ترغب بنشر مسار تعليمي؟ اضغط هنا

Temporal Action Detection with Multi-level Supervision

335   0   0.0 ( 0 )
 نشر من قبل Baifeng Shi
 تاريخ النشر 2020
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Training temporal action detection in videos requires large amounts of labeled data, yet such annotation is expensive to collect. Incorporating unlabeled or weakly-labeled data to train action detection model could help reduce annotation cost. In this work, we first introduce the Semi-supervised Action Detection (SSAD) task with a mixture of labeled and unlabeled data and analyze different types of errors in the proposed SSAD baselines which are directly adapted from the semi-supervised classification task. To alleviate the main error of action incompleteness (i.e., missing parts of actions) in SSAD baselines, we further design an unsupervised foreground attention (UFA) module utilizing the independence between foreground and background motion. Then we incorporate weakly-labeled data into SSAD and propose Omni-supervised Action Detection (OSAD) with three levels of supervision. An information bottleneck (IB) suppressing the scene information in non-action frames while preserving the action information is designed to help overcome the accompanying action-context confusion problem in OSAD baselines. We extensively benchmark against the baselines for SSAD and OSAD on our created data splits in THUMOS14 and ActivityNet1.2, and demonstrate the effectiveness of the proposed UFA and IB methods. Lastly, the benefit of our full OSAD-IB model under limited annotation budgets is shown by exploring the optimal annotation strategy for labeled, unlabeled and weakly-labeled data.



قيم البحث

اقرأ أيضاً

Spatio-temporal action detection in videos requires localizing the action both spatially and temporally in the form of an action tube. Nowadays, most spatio-temporal action detection datasets (e.g. UCF101-24, AVA, DALY) are annotated with action tube s that contain a single person performing the action, thus the predominant action detection models simply employ a person detection and tracking pipeline for localization. However, when the action is defined as an interaction between multiple objects, such methods may fail since each bounding box in the action tube contains multiple objects instead of one person. In this paper, we study the spatio-temporal action detection problem with multi-object interaction. We introduce a new dataset that is annotated with action tubes containing multi-object interactions. Moreover, we propose an end-to-end spatio-temporal action detection model that performs both spatial and temporal regression simultaneously. Our spatial regression may enclose multiple objects participating in the action. During test time, we simply connect the regressed bounding boxes within the predicted temporal duration using a simple heuristic. We report the baseline results of our proposed model on this new dataset, and also show competitive results on the standard benchmark UCF101-24 using only RGB input.
Weakly-supervised temporal action localization aims to localize actions in untrimmed videos with only video-level action category labels. Most of previous methods ignore the incompleteness issue of Class Activation Sequences (CAS), suffering from tri vial localization results. To solve this issue, we introduce an adaptive mutual supervision framework (AMS) with two branches, where the base branch adopts CAS to localize the most discriminative action regions, while the supplementary branch localizes the less discriminative action regions through a novel adaptive sampler. The adaptive sampler dynamically updates the input of the supplementary branch with a sampling weight sequence negatively correlated with the CAS from the base branch, thereby prompting the supplementary branch to localize the action regions underestimated by the base branch. To promote mutual enhancement between these two branches, we construct mutual location supervision. Each branch leverages location pseudo-labels generated from the other branch as localization supervision. By alternately optimizing the two branches in multiple iterations, we progressively complete action regions. Extensive experiments on THUMOS14 and ActivityNet1.2 demonstrate that the proposed AMS method significantly outperforms the state-of-the-art methods.
Temporal action detection (TAD) aims to determine the semantic label and the boundaries of every action instance in an untrimmed video. It is a fundamental and challenging task in video understanding and significant progress has been made. Previous m ethods involve multiple stages or networks and hand-designed rules or operations, which fall short in efficiency and flexibility. In this paper, we propose an end-to-end framework for TAD upon Transformer, termed textit{TadTR}, which maps a set of learnable embeddings to action instances in parallel. TadTR is able to adaptively extract temporal context information required for making action predictions, by selectively attending to a sparse set of snippets in a video. As a result, it simplifies the pipeline of TAD and requires lower computation cost than previous detectors, while preserving remarkable detection performance. TadTR achieves state-of-the-art performance on HACS Segments (+3.35% average mAP). As a single-network detector, TadTR runs 10$times$ faster than its comparable competitor. It outperforms existing single-network detectors by a large margin on THUMOS14 (+5.0% average mAP) and ActivityNet (+7.53% average mAP). When combined with other detectors, it reports 54.1% mAP at IoU=0.5 on THUMOS14, and 34.55% average mAP on ActivityNet-1.3. Our code will be released at url{https://github.com/xlliu7/TadTR}.
Given a sufficiently large training dataset, it is relatively easy to train a modern convolution neural network (CNN) as a required image classifier. However, for the task of fish classification and/or fish detection, if a CNN was trained to detect o r classify particular fish species in particular background habitats, the same CNN exhibits much lower accuracy when applied to new/unseen fish species and/or fish habitats. Therefore, in practice, the CNN needs to be continuously fine-tuned to improve its classification accuracy to handle new project-specific fish species or habitats. In this work we present a labelling-efficient method of training a CNN-based fish-detector (the Xception CNN was used as the base) on relatively small numbers (4,000) of project-domain underwater fish/no-fish images from 20 different habitats. Additionally, 17,000 of known negative (that is, missing fish) general-domain (VOC2012) above-water images were used. Two publicly available fish-domain datasets supplied additional 27,000 of above-water and underwater positive/fish images. By using this multi-domain collection of images, the trained Xception-based binary (fish/not-fish) classifier achieved 0.17% false-positives and 0.61% false-negatives on the projects 20,000 negative and 16,000 positive holdout test images, respectively. The area under the ROC curve (AUC) was 99.94%.
Action Unit (AU) detection plays an important role for facial expression recognition. To the best of our knowledge, there is little research about AU analysis for micro-expressions. In this paper, we focus on AU detection in micro-expressions. Microe xpression AU detection is challenging due to the small quantity of micro-expression databases, low intensity, short duration of facial muscle change, and class imbalance. In order to alleviate the problems, we propose a novel Spatio-Temporal Adaptive Pooling (STAP) network for AU detection in micro-expressions. Firstly, STAP is aggregated by a series of convolutional filters of different sizes. In this way, STAP can obtain multi-scale information on spatial and temporal domains. On the other hand, STAP contains less parameters, thus it has less computational cost and is suitable for micro-expression AU detection on very small databases. Furthermore, STAP module is designed to pool discriminative information for micro-expression AUs on spatial and temporal domains.Finally, Focal loss is employed to prevent the vast number of negatives from overwhelming the microexpression AU detector. In experiments, we firstly polish the AU annotations on three commonly used databases. We conduct intensive experiments on three micro-expression databases, and provide several baseline results on micro-expression AU detection. The results show that our proposed approach outperforms the basic Inflated inception-v1 (I3D) in terms of an average of F1- score. We also evaluate the performance of our proposed method on cross-database protocol. It demonstrates that our proposed approach is feasible for cross-database micro-expression AU detection. Importantly, the results on three micro-expression databases and cross-database protocol provide extensive baseline results for future research on micro-expression AU detection.
التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا