Adaptive Prototype Learning for Weakly-Supervised Temporal Action Localization.

Detecting actions in videos have been widely applied in on-device applications, such as cars, robots, etc. Practical on-device videos are always untrimmed with both action and background. It is desirable for a model to both recognize the class of action and localize the temporal position where the action happens. Such a task is called temporal action location (TAL), which is always trained on the cloud where multiple untrimmed videos are collected and labeled. It is desirable for a TAL model to continuously and locally learn from new data, which can directly improve the action detection precision while protecting customers’ privacy. However, directly training a TAL model on the device is nontrivial. To train a TAL model which can precisely recognize and localize each action, tremendous video samples with temporal annotations are required. However, annotating videos frame by frame is exorbitantly time consuming and expensive. Although weakly supervised temporal action localization (W-TAL) has been proposed to learn from untrimmed videos with only video-level labels, such an approach is also not suitable for on-device learning scenarios. In practical on-device learning applications, data are collected in streaming. For example, the camera on the device keeps collecting video frames for hours or days, and the actions of nearly all classes are included in a single long video stream. Dividing such a long video stream into multiple video segments requires lots of human effort, which hinders the exploration of applying the TAL tasks to realistic on-device learning applications. To enable W-TAL models to learn from a long, untrimmed streaming video, we propose an efficient video learning approach that can directly adapt to new environments. We first propose a self-adaptive video dividing approach with a contrast score-based segment merging approach to convert the video stream into multiple segments. Then, we explore different sampling strategies on the TAL tasks to request as few labels as possible. To the best of our knowledge, we are the first attempt to directly learn from the on-device, long video stream. Experimental results on the THUMOS’14 dataset show that the performance of our approach is comparable to the current W-TAL state-of-the-art (SOTA) work without any laborious manual video splitting.

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 weakly supervised (WSAL) and unsupervised temporal action localization (UAL), the target is to simultaneously localize temporal boundaries and identify category labels of actions with only video-level category labels (WSAL) or category numbers in a dataset (UAL) during training. Among existing methods, attention based methods have achieved superior performance in both tasks by highlighting action segments with foreground attention weights. However, without the segment-level supervision on the attention weight learning, the quality of the attention weight hinders the performance of these methods. In this paper, we propose a novel Uncertainty Guided Collaborative Training (UGCT) strategy to alleviate this problem, which mainly includes two key designs: (1) The first design is an online pseudo label generation module, in which the RGB and FLOW streams work collaboratively to learn from each other. (2) The second design is an uncertainty aware learning module, which can mitigate the noise in the generated pseudo labels. These two designs work together to promote the model performance effectively and efficiently by exchanging information between RGB and FLOW streams. Extensive experimental results on two benchmark datasets with three attention based methods demonstrate the effectiveness of the proposed method, e.g, more than 7.0% performance gain for mAP@IoU=0.5 on THUMOS14 dataset.

In this paper, we explore the problem of Weakly-supervised Temporal Action Localization (W-TAL), where the task is to localize the temporal boundaries of all action instances in an untrimmed video with only video-level supervision. The existing W-TAL methods achieve a good action localization performance by separating the discriminative action and background frames. However, there is still a large performance gap between the weakly and fully supervised methods. The main reason comes from that there are plenty of ambiguous action and background frames in addition to the discriminative action and background frames. Due to the lack of temporal annotations in W-TAL, the ambiguous background frames may be localized as foreground and the ambiguous action frames may be suppressed as background, which result in false positives and false negatives, respectively. In this paper, we introduce a novel collaborative Foreground, Background, and Action Modeling Network (FBA-Net) to suppress the background (i.e., both the discriminative and ambiguous background) frames, and localize the actual-action-related (i.e., both the discriminative and ambiguous action) frames as foreground, for the precise temporal action localization. We design our FBA-Net with three branches: the foreground modeling (FM) branch, the background modeling (BM) branch, and the class-specific action and background modeling (CM) branch. The CM branch learns to highlight the video frames related to <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</i> action classes, and separate the action-related frames of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</i> action classes from the ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</i> + 1)th background class. The collaboration between FM and CM regularizes the consistency between the FM and the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</i> action classes of CM, which reduces the false negative rate by localizing different actual-action-related (i.e., both the discriminative and ambiguous action) frames in a video as foreground. On the other hand, the collaboration between BM and CM regularizes the consistency between the BM and the ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</i> + 1)th background class of CM, which reduces the false positive rate by suppressing both the discriminative and ambiguous background frames. Furthermore, the collaboration between FM and BM enforces more effective foreground-background separation. To evaluate the effectiveness of our FBA-Net, we perform extensive experiments on two challenging datasets, THUMOS14 and ActivityNet1.3. The experiments show that our FBA-Net attains superior results.

Weakly-supervised temporal action localization is a very challenging problem because frame-wise labels are not given in the training stage while the only hint is video-level labels: whether each video contains action frames of interest. Previous methods aggregate frame-level class scores to produce video-level prediction and learn from video-level action labels. This formulation does not fully model the problem in that background frames are forced to be misclassified as action classes to predict video-level labels accurately. In this paper, we design Background Suppression Network (BaS-Net) which introduces an auxiliary class for background and has a two-branch weight-sharing architecture with an asymmetrical training strategy. This enables BaS-Net to suppress activations from background frames to improve localization performance. Extensive experiments demonstrate the effectiveness of BaS-Net and its superiority over the state-of-the-art methods on the most popular benchmarks – THUMOS'14 and ActivityNet. Our code and the trained model are available at https://github.com/Pilhyeon/BaSNet-pytorch.

Weakly-supervised temporal action localization (WTAL) in untrimmed videos has emerged as a practical but challenging task since only video-level labels are available. Existing approaches typically leverage off-the-shelf segment-level features, which suffer from spatial incompleteness and temporal incoherence, thus limiting their performance. In this paper, we tackle this problem from a new perspective by enhancing segment-level representations with a simple yet effective graph convolutional network, namely action complement graph network (ACGNet). It facilitates the current video segment to perceive spatial-temporal dependencies from others that potentially convey complementary clues, implicitly mitigating the negative effects caused by the two issues above. By this means, the segment-level features are more discriminative and robust to spatial-temporal variations, contributing to higher localization accuracies. More importantly, the proposed ACGNet works as a universal module that can be flexibly plugged into different WTAL frameworks, while maintaining the end-to-end training fashion. Extensive experiments are conducted on the THUMOS'14 and ActivityNet1.2 benchmarks, where the state-of-the-art results clearly demonstrate the superiority of the proposed approach.

Context Sensitive Network for weakly-supervised fine-grained temporal action localization.

Weakly-supervised temporal action localization (W-TAL) aims to classify and localize all action instances in untrimmed videos under only video-level supervision. Without frame-level annotations, it is challenging for W-TAL methods to clearly distinguish actions and background, which severely degrades the action boundary localization and action proposal scoring. In this paper, we present an adaptive two-stream consensus network (A-TSCN) to address this problem. Our A-TSCN features an iterative refinement training scheme: a frame-level pseudo ground truth is generated and iteratively updated from a late-fusion activation sequence, and used to provide frame-level supervision for improved model training. Besides, we introduce an adaptive attention normalization loss, which adaptively selects action and background snippets according to video attention distribution. By differentiating the attention values of the selected action snippets and background snippets, it forces the predicted attention to act as a binary selection and promotes the precise localization of action boundaries. Furthermore, we propose a video-level and a snippet-level uncertainty estimator, and they can mitigate the adverse effect caused by learning from noisy pseudo ground truth. Experiments conducted on the THUMOS14, ActivityNet v1.2, ActivityNet v1.3, and HACS datasets show that our A-TSCN outperforms current state-of-the-art methods, and even achieves comparable performance with several fully-supervised methods.

As a challenging task of high-level video understanding, Weakly-supervised Temporal Action Localization (WTAL) has attracted increasing attention in recent years. However, due to the weak supervisions of whole-video classification labels, it is challenging to accurately determine action instance boundaries. To address this issue, pseudo-label-based methods [Alwassel et al. (2019), Luo et al. (2020), and Zhai et al. (2020)] were proposed to generate snippet-level pseudo labels from classification results. In spite of the promising performance, these methods hardly take full advantages of multiple modalities, i.e., RGB and optical flow sequences, to generate high quality pseudo labels. Most of them ignored how to mitigate the label noise, which hinders the capability of the network on learning discriminative feature representations. To address these challenges, we propose a Multi-Modality Self-Distillation (MMSD) framework, which contains two single-modal streams and a fused-modal stream to perform multi-modality knowledge distillation and multi-modality self-voting. On the one hand, multi-modality knowledge distillation improves snippet-level classification performance by transferring knowledge between single-modal streams and a fused-modal stream. On the other hand, multi-modality self-voting mitigates the label noise in a modality voting manner according to the reliability and complementarity of the streams. Experimental results on THUMOS14 and ActivityNet1.3 datasets demonstrate the effectiveness of our method and superior performance over state-of-the-art approaches. Our code is available at https://github.com/LeonHLJ/MMSD.

Weakly-supervised temporal action localization (WTAL) has recently attracted attentions. Many of the state-of-the-art methods usually utilize temporal class activation map (T-CAM) to obtain target action temporal regions. However, class-specific T-CAM tends to cover only the most discriminative part of the actions, not the entire action. In this paper, we propose an erasing strategy for mining discriminative regions in weakly-supervised temporal action localization (DRES). DRES achieves better performance with action localization, which can be attribute to two aspects. First, we employ the salient detection module, which suppresses the background to obtain the most discriminative regions. Second, we design the eraser module to discover the missed action regions by the salient detection module, which complements action regions. Based on experiments, we demonstrate that DRES improve the state-of-the-art performance on THUMOS’14.

Weakly-supervised temporal action localization aims to predict when and what actions occur in untrimmed videos with only video-level class labels. Most current methods make prediction based on global features, while ignoring the classification performance of local descriptions of human body. Additionally, these methods generate incomplete proposals via thresholding, which is too single and crude. To acquire high-quality proposals, we focus on incorporating local information, i.e. human body poses in videos, and propose a noval method called Class Activation and Pose Pattern (CAPP) for weakly-supervised temporal action localization. In our method, action proposals are generated by two modules: a Class Activation Sequence (CAS) module and a Pose Pattern Sequence (PPS) module. The CAS module fuses global features and local features to improve clip-level classification performance and the PPS module adds complementary proposals with high recall via pose pattern clustering. CAPP outperforms the state-of-the-art methods on both the THUMOS-14 and ActivityNet v1.2 datasets, which demonstrates the effectiveness of our method.

Entropy guided attention network for weakly-supervised action localization

Most activity localization methods in the literature suffer from the burden of frame-wise annotation requirement. Learning from weak labels may be a potential solution towards reducing such manual labeling effort. Recent years have witnessed a substantial influx of tagged videos on the Internet, which can serve as a rich source of weakly-supervised training data. Specifically, the correlations between videos with similar tags can be utilized to temporally localize the activities. Towards this goal, we present W-TALC, a Weakly-supervised Temporal Activity Localization and Classification framework using only video-level labels. The proposed network can be divided into two sub-networks, namely the Two-Stream based feature extractor network and a weakly-supervised module, which we learn by optimizing two complimentary loss functions. Qualitative and quantitative results on two challenging datasets - Thumos14 and ActivityNet1.2, demonstrate that the proposed method is able to detect activities at a fine granularity and achieve better performance than current state-of-the-art methods.

Deep feature enhancing and selecting network for weakly supervised temporal action localization

Exploring frame segmentation networks for temporal action localization