We propose a novel video understanding task by fusing knowledge-based and video question answering. First, we introduce KnowIT VQA, a video dataset with 24,282 human-generated question-answer pairs about a popular sitcom. The dataset combines visual, textual and temporal coherence reasoning together with knowledge-based questions, which need of the experience obtained from the viewing of the series to be answered. Second, we propose a video understanding model by combining the visual and textual video content with specific knowledge about the show. Our main findings are: (i) the incorporation of knowledge produces outstanding improvements for VQA in video, and (ii) the performance on KnowIT VQA still lags well behind human accuracy, indicating its usefulness for studying current video modelling limitations.
As scene segmentation systems reach visually accurate results, many recent papers focus on making these network architectures faster, smaller and more efficient. In particular, studies often aim at designingreal-time'systems. Achieving this goal is particularly relevant in the context of real-time video understanding for autonomous vehicles, and robots. In this paper, we argue that the commonly used performance metric of mean Intersection over Union (mIoU) does not fully capture the information required to estimate the true performance of these networks when they operate inreal-time'. We propose a change of objective in the segmentation task, and its associated metric that encapsulates this missing information in the following way: We propose to predict the future output segmentation map that will match the future input frame at the time when the network finishes the processing. We introduce the associated latency-aware metric, from which we can determine a ranking. We perform latency timing experiments of some recent networks on different hardware and assess the performances of these networks on our proposed task. We propose improvements to scene segmentation networks to better perform on our task by using multi-frames input and increasing capacity in the initial convolutional layers.
Hand hygiene is one of the most significant factors in preventing hospital acquired infections (HAI) which often be transmitted by medical staffs in contact with patients in the operating room (OR). Hand hygiene monitoring could be important to investigate and reduce the outbreak of infections within the OR. However, an effective monitoring tool for hand hygiene compliance is difficult to develop due to the visual complexity of the OR scene. Recent progress in video understanding with convolutional neural net (CNN) has increased the application of recognition and detection of human actions. Leveraging this progress, we proposed a fully automated hand hygiene monitoring tool of the alcohol-based hand rubbing action of anesthesiologists on OR video using spatio-temporal features with 3D CNN. First, the region of interest (ROI) of anesthesiologists' upper body were detected and cropped. A temporal smoothing filter was applied to the ROIs. Then, the ROIs were given to a 3D CNN and classified into two classes: rubbing hands or other actions. We observed that a transfer learning from Kinetics-400 is beneficial and the optical flow stream was not helpful in our dataset. The final accuracy, precision, recall and F1 score in testing is 0.76, 0.85, 0.65 and 0.74, respectively.
Eye movement and strategic placement of the visual field onto the retina, gives animals increased resolution of the scene and suppresses distracting information. This fundamental system has been missing from video understanding with deep networks, typically limited to 224 by 224 pixel content locked to the camera frame. We propose a simple idea, WorldFeatures, where each feature at every layer has a spatial transformation, and the feature map is only transformed as needed. We show that a network built with these WorldFeatures, can be used to model eye movements, such as saccades, fixation, and smooth pursuit, even in a batch setting on pre-recorded video. That is, the network can for example use all 224 by 224 pixels to look at a small detail one moment, and the whole scene the next. We show that typical building blocks, such as convolutions and pooling, can be adapted to support WorldFeatures using available tools. Experiments are presented on the Charades, Olympic Sports, and Caltech-UCSD Birds-200-2011 datasets, exploring action recognition, fine-grained recognition, and video stabilization.
In this technical report, we briefly introduce the solutions of our team 'Efficient' for the Multi-Moments in Time challenge in ICCV 2019. We first conduct several experiments with popular Image-Based action recognition methods TRN, TSN, and TSM. Then a novel temporal interlacing network is proposed towards fast and accurate recognition. Besides, the SlowFast network and its variants are explored. Finally, we ensemble all the above models and achieve 67.22\% on the validation set and 60.77\% on the test set, which ranks 1st on the final leaderboard. In addition, we release a new code repository for video understanding which unifies state-of-the-art 2D and 3D methods based on PyTorch. The solution of the challenge is also included in the repository, which is available at https://github.com/Sense-X/X-Temporal.
Captioning is a crucial and challenging task for video understanding. In videos that involve active agents such as humans, the agent's actions can bring about myriad changes in the scene. Observable changes such as movements, manipulations, and transformations of the objects in the scene, are reflected in conventional video captioning. Unlike images, actions in videos are also inherently linked to social aspects such as intentions (why the action is taking place), effects (what changes due to the action), and attributes that describe the agent. Thus for video understanding, such as when captioning videos or when answering questions about videos, one must have an understanding of these commonsense aspects. We present the first work on generating commonsense captions directly from videos, to describe latent aspects such as intentions, effects, and attributes. We present a new dataset "Video-to-Commonsense (V2C)" that contains $\sim9k$ videos of human agents performing various actions, annotated with 3 types of commonsense descriptions. Additionally we explore the use of open-ended video-based commonsense question answering (V2C-QA) as a way to enrich our captions. Both the generation task and the QA task can be used to enrich video captions.
With the rapid development of digital multimedia, video understanding has become an important field. For action recognition, temporal dimension plays an important role, and this is quite different from image recognition. In order to learn powerful feature of videos, we propose a Collaborative Temporal Modeling (CTM) block (Figure 1) to learn temporal information for action recognition. Besides a parameter-free identity shortcut, as a separate temporal modeling block, CTM includes two collaborative paths: a spatial-aware temporal modeling path, which we propose the Temporal-Channel Convolution Module (TCCM) with unshared parameters for each spatial position (H*W) to build, and a spatial-unaware temporal modeling path. CTM blocks can seamlessly be inserted into many popular networks to generate CTM Networks and bring the capability of learning temporal information to 2D CNN backbone networks, which only capture spatial information. Experiments on several popular action recognition datasets demonstrate that CTM blocks bring the performance improvements on 2D CNN baselines, and our method achieves the competitive results against the state-of-the-art methods. Code will be made publicly available.
Temporal action localization is an important step towards video understanding. Most current action localization methods depend on untrimmed videos with full temporal annotations of action instances. However, it is expensive and time-consuming to annotate both action labels and temporal boundaries of videos. To this end, we propose a weakly supervised temporal action localization method that only requires video-level action instances as supervision during training. We propose a classification module to generate action labels for each segment in the video, and a deep metric learning module to learn the similarity between different action instances. We jointly optimize a balanced binary cross-entropy loss and a metric loss using a standard backpropagation algorithm. Extensive experiments demonstrate the effectiveness of both of these components in temporal localization. We evaluate our algorithm on two challenging untrimmed video datasets: THUMOS14 and ActivityNet1.2. Our approach improves the current state-of-the-art result for THUMOS14 by 6.5% mAP at IoU threshold 0.5, and achieves competitive performance for ActivityNet1.2.
Temporally language grounding in untrimmed videos is a newly-raised task in video understanding. Most of the existing methods suffer from inferior efficiency, lacking interpretability, and deviating from the human perception mechanism. Inspired by human's coarse-to-fine decision-making paradigm, we formulate a novel Tree-Structured Policy based Progressive Reinforcement Learning (TSP-PRL) framework to sequentially regulate the temporal boundary by an iterative refinement process. The semantic concepts are explicitly represented as the branches in the policy, which contributes to efficiently decomposing complex policies into an interpretable primitive action. Progressive reinforcement learning provides correct credit assignment via two task-oriented rewards that encourage mutual promotion within the tree-structured policy. We extensively evaluate TSP-PRL on the Charades-STA and ActivityNet datasets, and experimental results show that TSP-PRL achieves competitive performance over existing state-of-the-art methods.
For a long time, the vision community tries to learn the spatio-temporal representation by combining convolutional neural network together with various temporal models, such as the families of Markov chain, optical flow, RNN and temporal convolution. However, these pipelines consume enormous computing resources due to the alternately learning process for spatial and temporal information. One natural question is whether we can embed the temporal information into the spatial one so the information in the two domains can be jointly learned once-only. In this work, we answer this question by presenting a simple yet powerful operator -- temporal interlacing network (TIN). Instead of learning the temporal features, TIN fuses the two kinds of information by interlacing spatial representations from the past to the future, and vice versa. A differentiable interlacing target can be learned to control the interlacing process. In this way, a heavy temporal model is replaced by a simple interlacing operator. We theoretically prove that with a learnable interlacing target, TIN performs equivalently to the regularized temporal convolution network (r-TCN), but gains 4% more accuracy with 6x less latency on 6 challenging benchmarks. These results push the state-of-the-art performances of video understanding by a considerable margin. Not surprising, the ensemble model of the proposed TIN won the $1^{st}$ place in the ICCV19 - Multi Moments in Time challenge. Code is made available to facilitate further research at https://github.com/deepcs233/TIN
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However, most of sequential data, as seen with videos, have complex dependency structures that imply variable-length semantic flows and their compositions, and those are hard to be captured by conventional methods. Here, we propose Cut-Based Graph Learning Networks (CB-GLNs) for learning video data by discovering these complex structures of the video. The CB-GLNs represent video data as a graph, with nodes and edges corresponding to frames of the video and their dependencies respectively. The CB-GLNs find compositional dependencies of the data in multilevel graph forms via a parameterized kernel with graph-cut and a message passing framework. We evaluate the proposed method on the two different tasks for video understanding: Video theme classification (Youtube-8M dataset) and Video Question and Answering (TVQA dataset). The experimental results show that our model efficiently learns the semantic compositional structure of video data. Furthermore, our model achieves the highest performance in comparison to other baseline methods.
Videos can evoke a range of affective responses in viewers. The ability to predict evoked affect from a video, before viewers watch the video, can help in content creation and video recommendation. We introduce the Evoked Expressions from Videos (EEV) dataset, a large-scale dataset for studying viewer responses to videos. Each video is annotated at 6 Hz with 15 continuous evoked expression labels, corresponding to the facial expression of viewers who reacted to the video. We use an expression recognition model within our data collection framework to achieve scalability. In total, there are 36.7 million annotations of viewer facial reactions to 23,574 videos (1,700 hours). We use a publicly available video corpus to obtain a diverse set of video content. We establish baseline performance on the EEV dataset using an existing multimodal recurrent model. Transfer learning experiments show an improvement in performance on the LIRIS-ACCEDE video dataset when pre-trained on EEV. We hope that the size and diversity of the EEV dataset will encourage further explorations in video understanding and affective computing. A subset of EEV is released at https://github.com/google-research-datasets/eev.
Soccer videos can serve as a perfect research object for video understanding because soccer games are played under well-defined rules while complex and intriguing enough for researchers to study. In this paper, we propose a new soccer video database named SoccerDB, comprising 171,191 video segments from 346 high-quality soccer games. The database contains 702,096 bounding boxes, 37,709 essential event labels with time boundary and 17,115 highlight annotations for object detection, action recognition, temporal action localization, and highlight detection tasks. To our knowledge, it is the largest database for comprehensive sports video understanding on various aspects. We further survey a collection of strong baselines on SoccerDB, which have demonstrated state-of-the-art performances on independent tasks. Our evaluation suggests that we can benefit significantly when jointly considering the inner correlations among those tasks. We believe the release of SoccerDB will tremendously advance researches around comprehensive video understanding. {\itshape Our dataset and code published on https://github.com/newsdata/SoccerDB.}
Action Detection is a complex task that aims to detect and classify human actions in video clips. Typically, it has been addressed by processing fine-grained features extracted from a video classification backbone. Recently, thanks to the robustness of object and people detectors, a deeper focus has been added on relationship modelling. Following this line, we propose a graph-based framework to learn high-level interactions between people and objects, in both space and time. In our formulation, spatio-temporal relationships are learned through self-attention on a multi-layer graph structure which can connect entities from consecutive clips, thus considering long-range spatial and temporal dependencies. The proposed module is backbone independent by design and does not require end-to-end training. Extensive experiments are conducted on the AVA dataset, where our model demonstrates state-of-the-art results and consistent improvements over baselines built with different backbones. Code is publicly available at https://github.com/aimagelab/STAGE_action_detection.
This paper introduces video domain generalization where most video classification networks degenerate due to the lack of exposure to the target domains of divergent distributions. We observe that the global temporal features are less generalizable, due to the temporal domain shift that videos from other unseen domains may have an unexpected absence or misalignment of the temporal relations. This finding has motivated us to solve video domain generalization by effectively learning the local-relation features of different timescales that are more generalizable, and exploiting them along with the global-relation features to maintain the discriminability. This paper presents the VideoDG framework with two technical contributions. The first is a new deep architecture named the Adversarial Pyramid Network, which improves the generalizability of video features by capturing the local-relation, global-relation, and cross-relation features progressively. On the basis of pyramid features, the second contribution is a new and robust approach of adversarial data augmentation that can bridge different video domains by improving the diversity and quality of augmented data. We construct three video domain generalization benchmarks in which domains are divided according to different datasets, different consequences of actions, or different camera views, respectively. VideoDG consistently outperforms the combinations of previous video classification models and existing domain generalization methods on all benchmarks.
In static monitoring cameras, useful contextual information can stretch far beyond the few seconds typical video understanding models might see: subjects may exhibit similar behavior over multiple days, and background objects remain static. Due to power and storage constraints, sampling frequencies are low, often no faster than one frame per second, and sometimes are irregular due to the use of a motion trigger. In order to perform well in this setting, models must be robust to irregular sampling rates. In this paper we propose a method that leverages temporal context from the unlabeled frames of a novel camera to improve performance at that camera. Specifically, we propose an attention-based approach that allows our model, Context R-CNN, to index into a long term memory bank constructed on a per-camera basis and aggregate contextual features from other frames to boost object detection performance on the current frame. We apply Context R-CNN to two settings: (1) species detection using camera traps, and (2) vehicle detection in traffic cameras, showing in both settings that Context R-CNN leads to performance gains over strong baselines. Moreover, we show that increasing the contextual time horizon leads to improved results. When applied to camera trap data from the Snapshot Serengeti dataset, Context R-CNN with context from up to a month of images outperforms a single-frame baseline by 17.9% mAP, and outperforms S3D (a 3d convolution based baseline) by 11.2% mAP.
In video understanding, action spotting consists in temporally localizing human-induced events annotated with single timestamps. In this paper, we propose a novel loss function that specifically considers the temporal context naturally present around each action, rather than focusing on the single annotated frame to spot. We benchmark our loss on a large dataset of soccer videos, SoccerNet, and achieve an improvement of 12.8% over the baseline. We show the generalization capability of our loss for generic activity proposals and detection on ActivityNet, by spotting the beginning and the end of each activity. Furthermore, we provide an extended ablation study and display challenging cases for action spotting in soccer videos. Finally, we qualitatively illustrate how our loss induces a precise temporal understanding of actions and show how such semantic knowledge can be used for automatic highlights generation.
This paper presents our approach to the third YouTube-8M video understanding competition that challenges par-ticipants to localize video-level labels at scale to the pre-cise time in the video where the label actually occurs. Ourmodel is an ensemble of frame-level models such as GatedNetVLAD and NeXtVLAD and various BERT models withtest-time augmentation. We explore multiple ways to ag-gregate BERT outputs as video representation and variousways to combine visual and audio information. We proposetest-time augmentation as shifting video frames to one leftor right unit, which adds variety to the predictions and em-pirically shows improvement in evaluation metrics. We firstpre-train the model on the 4M training video-level data, andthen fine-tune the model on 237K annotated video segment-level data. We achieve MAP@100K 0.7871 on private test-ing video segment data, which is ranked 9th over 283 teams.
Training competitive deep video models is an order of magnitude slower than training their counterpart image models. Slow training causes long research cycles, which hinders progress in video understanding research. Following standard practice for training image models, video model training assumes a fixed mini-batch shape: a specific number of clips, frames, and spatial size. However, what is the optimal shape? High resolution models perform well, but train slowly. Low resolution models train faster, but they are inaccurate. Inspired by multigrid methods in numerical optimization, we propose to use variable mini-batch shapes with different spatial-temporal resolutions that are varied according to a schedule. The different shapes arise from resampling the training data on multiple sampling grids. Training is accelerated by scaling up the mini-batch size and learning rate when shrinking the other dimensions. We empirically demonstrate a general and robust grid schedule that yields a significant out-of-the-box training speedup without a loss in accuracy for different models (I3D, non-local, SlowFast), datasets (Kinetics, Something-Something, Charades), and training settings (with and without pre-training, 128 GPUs or 1 GPU). As an illustrative example, the proposed multigrid method trains a ResNet-50 SlowFast network 4.5x faster (wall-clock time, same hardware) while also improving accuracy (+0.8% absolute) on Kinetics-400 compared to the baseline training method. Code is available online.
The point process is a solid framework to model sequential data, such as videos, by exploring the underlying relevance. As a challenging problem for high-level video understanding, weakly supervised action recognition and localization in untrimmed videos has attracted intensive research attention. Knowledge transfer by leveraging the publicly available trimmed videos as external guidance is a promising attempt to make up for the coarse-grained video-level annotation and improve the generalization performance. However, unconstrained knowledge transfer may bring about irrelevant noise and jeopardize the learning model. This paper proposes a novel adaptability decomposing encoder-decoder network to transfer reliable knowledge between trimmed and untrimmed videos for action recognition and localization via bidirectional point process modeling, given only video-level annotations. By decomposing the original features into domain-adaptable and domain-specific ones based on their adaptability, trimmed-untrimmed knowledge transfer can be safely confined within a more coherent subspace. An encoder-decoder based structure is carefully designed and jointly optimized to facilitate effective action classification and temporal localization. Extensive experiments are conducted on two benchmark datasets (i.e., THUMOS14 and ActivityNet1.3), and experimental results clearly corroborate the efficacy of our method.