Related papers: LAP-Net: Adaptive Features Sampling via Learning A…
Online temporal action localization from an untrimmed video stream is a challenging problem in computer vision. It is challenging because of i) in an untrimmed video stream, more than one action instance may appear, including background…
Online action recognition is an important task for human centered intelligent services, which is still difficult to achieve due to the varieties and uncertainties of spatial and temporal scales of human actions. In this paper, we propose…
We present a novel framework, Action Progression Network (APN), for temporal action detection (TAD) in videos. The framework locates actions in videos by detecting the action evolution process. To encode the action evolution, we quantify a…
Action recognition is an open and challenging problem in computer vision. While current state-of-the-art models offer excellent recognition results, their computational expense limits their impact for many real-world applications. In this…
Recognising human activities from streaming videos poses unique challenges to learning algorithms: predictive models need to be scalable, incrementally trainable, and must remain bounded in size even when the data stream is arbitrarily…
Many video understanding tasks work in the offline setting by assuming that the input video is given from the start to the end. However, many real-world problems require the online setting, making a decision immediately using only the…
This paper proposes a novel memory-based online video representation that is efficient, accurate and predictive. This is in contrast to prior works that often rely on computationally heavy 3D convolutions, ignore actual motion when aligning…
Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level that are then linked or tracked across time. In this paper, we leverage the temporal continuity of videos instead of operating…
Temporal action detection (TAD) aims to detect the semantic labels and boundaries of action instances in untrimmed videos. Current mainstream approaches are multi-step solutions, which fall short in efficiency and flexibility. In this…
This paper addresses the critical need for online action representation, which is essential for various applications like rehabilitation, surveillance, etc. The task can be defined as representation of actions as soon as they happen in a…
Online action detection has attracted increasing research interests in recent years. Current works model historical dependencies and anticipate the future to perceive the action evolution within a video segment and improve the detection…
Adaptive sampling that exploits the spatiotemporal redundancy in videos is critical for always-on action recognition on wearable devices with limited computing and battery resources. The commonly used fixed sampling strategy is not…
Video Recognition has drawn great research interest and great progress has been made. A suitable frame sampling strategy can improve the accuracy and efficiency of recognition. However, mainstream solutions generally adopt hand-crafted…
While deep feature learning has revolutionized techniques for static-image understanding, the same does not quite hold for video processing. Architectures and optimization techniques used for video are largely based off those for static…
Different from traditional action recognition based on video segments, online action recognition aims to recognize actions from unsegmented streams of data in a continuous manner. One way for online recognition is based on the evidence…
Although dense local spatial-temporal features with bag-of-features representation achieve state-of-the-art performance for action recognition, the huge feature number and feature size prevent current methods from scaling up to real size…
In this paper, we propose Two-Stream AMTnet, which leverages recent advances in video-based action representation[1] and incremental action tube generation[2]. Majority of the present action detectors follow a frame-based representation, a…
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…
Online continual learning for image classification is crucial for models to adapt to new data while retaining knowledge of previously learned tasks. This capability is essential to address real-world challenges involving dynamic…
In recent times, learning-based methods for video deraining have demonstrated commendable results. However, there are two critical challenges that these methods are yet to address: exploiting temporal correlations among adjacent frames and…