomposition (SVD), which is often used in the existing methods with expensive computation cost. Furthermore, a diagonalizing SPD layer is designed to efficiently calculate the final metric for the classification task. To evaluate our proposed method, we conduct extensive experiments on the task of action recognition, where input signals are popularly modeled as SPD matrices. The experimental results demonstrate that our DMT-Net is much more competitive over state-of-the-art.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
