Related papers: SimOn: A Simple Framework for Online Temporal Acti…
Despite the recent progress in video understanding and the continuous rate of improvement in temporal action localization throughout the years, it is still unclear how far (or close?) we are to solving the problem. To this end, we introduce…
Predicting motion of surrounding agents is critical to real-world applications of tactical path planning for autonomous driving. Due to the complex temporal dependencies and social interactions of agents, on-line trajectory prediction is a…
Online action detection in untrimmed videos aims to identify an action as it happens, which makes it very important for real-time applications. Previous methods rely on tedious annotations of temporal action boundaries for training, which…
The task of action detection aims at deducing both the action category and localization of the start and end moment for each action instance in a long, untrimmed video. While vision Transformers have driven the recent advances in video…
The crux of semi-supervised temporal action localization (SS-TAL) lies in excavating valuable information from abundant unlabeled videos. However, current approaches predominantly focus on building models that are robust to the error-prone…
Weakly supervised video object localization (WSVOL) allows locating object in videos using only global video tags such as object class. State-of-art methods rely on multiple independent stages, where initial spatio-temporal proposals are…
We present ActionPlan, a unified motion diffusion framework that bridges real-time streaming with high-quality offline generation within a single model. The core idea is to introduce a per-frame action plan: the model predicts frame-level…
Learning to localize actions in long, cluttered, and untrimmed videos is a hard task, that in the literature has typically been addressed assuming the availability of large amounts of annotated training samples for each class -- either in a…
We present our solution to the BinEgo-360 Challenge at ICCV 2025, which focuses on temporal action localization (TAL) in multi-perspective and multi-modal video settings. The challenge provides a dataset containing panoramic, third-person,…
Localizing actions in video is a core task in computer vision. The weakly supervised temporal localization problem investigates whether this task can be adequately solved with only video-level labels, significantly reducing the amount of…
In this work, we address the problem of spatio-temporal action detection in temporally untrimmed videos. It is an important and challenging task as finding accurate human actions in both temporal and spatial space is important for analyzing…
Human action recognition from well-segmented 3D skeleton data has been intensively studied and has been attracting an increasing attention. Online action detection goes one step further and is more challenging, which identifies the action…
We tackle the problem of localizing temporal intervals of actions with only a single frame label for each action instance for training. Owing to label sparsity, existing work fails to learn action completeness, resulting in fragmentary…
Temporal action detection aims to locate the boundaries of action in the video. The current method based on boundary matching enumerates and calculates all possible boundary matchings to generate proposals. However, these methods neglect…
Video captioning is an essential technology to understand scenes and describe events in natural language. To apply it to real-time monitoring, a system needs not only to describe events accurately but also to produce the captions as soon as…
We propose a weakly supervised temporal action localization algorithm on untrimmed videos using convolutional neural networks. Our algorithm learns from video-level class labels and predicts temporal intervals of human actions with no…
Weakly-supervised temporal action localization aims to localize and recognize actions in untrimmed videos with only video-level category labels during training. Without instance-level annotations, most existing methods follow the…
Video salient object detection (SOD) relies on motion cues to distinguish salient objects from backgrounds, but training such models is limited by scarce video datasets compared to abundant image datasets. Existing approaches that use…
Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with closed-set setting on large training data, recent zero-shot…
Temporal action localization is an important yet challenging problem. Given a long, untrimmed video consisting of multiple action instances and complex background contents, we need not only to recognize their action categories, but also to…