Bottom-Up Temporal Action Localization with Mutual Regularization

Temporal Action Localization (TAL) aims to classify and localize all actions within untrimmed videos. Existing TAL methods often struggle with inaccurate boundary predictions due to the similarity of action content and the uncertainty of boundaries between adjacent frames. Many of these methods rely on fixed or global proposal learning strategies, which lack a more refined method to improve localization accuracy. In this paper, we propose BRTAL, a new Boundary Refinement framework for TAL based on an offset-driven diffusion model, specifically designed to enhance action boundary precision through a refined approach iteratively. Unlike traditional TAL methods emphasizing global target predictions, BRTAL adopts a local refinement perspective by leveraging an offset-driven strategy. Specifically, our framework employs diffusion to iteratively generate local offsets between predictions and ground truth, gradually reducing these offsets to achieve better alignment with the ground truth. This refined approach is particularly effective in addressing the challenges of ambiguous boundaries frequently encountered in TAL, enabling BRTAL to achieve more refined boundary localization than existing methods. Furthermore, we introduce a lightweight yet powerful Temporal Context Modeling (TCM) module to enhance temporal information modeling for accurate action localization. TCM features a Temporal Representation Perception (TRP) layer, which captures temporal evolution and long-term contextual dependencies through a squeeze-and-excitation design combined with large convolutional kernels, ensuring robust temporal representation learning. Extensive experiments on THUMOS14, ActivityNet-1.3, and EPIC-KITCHEN 100 datasets highlight the significant advantages of BRTAL. Notably, BRTAL achieves an average mAP of 69.6% on THUMOS14, establishing a new state-of-the-art benchmark and demonstrating its outstanding boundary refinement capability.

Temporal Action Localization (TAL) aims to identify the boundaries of actions and their corresponding categories in untrimmed videos. Most existing methods simultaneously process past and future information, neglecting the inherently sequential nature of action occurrence. This confused treatment of past and future information hinders the model’s ability to understand action procedures effectively. To address these issues, we propose Bidirectional Feature Splitting with Cross-Layer Fusion for Temporal Action Localization (BFSTAL), a new bidirectional feature-splitting approach based on Mamba for the TAL task, composed of two core parts, Decomposed Bidirectionally Hybrid (DBH) and Cross-Layer Fusion Detection (CLFD), which explicitly enhances the model’s capacity to understand action procedures, especially to localize temporal boundaries of actions. Specifically, we introduce the Decomposed Bidirectionally Hybrid (DBH) component, which splits video features at a given timestamp into forward features (past information) and backward features (future information). DBH integrates three key modules: Bidirectional Multi-Head Self-Attention (Bi-MHSA), Bidirectional State Space Model (Bi-SSM), and Bidirectional Convolution (Bi-CONV). DBH effectively captures long-range dependencies by combining state-space modeling, attention mechanisms, and convolutional networks while improving spatial-temporal awareness. Furthermore, we propose Cross-Layer Fusion Detection (CLFD), which aggregates multi-scale features from different pyramid levels, enhancing contextual understanding and temporal action localization precision. Extensive experiments demonstrate that BFSTAL outperforms other methods on four widely used TAL benchmarks: THUMOS14, EPIC-KITCHENS 100, Charades, and MultiTHUMOS.

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.

APSL: Action-positive separation learning for unsupervised temporal action localization

Temporal action localization is an important task of computer vision. Though a variety of methods have been proposed, it still remains an open question how to predict the temporal boundaries of action segments precisely. Most works use segment-level classifiers to select video segments pre-determined by action proposal or dense sliding windows. However, in order to achieve more precise action boundaries, a temporal localization system should make dense predictions at a fine granularity. A newly proposed work exploits Convolutional-Deconvolutional-Convolutional (CDC) filters to upsample the predictions of 3D ConvNets, making it possible to perform per-frame action predictions and achieving promising performance in terms of temporal action localization. However, CDC network loses temporal information partially due to the temporal downsampling operation. In this paper, we propose an elegant and powerful Temporal Preservation Convolutional (TPC) Network that equips 3D ConvNets with TPC filters. TPC network can fully preserve temporal resolution and downsample the spatial resolution simultaneously, enabling frame-level granularity action localization with minimal loss of time information. TPC network can be trained in an end-to-end manner. Experiment results on public datasets show that TPC network achieves significant improvement in both per-frame action prediction and segment-level temporal action localization.

Temporal action localization is a fundamental video understanding task. Meanwhile, due to the complex video background, the varied duration and amplitude of the actions, it is also a considerable challenge. Currently, offline class-semantics representation is the mainstream input of this task since untrimmed videos occupy a large memory, high-quality untrimmed videos and annotations are difficult to access. Because these representations only focus on the class-semantics information, they are sub-optimal for the temporal action localization tasks. At the same time, the exploration of localization-semantics representation is very few due to the high resource consumption. Therefore, it is necessary to improve the detection capability of class-semantics representation directly. As an exploration, we propose the ForeBack module to enhance class-semantics features’ locating performance by augmenting the distinction modeling between foreground and background clips. This module could also eliminate part of the noise of inference probability sequences. Furthermore, we use phased training to learn and use the ForeBack module more effectively. Finally, we reveal the effectiveness of our approach by conduct experiments on THUMOS-14 and the mAP at tIoU@0.5 is improved from 38.8% (BMN action detection baseline) to 47.1%.

The main challenge of Temporal Action Localization is to retrieve subtle human actions from various co-occurring ingredients, e.g., context and background, in an untrimmed video. While prior approaches have achieved substantial progress through devising advanced action detectors, they still suffer from these co-occurring ingredients which often dominate the actual action content in videos. In this paper, we explore two orthogonal but complementary aspects of a video snippet, i.e., the action features and the co-occurrence features. Especially, we develop a novel auxiliary task by decoupling these two types of features within a video snippet and recombining them to generate a new feature representation with more salient action information for accurate action localization. We term our method RefactorNet, which first explicitly factorizes the action content and regularizes its co-occurrence features, and then synthesizes a new action-dominated video representation. Extensive experimental results and ablation studies on THUMOS14 and ActivityNet v 1.3 demonstrate that our new representation, combined with a simple action detector, can significantly improve the action localization performance.

PcmNet: Position-sensitive context modeling network for temporal action localization

Temporal action localization is an important task of computer vision. Though many methods have been proposed, it still remains an open question how to predict the temporal location of action segments precisely. Most state-of-the-art works train action classifiers on video segments pre-determined by action proposal. However, recent work found that a desirable model should move beyond segment-level and make dense predictions at a fine granularity in time to determine precise temporal boundaries. In this paper, we propose a Frame Segmentation Network (FSN) that places a temporal CNN on top of the 2D spatial CNNs. Spatial CNNs are responsible for abstracting semantics in spatial dimension while temporal CNN is responsible for introducing temporal context information and performing dense predictions. The proposed FSN can make dense predictions at frame-level for a video clip using both spatial and temporal context information. FSN is trained in an end-to-end manner, so the model can be optimized in spatial and temporal domain jointly. Experiment results on public dataset show that FSN achieves superior performance in both frame-level action localization and temporal action localization.

Exploring frame segmentation networks for temporal action localization

Temporal action localization in untrimmed long videos is an important yet challenging problem. The temporal ambiguity and the intra-class variations of temporal structure of actions make existing methods far from being satisfactory. In this paper, we propose a novel framework which firstly models each action clip based on its temporal evolution, and then adopts a deep multiple instance learning (MIL) network for jointly classifying action clips and refining their temporal boundaries. The proposed network utilizes a MIL scheme to make clip-level decisions based on temporal-instance-level decisions. Besides, a temporal smoothness constraint is introduced into the multi-task loss. We evaluate our framework on THUMOS Challenge 2014 benchmark and the experimental results show that it achieves considerable improvements as compared to the state-of-the-art methods. The performance gain is especially remarkable under precise localization with high tIoU thresholds, e.g. mAP@tIoU=0.5 is improved from 31.0% to 35.0%.

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.

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.}

Nowadays, automatic video analysis using state-of-the-art machine learning techniques is highly relevant and finds lots of industrial applications. This approach gives the possibility to solve a set of the problems such as finding the main part of the video, tracking in time by the duration of an action that is labor-intensive and almost impossible to be solved manually or by old-fashioned methods. One of the most promising approaches is the Weakly-supervised method. The Weakly-supervised technique can be used for temporal action localization, which is a challenging task because it uses only video-level labels during the training. The main benefit of this method is that it is not required to create large-scale datasets with temporal annotations, which are quite time-consuming. In this work, we propose to improve the current state-of-the-art in temporal action localization by introducing the new feature extraction procedure. We achieved better results on the RGB stream by making the new feature extraction using more powerful neural network models on the benchmark THUMOS”14 dataset [1]. We also provide a deep analysis of the importance of the feature extraction procedure in the whole workflow for temporal action detection. The results of our investigations can be applied directly for solving a wide range of industrial problems in a robust and accurate manner.

Semi-supervised pipe video temporal defect interval localization