相关论文: Probabilistic Temporal Masked Attention for Cross-…
We propose Heterogeneous Masked Autoregression (HMA) for modeling action-video dynamics to generate high-quality data and evaluation in scaling robot learning. Building interactive video world models and policies for robotics is difficult…
In this work, we propose a novel Spatial-Temporal Attention (STA) approach to tackle the large-scale person re-identification task in videos. Different from the most existing methods, which simply compute representations of video clips…
In this paper, we introduce Masked Anomaly Detection (MAD), a general self-supervised learning task for multivariate time series anomaly detection. With the increasing availability of sensor data from industrial systems, being able to…
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…
The main progress for action segmentation comes from densely-annotated data for fully-supervised learning. Since manual annotation for frame-level actions is time-consuming and challenging, we propose to exploit auxiliary unlabeled videos,…
Temporal action detection (TAD) is an important yet challenging task in video analysis. Most existing works draw inspiration from image object detection and tend to reformulate it as a proposal generation - classification problem. However,…
Point-supervised Temporal Action Localization (PTAL) adopts a lightly frame-annotated paradigm (\textit{i.e.}, labeling only a single frame per action instance) to train a model to effectively locate action instances within untrimmed…
Temporal Action Detection (TAD) aims to identify and localize actions by determining their starting and ending frames within untrimmed videos. Recent Structured State-Space Models such as Mamba have demonstrated potential in TAD due to…
Video anomaly detection (VAD) -- commonly formulated as a multiple-instance learning problem in a weakly-supervised manner due to its labor-intensive nature -- is a challenging problem in video surveillance where the frames of anomaly need…
With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers from complex Value…
Despite significant progress in video question answering (VideoQA), existing methods fall short of questions that require causal/temporal reasoning across frames. This can be attributed to imprecise motion representations. We introduce…
Human activity recognition (HAR) using drone-mounted cameras has attracted considerable interest from the computer vision research community in recent years. A robust and efficient HAR system has a pivotal role in fields like video…
Although many approaches for multi-human pose estimation in videos have shown profound results, they require densely annotated data which entails excessive man labor. Furthermore, there exists occlusion and motion blur that inevitably lead…
Online Action Detection (OAD) detects actions in streaming videos using past observations. State-of-the-art OAD approaches model past observations and their interactions with an anticipated future. The past is encoded using short- and…
Visual Question and Answering (VQA) problems are attracting increasing interest from multiple research disciplines. Solving VQA problems requires techniques from both computer vision for understanding the visual contents of a presented…
Training temporal action detection in videos requires large amounts of labeled data, yet such annotation is expensive to collect. Incorporating unlabeled or weakly-labeled data to train action detection model could help reduce annotation…
Recent advancements in sequence prediction have significantly improved the accuracy of video data interpretation; however, existing models often overlook the potential of attention-based mechanisms for next-frame prediction. This study…
Anticipating future actions based on spatiotemporal observations is essential in video understanding and predictive computer vision. Moreover, a model capable of anticipating the future has important applications, it can benefit…
In this paper we propose a novel approach to multi-action recognition that performs joint segmentation and classification. This approach models each action using a Gaussian mixture using robust low-dimensional action features. Segmentation…
Fusing multi-modality information is known to be able to effectively bring significant improvement in video classification. However, the most popular method up to now is still simply fusing each stream's prediction scores at the last stage.…