Despite the recent progress in video understanding and the continuous rate of improvement in temporal action localization throughout the years, it is still unclear how far (or close?) we are to solving the problem. To this end, we introduce a new diagnostic tool to analyze the performance of temporal action detectors in videos and compare different methods beyond a single scalar metric. We exemplify the use of our tool by analyzing the performance of the top rewarded entries in the latest ActivityNet action localization challenge. Our analysis shows that the most impactful areas to work on are: strategies to better handle temporal context around the instances, improving the robustness w.r.t. the instance absolute and relative size, and strategies to reduce the localization errors. Moreover, our experimental analysis finds the lack of agreement among annotator is not a major roadblock to attain progress in the field. Our diagnostic tool is publicly available to keep fueling the minds of other researchers with additional insights about their algorithms.
We introduce a simple baseline for action localization on the AVA dataset. The model builds upon the Faster R-CNN bounding box detection framework, adapted to operate on pure spatiotemporal features - in our case produced exclusively by an I3D model pretrained on Kinetics. This model obtains 21.9% average AP on the validation set of AVA v2.1, up from 14.5% for the best RGB spatiotemporal model used in the original AVA paper (which was pretrained on Kinetics and ImageNet), and up from 11.3 of the publicly available baseline using a ResNet101 image feature extractor, that was pretrained on ImageNet. Our final model obtains 22.8%/21.9% mAP on the val/test sets and outperforms all submissions to the AVA challenge at CVPR 2018.
Temporal Action Localization (TAL) in untrimmed video is important for many applications. But it is very expensive to annotate the segment-level ground truth (action class and temporal boundary). This raises the interest of addressing TAL with weak supervision, namely only video-level annotations are available during training). However, the state-of-the-art weakly-supervised TAL methods only focus on generating good Class Activation Sequence (CAS) over time but conduct simple thresholding on CAS to localize actions. In this paper, we first develop a novel weakly-supervised TAL framework called AutoLoc to directly predict the temporal boundary of each action instance. We propose a novel Outer-Inner-Contrastive (OIC) loss to automatically discover the needed segment-level supervision for training such a boundary predictor. Our method achieves dramatically improved performance: under the IoU threshold 0.5, our method improves mAP on THUMOS'14 from 13.7% to 21.2% and mAP on ActivityNet from 7.4% to 27.3%. It is also very encouraging to see that our weakly-supervised method achieves comparable results with some fully-supervised methods.
The goal of this work is spatio-temporal action localization in videos, using only the supervision from video-level class labels. The state-of-the-art casts this weakly-supervised action localization regime as a Multiple Instance Learning problem, where instances are a priori computed spatio-temporal proposals. Rather than disconnecting the spatio-temporal learning from the training, we propose Spatio-Temporal Instance Learning, which enables action localization directly from box proposals in video frames. We outline the assumptions of our model and propose a max-margin objective and optimization with latent variables that enable spatio-temporal learning of actions from video labels. We also provide an efficient linking algorithm and two reranking strategies to facilitate and further improve the action localization. Experimental evaluation on four action datasets demonstrate the effectiveness of our approach for localization from weak supervision. Moreover, we show how to incorporate other supervision levels and mixtures, as a step towards determining optimal supervision strategies for action localization.
This notebook paper presents an overview and comparative analysis of our systems designed for the following five tasks in ActivityNet Challenge 2018: temporal action proposals, temporal action localization, dense-captioning events in videos, trimmed action recognition, and spatio-temporal action localization.
Spatio-temporal action detection in videos is typically addressed in a fully-supervised setup with manual annotation of training videos required at every frame. Since such annotation is extremely tedious and prohibits scalability, there is a clear need to minimize the amount of manual supervision. In this work we propose a unifying framework that can handle and combine varying types of less-demanding weak supervision. Our model is based on discriminative clustering and integrates different types of supervision as constraints on the optimization. We investigate applications of such a model to training setups with alternative supervisory signals ranging from video-level class labels to the full per-frame annotation of action bounding boxes. Experiments on the challenging UCF101-24 and DALY datasets demonstrate competitive performance of our method at a fraction of supervision used by previous methods. The flexibility of our model enables joint learning from data with different levels of annotation. Experimental results demonstrate a significant gain by adding a few fully supervised examples to otherwise weakly labeled videos.
This paper addresses spatio-temporal localization of human actions in video. In order to localize actions in time, we propose a recurrent localization network (RecLNet) designed to model the temporal structure of actions on the level of person tracks. Our model is trained to simultaneously recognize and localize action classes in time and is based on two layer gated recurrent units (GRU) applied separately to two streams, i.e. appearance and optical flow streams. When used together with state-of-the-art person detection and tracking, our model is shown to improve substantially spatio-temporal action localization in videos. The gain is shown to be mainly due to improved temporal localization. We evaluate our method on two recent datasets for spatio-temporal action localization, UCF101-24 and DALY, demonstrating a significant improvement of the state of the art.
We address the problem of fine-grained action localization from temporally untrimmed web videos. We assume that only weak video-level annotations are available for training. The goal is to use these weak labels to identify temporal segments corresponding to the actions, and learn models that generalize to unconstrained web videos. We find that web images queried by action names serve as well-localized highlights for many actions, but are noisily labeled. To solve this problem, we propose a simple yet effective method that takes weak video labels and noisy image labels as input, and generates localized action frames as output. This is achieved by cross-domain transfer between video frames and web images, using pre-trained deep convolutional neural networks. We then use the localized action frames to train action recognition models with long short-term memory networks. We collect a fine-grained sports action data set FGA-240 of more than 130,000 YouTube videos. It has 240 fine-grained actions under 85 sports activities. Convincing results are shown on the FGA-240 data set, as well as the THUMOS 2014 localization data set with untrimmed training videos.
We propose an effective approach for spatio-temporal action localization in realistic videos. The approach first detects proposals at the frame-level and scores them with a combination of static and motion CNN features. It then tracks high-scoring proposals throughout the video using a tracking-by-detection approach. Our tracker relies simultaneously on instance-level and class-level detectors. The tracks are scored using a spatio-temporal motion histogram, a descriptor at the track level, in combination with the CNN features. Finally, we perform temporal localization of the action using a sliding-window approach at the track level. We present experimental results for spatio-temporal localization on the UCF-Sports, J-HMDB and UCF-101 action localization datasets, where our approach outperforms the state of the art with a margin of 15%, 7% and 12% respectively in mAP.
Action parsing in videos with complex scenes is an interesting but challenging task in computer vision. In this paper, we propose a generic 3D convolutional neural network in a multi-task learning manner for effective Deep Action Parsing (DAP3D-Net) in videos. Particularly, in the training phase, action localization, classification and attributes learning can be jointly optimized on our appearancemotion data via DAP3D-Net. For an upcoming test video, we can describe each individual action in the video simultaneously as: Where the action occurs, What the action is and How the action is performed. To well demonstrate the effectiveness of the proposed DAP3D-Net, we also contribute a new Numerous-category Aligned Synthetic Action dataset, i.e., NASA, which consists of 200; 000 action clips of more than 300 categories and with 33 pre-defined action attributes in two hierarchical levels (i.e., low-level attributes of basic body part movements and high-level attributes related to action motion). We learn DAP3D-Net using the NASA dataset and then evaluate it on our collected Human Action Understanding (HAU) dataset. Experimental results show that our approach can accurately localize, categorize and describe multiple actions in realistic videos.
We address temporal action localization in untrimmed long videos. This is important because videos in real applications are usually unconstrained and contain multiple action instances plus video content of background scenes or other activities. To address this challenging issue, we exploit the effectiveness of deep networks in temporal action localization via three segment-based 3D ConvNets: (1) a proposal network identifies candidate segments in a long video that may contain actions; (2) a classification network learns one-vs-all action classification model to serve as initialization for the localization network; and (3) a localization network fine-tunes on the learned classification network to localize each action instance. We propose a novel loss function for the localization network to explicitly consider temporal overlap and therefore achieve high temporal localization accuracy. Only the proposal network and the localization network are used during prediction. On two large-scale benchmarks, our approach achieves significantly superior performances compared with other state-of-the-art systems: mAP increases from 1.7% to 7.4% on MEXaction2 and increases from 15.0% to 19.0% on THUMOS 2014, when the overlap threshold for evaluation is set to 0.5.
Recent advances in image captioning task have led to increasing interests in video captioning task. However, most works on video captioning are focused on generating single input of aggregated features, which hardly deviates from image captioning process and does not fully take advantage of dynamic contents present in videos. We attempt to generate video captions that convey richer contents by temporally segmenting the video with action localization, generating multiple captions from multiple frames, and connecting them with natural language processing techniques, in order to generate a story-like caption. We show that our proposed method can generate captions that are richer in contents and can compete with state-of-the-art method without explicitly using video-level features as input.
This paper considers the problem of localizing actions in videos as a sequences of bounding boxes. The objective is to generate action proposals that are likely to include the action of interest, ideally achieving high recall with few proposals. Our contributions are threefold. First, inspired by selective search for object proposals, we introduce an approach to generate action proposals from spatiotemporal super-voxels in an unsupervised manner, we call them Tubelets. Second, along with the static features from individual frames our approach advantageously exploits motion. We introduce independent motion evidence as a feature to characterize how the action deviates from the background and explicitly incorporate such motion information in various stages of the proposal generation. Finally, we introduce spatiotemporal refinement of Tubelets, for more precise localization of actions, and pruning to keep the number of Tubelets limited. We demonstrate the suitability of our approach by extensive experiments for action proposal quality and action localization on three public datasets: UCF Sports, MSR-II and UCF101. For action proposal quality, our unsupervised proposals beat all other existing approaches on the three datasets. For action localization, we show top performance on both the trimmed videos of UCF Sports and UCF101 as well as the untrimmed videos of MSR-II.
We present a new architecture for end-to-end sequence learning of actions in video, we call VideoLSTM. Rather than adapting the video to the peculiarities of established recurrent or convolutional architectures, we adapt the architecture to fit the requirements of the video medium. Starting from the soft-Attention LSTM, VideoLSTM makes three novel contributions. First, video has a spatial layout. To exploit the spatial correlation we hardwire convolutions in the soft-Attention LSTM architecture. Second, motion not only informs us about the action content, but also guides better the attention towards the relevant spatio-temporal locations. We introduce motion-based attention. And finally, we demonstrate how the attention from VideoLSTM can be used for action localization by relying on just the action class label. Experiments and comparisons on challenging datasets for action classification and localization support our claims.
We strive for spatio-temporal localization of actions in videos. The state-of-the-art relies on action proposals at test time and selects the best one with a classifier trained on carefully annotated box annotations. Annotating action boxes in video is cumbersome, tedious, and error prone. Rather than annotating boxes, we propose to annotate actions in video with points on a sparse subset of frames only. We introduce an overlap measure between action proposals and points and incorporate them all into the objective of a non-convex Multiple Instance Learning optimization. Experimental evaluation on the UCF Sports and UCF 101 datasets shows that (i) spatio-temporal proposals can be used to train classifiers while retaining the localization performance, (ii) point annotations yield results comparable to box annotations while being significantly faster to annotate, (iii) with a minimum amount of supervision our approach is competitive to the state-of-the-art. Finally, we introduce spatio-temporal action annotations on the train and test videos of Hollywood2, resulting in Hollywood2Tubes, available at http://tinyurl.com/hollywood2tubes.
We present a unified framework for understanding human social behaviors in raw image sequences. Our model jointly detects multiple individuals, infers their social actions, and estimates the collective actions with a single feed-forward pass through a neural network. We propose a single architecture that does not rely on external detection algorithms but rather is trained end-to-end to generate dense proposal maps that are refined via a novel inference scheme. The temporal consistency is handled via a person-level matching Recurrent Neural Network. The complete model takes as input a sequence of frames and outputs detections along with the estimates of individual actions and collective activities. We demonstrate state-of-the-art performance of our algorithm on multiple publicly available benchmarks.
This paper studies the joint learning of action recognition and temporal localization in long, untrimmed videos. We employ a multi-task learning framework that performs the three highly related steps of action proposal, action recognition, and action localization refinement in parallel instead of the standard sequential pipeline that performs the steps in order. We develop a novel temporal actionness regression module that estimates what proportion of a clip contains action. We use it for temporal localization but it could have other applications like video retrieval, surveillance, summarization, etc. We also introduce random shear augmentation during training to simulate viewpoint change. We evaluate our framework on three popular video benchmarks. Results demonstrate that our joint model is efficient in terms of storage and computation in that we do not need to compute and cache dense trajectory features, and that it is several times faster than its sequential ConvNets counterpart. Yet, despite being more efficient, it outperforms state-of-the-art methods with respect to accuracy.
We address the problem of temporal action localization in videos. We pose action localization as a structured prediction over arbitrary-length temporal windows, where each window is scored as the sum of frame-wise classification scores. Additionally, our model classifies the start, middle, and end of each action as separate components, allowing our system to explicitly model each action's temporal evolution and take advantage of informative temporal dependencies present in this structure. In this framework, we localize actions by searching for the structured maximal sum, a problem for which we develop a novel, provably-efficient algorithmic solution. The frame-wise classification scores are computed using features from a deep Convolutional Neural Network (CNN), which are trained end-to-end to directly optimize for a novel structured objective. We evaluate our system on the THUMOS 14 action detection benchmark and achieve competitive performance.
The aim of this paper is to propose distributed strategies for adaptive learning of signals defined over graphs. Assuming the graph signal to be bandlimited, the method enables distributed reconstruction, with guaranteed performance in terms of mean-square error, and tracking from a limited number of sampled observations taken from a subset of vertices. A detailed mean square analysis is carried out and illustrates the role played by the sampling strategy on the performance of the proposed method. Finally, some useful strategies for distributed selection of the sampling set are provided. Several numerical results validate our theoretical findings, and illustrate the performance of the proposed method for distributed adaptive learning of signals defined over graphs.
We introduce an approach for spatio-temporal human action localization using sparse spatial supervision. Our method leverages the large amount of annotated humans available today and extracts human tubes by combining a state-of-the-art human detector with a tracking-by-detection approach. Given these high-quality human tubes and temporal supervision, we select positive and negative tubes with very sparse spatial supervision, i.e., only one spatially annotated frame per instance. The selected tubes allow us to effectively learn a spatio-temporal action detector based on dense trajectories or CNNs. We conduct experiments on existing action localization benchmarks: UCF-Sports, J-HMDB and UCF-101. Our results show that our approach, despite using sparse spatial supervision, performs on par with methods using full supervision, i.e., one bounding box annotation per frame. To further validate our method, we introduce DALY (Daily Action Localization in YouTube), a dataset for realistic action localization in space and time. It contains high quality temporal and spatial annotations for 3.6k instances of 10 actions in 31 hours of videos (3.3M frames). It is an order of magnitude larger than existing datasets, with more diversity in appearance and long untrimmed videos.