Related papers: A Comprehensive Study on Temporal Modeling for Onl…
In online action detection, the goal is to detect the start of an action in a video stream as soon as it happens. For instance, if a child is chasing a ball, an autonomous car should recognize what is going on and respond immediately. This…
Anomaly detection in video surveillance has recently gained interest from the research community. Temporal duration of anomalies vary within video streams, leading to complications in learning the temporal dynamics of specific events. This…
Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure.…
Temporally consistent depth estimation is crucial for online applications such as augmented reality. While stereo depth estimation has received substantial attention as a promising way to generate 3D information, there is relatively little…
Open-Vocabulary Temporal Action Detection (OV-TAD) aims to classify and localize action segments in untrimmed videos for unseen categories. Previous methods rely solely on global alignment between label-level semantics and visual features,…
Temporal action segmentation (TAS) is a critical step toward long-term video understanding. Recent studies follow a pattern that builds models based on features instead of raw video picture information. However, we claim those models are…
Real-world machine learning applications often face simultaneous covariate and semantic shifts, challenging traditional domain generalization and out-of-distribution (OOD) detection methods. We introduce Meta-learned Across Domain…
Video Anomaly Detection (VAD) identifies unusual activities in video streams, a key technology with broad applications ranging from surveillance to healthcare. Tackling VAD in real-life settings poses significant challenges due to the…
Temporal action localization aims at localizing action instances from untrimmed videos. Existing works have designed various effective modules to precisely localize action instances based on appearance and motion features. However, by…
As a novel 3D scene representation, semantic occupancy has gained much attention in autonomous driving. However, existing occupancy prediction methods mainly focus on designing better occupancy representations, such as tri-perspective view…
Out-of-distribution (OOD) detection aims to detect "unknown" data whose labels have not been seen during the in-distribution (ID) training process. Recent progress in representation learning gives rise to distance-based OOD detection that…
Online temporal action segmentation shows a strong potential to facilitate many HRI tasks where extended human action sequences must be tracked and understood in real time. Traditional action segmentation approaches, however, operate in an…
This paper presents a novel spatiotemporal transformer network that introduces several original components to detect actions in untrimmed videos. First, the multi-feature selective semantic attention model calculates the correlations…
Out-of-distribution detection (OOD) is a pivotal task for real-world applications that trains models to identify samples that are distributionally different from the in-distribution (ID) data during testing. Recent advances in AI,…
How can models effectively detect out-of-distribution (OOD) samples in complex, multi-label settings without extensive retraining? Existing OOD detection methods struggle to capture the intricate semantic relationships and label…
Driver distractions are known to be the dominant cause of road accidents. While monitoring systems can detect non-driving-related activities and facilitate reducing the risks, they must be accurate and efficient to be applicable.…
Temporal modeling plays a crucial role in understanding video content. To tackle this problem, previous studies built complicated temporal relations through time sequence thanks to the development of computationally powerful devices. In…
Temporal understanding in autonomous driving (AD) remains a significant challenge, even for recent state-of-the-art (SoTA) Vision-Language Models (VLMs). Prior work has introduced datasets and benchmarks aimed at improving temporal…
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…
Various approaches have been proposed for out-of-distribution (OOD) detection by augmenting models, input examples, training sets, and optimization objectives. Deviating from existing work, we have a simple hypothesis that standard…