Exploring Temporal Preservation Networks for Precise 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 (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.

Recently, temporal action localization (TAL), i.e., finding specific action segments in untrimmed videos, has attracted increasing attentions of the computer vision community. State-of-the-art solutions for TAL involves evaluating the frame-level probabilities of three action-indicating phases, i.e. starting, continuing, and ending; and then post-processing these predictions for the final localization. This paper delves deep into this mechanism, and argues that existing methods, by modeling these phases as individual classification tasks, ignored the potential temporal constraints between them. This can lead to incorrect and/or inconsistent predictions when some frames of the video input lack sufficient discriminative information. To alleviate this problem, we introduce two regularization terms to mutually regularize the learning procedure: the Intra-phase Consistency (IntraC) regularization is proposed to make the predictions verified inside each phase; and the Inter-phase Consistency (InterC) regularization is proposed to keep consistency between these phases. Jointly optimizing these two terms, the entire framework is aware of these potential constraints during an end-to-end optimization process. Experiments are performed on two popular TAL datasets, THUMOS14 and ActivityNet1.3. Our approach clearly outperforms the baseline both quantitatively and qualitatively. The proposed regularization also generalizes to other TAL methods (e.g., TSA-Net and PGCN). Code: https://github.com/PeisenZhao/Bottom-Up-TAL-with-MR .

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.

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.

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

APSL: Action-positive separation learning for unsupervised 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%.

Semi-supervised pipe video temporal defect interval localization

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.

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%.

OW-TAL: Learning Unknown Human Activities for Open-World Temporal Action Localization

Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion. To overcome this challenge, one recent work builds an action-click supervision framework. It requires similar annotation costs but can steadily improve the localization performance when compared to the conventional weakly supervised methods. In this paper, by revealing that the performance bottleneck of the existing approaches mainly comes from the background errors, we find that a stronger action localizer can be trained with labels on the background video frames rather than those on the action frames. To this end, we convert the action-click supervision to the background-click supervision and develop a novel method, called BackTAL. Specifically, BackTAL implements two-fold modeling on the background video frames, i.e., the position modeling and the feature modeling. In position modeling, we not only conduct supervised learning on the annotated video frames but also design a score separation module to enlarge the score differences between the potential action frames and backgrounds. In feature modeling, we propose an affinity module to measure frame-specific similarities among neighboring frames and dynamically attend to informative neighbors when calculating temporal convolution. Extensive experiments on three benchmarks are conducted, which demonstrate the high performance of the established BackTAL and the rationality of the proposed background-click supervision.

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.