Falling of elderly people who are staying alone at home leads to health risks. If they are not attended immediately even it may lead to fatal danger to their life. In this paper a novel computer vision-based system for smart monitoring of elderly people using Series Convolutional Neural Network (SCNN) with transfer learning is proposed. When CNN is trained by the frames of the videos directly, it learns from all pixels including the background pixels. Generally, the background in a video does not contribute anything in identifying the action and actually it will mislead the action classification. So, we propose a novel action recognition system and our contributions are 1) to generate more general action patterns which are not affected by illumination and background variations of the video sequences and eliminate the obligation of image augmentation in CNN training 2) to design SCNN architecture and enhance the feature extraction process to learn large amount of data, 3) to present the patterns learnt by the neurons in the layers and analyze how these neurons capture the action when the input pattern is passing through these neurons, and 4) to extend the capability of the trained SCNN for recognizing fall actions using transfer learning.
Understanding which features humans rely on -- in visually recognizing action similarity is a crucial step towards a clearer picture of human action perception from a learning and developmental perspective. In the present work, we investigate to which extent a computational model based on kinematics can determine action similarity and how its performance relates to human similarity judgments of the same actions. To this aim, twelve participants perform an action similarity task, and their performances are compared to that of a computational model solving the same task. The chosen model has its roots in developmental robotics and performs action classification based on learned kinematic primitives. The comparative experiment results show that both the model and human participants can reliably identify whether two actions are the same or not. However, the model produces more false hits and has a greater selection bias than human participants. A possible reason for this is the particular sensitivity of the model towards kinematic primitives of the presented actions. In a second experiment, human participants' performance on an action identification task indicated that they relied solely on kinematic information rather than on action semantics. The results show that both the model and human performance are highly accurate in an action similarity task based on kinematic-level features, which can provide an essential basis for classifying human actions.
We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate results can vary for different input space partitions. Therefore, we consider mixtures where experts require different amounts of data, and train a sparse gating function to divide the input space for each expert. By appropriate hyperparameter selection, our approach is able to bias mixtures of experts towards selecting specific experts over others. In this way, we show that the data transfer optimization between visual sensing and processing can be solved as a convex optimization problem.To demonstrate the relation between data availability and performance, we evaluate biased mixtures on a range of mainstream computer vision problems, namely: (i) single shot detection, (ii) image super resolution, and (iii) realtime video action classification. For all cases, and when experts constitute modified baselines to meet different limits on allowed data utility, biased mixtures significantly outperform previous work optimized to meet the same constraints on available data.
We create a family of powerful video models which are able to: (i) learn interactions between semantic object information and raw appearance and motion features, and (ii) deploy attention in order to better learn the importance of features at each convolutional block of the network. A new network component named peer-attention is introduced, which dynamically learns the attention weights using another block or input modality. Even without pre-training, our models outperform the previous work on standard public activity recognition datasets with continuous videos, establishing new state-of-the-art. We also confirm that our findings of having neural connections from the object modality and the use of peer-attention is generally applicable for different existing architectures, improving their performances. We name our model explicitly as AssembleNet++. The code will be available at: https://sites.google.com/corp/view/assemblenet/
The objective of this paper is self-supervised learning from video, in particular for representations for action recognition. We make the following contributions: (i) We propose a new architecture and learning framework Memory-augmented Dense Predictive Coding (MemDPC) for the task. It is trained with a predictive attention mechanism over the set of compressed memories, such that any future states can always be constructed by a convex combination of the condense representations, allowing to make multiple hypotheses efficiently. (ii) We investigate visual-only self-supervised video representation learning from RGB frames, or from unsupervised optical flow, or both. (iii) We thoroughly evaluate the quality of learnt representation on four different downstream tasks: action recognition, video retrieval, learning with scarce annotations, and unintentional action classification. In all cases, we demonstrate state-of-the-art or comparable performance over other approaches with orders of magnitude fewer training data.
Research on human action classification has made significant progresses in the past few years. Most deep learning methods focus on improving performance by adding more network components. We propose, however, to better utilize auxiliary mechanisms, including hierarchical classification, network pruning, and skeleton-based preprocessing, to boost the model robustness and performance. We test the effectiveness of our method on four commonly used testing datasets: NTU RGB+D 60, NTU RGB+D 120, Northwestern-UCLA Multiview Action 3D, and UTD Multimodal Human Action Dataset. Our experiments show that our method can achieve either comparable or better performance on all four datasets. In particular, our method sets up a new baseline for NTU 120, the largest dataset among the four. We also analyze our method with extensive comparisons and ablation studies.
Recent progress in fine-grained gesture and action classification, and machine translation, point to the possibility of automated sign language recognition becoming a reality. A key stumbling block in making progress towards this goal is a lack of appropriate training data, stemming from the high complexity of sign annotation and a limited supply of qualified annotators. In this work, we introduce a new scalable approach to data collection for sign recognition in continuous videos. We make use of weakly-aligned subtitles for broadcast footage together with a keyword spotting method to automatically localise sign-instances for a vocabulary of 1,000 signs in 1,000 hours of video. We make the following contributions: (1) We show how to use mouthing cues from signers to obtain high-quality annotations from video data - the result is the BSL-1K dataset, a collection of British Sign Language (BSL) signs of unprecedented scale; (2) We show that we can use BSL-1K to train strong sign recognition models for co-articulated signs in BSL and that these models additionally form excellent pretraining for other sign languages and benchmarks - we exceed the state of the art on both the MSASL and WLASL benchmarks. Finally, (3) we propose new large-scale evaluation sets for the tasks of sign recognition and sign spotting and provide baselines which we hope will serve to stimulate research in this area.
Motion plays a crucial role in understanding videos and most state-of-the-art neural models for video classification incorporate motion information typically using optical flows extracted by a separate off-the-shelf method. As the frame-by-frame optical flows require heavy computation, incorporating motion information has remained a major computational bottleneck for video understanding. In this work, we replace external and heavy computation of optical flows with internal and light-weight learning of motion features. We propose a trainable neural module, dubbed MotionSqueeze, for effective motion feature extraction. Inserted in the middle of any neural network, it learns to establish correspondences across frames and convert them into motion features, which are readily fed to the next downstream layer for better prediction. We demonstrate that the proposed method provides a significant gain on four standard benchmarks for action recognition with only a small amount of additional cost, outperforming the state of the art on Something-Something-V1&V2 datasets.
Convolutional Neural Networks (CNNs) model long-range dependencies by deeply stacking convolution operations with small window sizes, which makes the optimizations difficult. This paper presents region-based non-local (RNL) operations as a family of self-attention mechanisms, which can directly capture long-range dependencies without using a deep stack of local operations. Given an intermediate feature map, our method recalibrates the feature at a position by aggregating the information from the neighboring regions of all positions. By combining a channel attention module with the proposed RNL, we design an attention chain, which can be integrated into the off-the-shelf CNNs for end-to-end training. We evaluate our method on two video classification benchmarks. The experimental results of our method outperform other attention mechanisms, and we achieve state-of-the-art performance on the Something-Something V1 dataset.
We propose an effective framework for the temporal action segmentation task, namely an Action Segment Refinement Framework (ASRF). Our model architecture consists of a long-term feature extractor and two branches: the Action Segmentation Branch (ASB) and the Boundary Regression Branch (BRB). The long-term feature extractor provides shared features for the two branches with a wide temporal receptive field. The ASB classifies video frames with action classes, while the BRB regresses the action boundary probabilities. The action boundaries predicted by the BRB refine the output from the ASB, which results in a significant performance improvement. Our contributions are three-fold: (i) We propose a framework for temporal action segmentation, the ASRF, which divides temporal action segmentation into frame-wise action classification and action boundary regression. Our framework refines frame-level hypotheses of action classes using predicted action boundaries. (ii) We propose a loss function for smoothing the transition of action probabilities, and analyze combinations of various loss functions for temporal action segmentation. (iii) Our framework outperforms state-of-the-art methods on three challenging datasets, offering an improvement of up to 13.7% in terms of segmental edit distance and up to 16.1% in terms of segmental F1 score. Our code will be publicly available soon.
We introduce a new public video dataset for action recognition: Anonymized Videos from Diverse countries (AViD). Unlike existing public video datasets, AViD is a collection of action videos from many different countries. The motivation is to create a public dataset that would benefit training and pretraining of action recognition models for everybody, rather than making it useful for limited countries. Further, all the face identities in the AViD videos are properly anonymized to protect their privacy. It also is a static dataset where each video is licensed with the creative commons license. We confirm that most of the existing video datasets are statistically biased to only capture action videos from a limited number of countries. We experimentally illustrate that models trained with such biased datasets do not transfer perfectly to action videos from the other countries, and show that AViD addresses such problem. We also confirm that the new AViD dataset could serve as a good dataset for pretraining the models, performing comparably or better than prior datasets.
In this paper, we focus on the spatio-temporal aspect of recognizing Activities of Daily Living (ADL). ADL have two specific properties (i) subtle spatio-temporal patterns and (ii) similar visual patterns varying with time. Therefore, ADL may look very similar and often necessitate to look at their fine-grained details to distinguish them. Because the recent spatio-temporal 3D ConvNets are too rigid to capture the subtle visual patterns across an action, we propose a novel Video-Pose Network: VPN. The 2 key components of this VPN are a spatial embedding and an attention network. The spatial embedding projects the 3D poses and RGB cues in a common semantic space. This enables the action recognition framework to learn better spatio-temporal features exploiting both modalities. In order to discriminate similar actions, the attention network provides two functionalities - (i) an end-to-end learnable pose backbone exploiting the topology of human body, and (ii) a coupler to provide joint spatio-temporal attention weights across a video. Experiments show that VPN outperforms the state-of-the-art results for action classification on a large scale human activity dataset: NTU-RGB+D 120, its subset NTU-RGB+D 60, a real-world challenging human activity dataset: Toyota Smarthome and a small scale human-object interaction dataset Northwestern UCLA.
This work introduces pyramidal convolution (PyConv), which is capable of processing the input at multiple filter scales. PyConv contains a pyramid of kernels, where each level involves different types of filters with varying size and depth, which are able to capture different levels of details in the scene. On top of these improved recognition capabilities, PyConv is also efficient and, with our formulation, it does not increase the computational cost and parameters compared to standard convolution. Moreover, it is very flexible and extensible, providing a large space of potential network architectures for different applications. PyConv has the potential to impact nearly every computer vision task and, in this work, we present different architectures based on PyConv for four main tasks on visual recognition: image classification, video action classification/recognition, object detection and semantic image segmentation/parsing. Our approach shows significant improvements over all these core tasks in comparison with the baselines. For instance, on image recognition, our 50-layers network outperforms in terms of recognition performance on ImageNet dataset its counterpart baseline ResNet with 152 layers, while having 2.39 times less parameters, 2.52 times lower computational complexity and more than 3 times less layers. On image segmentation, our novel framework sets a new state-of-the-art on the challenging ADE20K benchmark for scene parsing. Code is available at: https://github.com/iduta/pyconv
This technical report analyzes a temporal action localization method we used in the HACS competition which is hosted in Activitynet Challenge 2020.The goal of our task is to locate the start time and end time of the action in the untrimmed video, and predict action category.Firstly, we utilize the video-level feature information to train multiple video-level action classification models. In this way, we can get the category of action in the video.Secondly, we focus on generating high quality temporal proposals.For this purpose, we apply BMN to generate a large number of proposals to obtain high recall rates. We then refine these proposals by employing a cascade structure network called Refine Network, which can predict position offset and new IOU under the supervision of ground truth.To make the proposals more accurate, we use bidirectional LSTM, Nonlocal and Transformer to capture temporal relationships between local features of each proposal and global features of the video data.Finally, by fusing the results of multiple models, our method obtains 40.55% on the validation set and 40.53% on the test set in terms of mAP, and achieves Rank 1 in this challenge.
Generalizing over temporal variations is a prerequisite for effective action recognition in videos. Despite significant advances in deep neural networks, it remains a challenge to focus on short-term discriminative motions in relation to the overall performance of an action. We address this challenge by allowing some flexibility in discovering relevant spatio-temporal features. We introduce Squeeze and Recursion Temporal Gates (SRTG), an approach that favors inputs with similar activations with potential temporal variations. We implement this idea with a novel CNN block that uses an LSTM to encapsulate feature dynamics, in conjunction with a temporal gate that is responsible for evaluating the consistency of the discovered dynamics and the modeled features. We show consistent improvement when using SRTG blocks, with only a minimal increase in the number of GFLOPs. On Kinetics-700, we perform on par with current state-of-the-art models, and outperform these on HACS, Moments in Time, UCF-101 and HMDB-51.
Weakly-supervised temporal action localization aims to learn detecting temporal intervals of action classes with only video-level labels. To this end, it is crucial to separate frames of action classes from the background frames (i.e., frames not belonging to any action classes). In this paper, we present a new perspective on background frames where they are modeled as out-of-distribution samples regarding their inconsistency. Then, background frames can be detected by estimating the probability of each frame being out-of-distribution, known as uncertainty, but it is infeasible to directly learn uncertainty without frame-level labels. To realize the uncertainty learning in the weakly-supervised setting, we leverage the multiple instance learning formulation. Moreover, we further introduce a background entropy loss to better discriminate background frames by encouraging their in-distribution (action) probabilities to be uniformly distributed over all action classes. Experimental results show that our uncertainty modeling is effective at alleviating the interference of background frames and brings a large performance gain without bells and whistles. We demonstrate that our model significantly outperforms state-of-the-art methods on the benchmarks, THUMOS'14 and ActivityNet (1.2 & 1.3). Our code is available at https://github.com/Pilhyeon/WTAL-Uncertainty-Modeling.
In this paper, we address the problem of action recognition from still images and videos. Traditional local features such as SIFT, STIP etc. invariably pose two potential problems: 1) they are not evenly distributed in different entities of a given category and 2) many of such features are not exclusive of the visual concept the entities represent. In order to generate a dictionary taking the aforementioned issues into account, we propose a novel discriminative method for identifying robust and category specific local features which maximize the class separability to a greater extent. Specifically, we pose the selection of potent local descriptors as filtering based feature selection problem which ranks the local features per category based on a novel measure of distinctiveness. The underlying visual entities are subsequently represented based on the learned dictionary and this stage is followed by action classification using the random forest model followed by label propagation refinement. The framework is validated on the action recognition datasets based on still images (Stanford-40) as well as videos (UCF-50) and exhibits superior performances than the representative methods from the literature.
This paper describes the AVA-Kinetics localized human actions video dataset. The dataset is collected by annotating videos from the Kinetics-700 dataset using the AVA annotation protocol, and extending the original AVA dataset with these new AVA annotated Kinetics clips. The dataset contains over 230k clips annotated with the 80 AVA action classes for each of the humans in key-frames. We describe the annotation process and provide statistics about the new dataset. We also include a baseline evaluation using the Video Action Transformer Network on the AVA-Kinetics dataset, demonstrating improved performance for action classification on the AVA test set. The dataset can be downloaded from https://research.google.com/ava/
This paper presents X3D, a family of efficient video networks that progressively expand a tiny 2D image classification architecture along multiple network axes, in space, time, width and depth. Inspired by feature selection methods in machine learning, a simple stepwise network expansion approach is employed that expands a single axis in each step, such that good accuracy to complexity trade-off is achieved. To expand X3D to a specific target complexity, we perform progressive forward expansion followed by backward contraction. X3D achieves state-of-the-art performance while requiring 4.8x and 5.5x fewer multiply-adds and parameters for similar accuracy as previous work. Our most surprising finding is that networks with high spatiotemporal resolution can perform well, while being extremely light in terms of network width and parameters. We report competitive accuracy at unprecedented efficiency on video classification and detection benchmarks. Code will be available at: https://github.com/facebookresearch/SlowFast
Deep Learning has driven recent and exciting progress in computer vision, instilling the belief that these algorithms could solve any visual task. Yet, datasets commonly used to train and test computer vision algorithms have pervasive confounding factors. Such biases make it difficult to truly estimate the performance of those algorithms and how well computer vision models can extrapolate outside the distribution in which they were trained. In this work, we propose a new action classification challenge that is performed well by humans, but poorly by state-of-the-art Deep Learning models. As a proof-of-principle, we consider three exemplary tasks: drinking, reading, and sitting. The best accuracies reached using state-of-the-art computer vision models were 61.7%, 62.8%, and 76.8%, respectively, while human participants scored above 90% accuracy on the three tasks. We propose a rigorous method to reduce confounds when creating datasets, and when comparing human versus computer vision performance. Source code and datasets are publicly available.