相关论文: Finding Action Tubes with a Sparse-to-Dense Framew…

The current main stream methods formulate their video saliency mainly from two independent venues, i.e., the spatial and temporal branches. As a complementary component, the main task for the temporal branch is to intermittently focus the…

We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between…

Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between…

Existing tracking algorithms typically rely on low-frame-rate RGB cameras coupled with computationally intensive deep neural network architectures to achieve effective tracking. However, such frame-based methods inherently face challenges…

Multi-frame methods improve monocular depth estimation over single-frame approaches by aggregating spatial-temporal information via feature matching. However, the spatial-temporal feature leads to accuracy degradation in dynamic scenes. To…

Currently, spatiotemporal features are embraced by most deep learning approaches for human action detection in videos, however, they neglect the important features in frequency domain. In this work, we propose an end-to-end network that…

Spatio-temporal action localization consists of three levels of tasks: spatial localization, action classification, and temporal localization. In this work, we propose a new progressive cross-stream cooperation (PCSC) framework that…

Video segmentation aims to segment and track every pixel in diverse scenarios accurately. In this paper, we present Tube-Link, a versatile framework that addresses multiple core tasks of video segmentation with a unified architecture. Our…

State-of-the-art temporal action detectors inefficiently search the entire video for specific actions. Despite the encouraging progress these methods achieve, it is crucial to design automated approaches that only explore parts of the video…

For safety-critical robotics applications such as autonomous driving, it is important to detect all required objects accurately in real-time. Motion segmentation offers a solution by identifying dynamic objects from the scene in a…

Typical video classification methods often divide a video into short clips, do inference on each clip independently, then aggregate the clip-level predictions to generate the video-level results. However, processing visually similar clips…

Temporal action localization is an important step towards video understanding. Most current action localization methods depend on untrimmed videos with full temporal annotations of action instances. However, it is expensive and…

Traditional video action detectors typically adopt the two-stage pipeline, where a person detector is first employed to generate actor boxes and then 3D RoIAlign is used to extract actor-specific features for classification. This detection…

In this paper, we propose a new framework for action localization that tracks people in videos and extracts full-body human tubes, i.e., spatio-temporal regions localizing actions, even in the case of occlusions or truncations. This is…

Modern technological advances have expanded the scope of applications requiring analysis of large-scale datastreams that comprise multiple indefinitely long time series. There is an acute need for statistical methodologies that perform…

Video transformers have achieved impressive results on major video recognition benchmarks, which however suffer from high computational cost. In this paper, we present STTS, a token selection framework that dynamically selects a few…

As moving objects always draw more attention of human eyes, the temporal motive information is always exploited complementarily with spatial information to detect salient objects in videos. Although efficient tools such as optical flow have…

Despite recent advances in video-based action recognition and robust spatio-temporal modeling, most of the proposed approaches rely on the abundance of computational resources to afford running huge and computation-intensive convolutional…

The cognitive system for human action and behavior has evolved into a deep learning regime, and especially the advent of Graph Convolution Networks has transformed the field in recent years. However, previous works have mainly focused on…

Temporal action segmentation (TAS) in videos aims at densely identifying video frames in minutes-long videos with multiple action classes. As a long-range video understanding task, researchers have developed an extended collection of…