相关论文: Spatio-temporal Tubelet Feature Aggregation and Ob…

We consider the problem of localizing a spatio-temporal tube in a video corresponding to a given text query. This is a challenging task that requires the joint and efficient modeling of temporal, spatial and multi-modal interactions. To…

Effective spatiotemporal feature representation is crucial to the video-based action recognition task. Focusing on discriminate spatiotemporal feature learning, we propose Information Fused Temporal Transformation Network (IF-TTN) for…

Modern one-stage video instance segmentation networks suffer from two limitations. First, convolutional features are neither aligned with anchor boxes nor with ground-truth bounding boxes, reducing the mask sensitivity to spatial location.…

It has been well recognized that modeling human-object or object-object relations would be helpful for detection task. Nevertheless, the problem is not trivial especially when exploring the interactions between human actor, object and scene…

This paper addresses spatio-temporal localization of human actions in video. In order to localize actions in time, we propose a recurrent localization network (RecLNet) designed to model the temporal structure of actions on the level of…

Recently, video object segmentation (VOS) networks typically use memory-based methods: for each query frame, the mask is predicted by space-time matching to memory frames. Despite these methods having superior performance, they suffer from…

Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…

The rapid evolution of AIGC technology enables misleading viewers by tampering mere small segments within a video, rendering video-level detection inaccurate and unpersuasive. Consequently, temporal forgery localization (TFL), which aims to…

Multi-object tracking (MOT) is an important and practical task related to both surveillance systems and moving camera applications, such as autonomous driving and robotic vision. However, due to unreliable detection, occlusion and fast…

Existing approaches for spatio-temporal action detection in videos are limited by the spatial extent and temporal duration of the actions. In this paper, we present a modular system for spatio-temporal action detection in untrimmed security…

Frame quality deterioration is one of the main challenges in the field of video understanding. To compensate for the information loss caused by deteriorated frames, recent approaches exploit transformer-based integration modules to obtain…

3D convolutional neural networks have achieved promising results for video tasks in computer vision, including video saliency prediction that is explored in this paper. However, 3D convolution encodes visual representation merely on fixed…

This paper strives to classify and detect the relationship between object tubelets appearing within a video as a <subject-predicate-object> triplet. Where existing works treat object proposals or tubelets as single entities and model their…

Video salient object detection aims at discovering the most visually distinctive objects in a video. How to effectively take object motion into consideration during video salient object detection is a critical issue. Existing…

Learning descriptive spatio-temporal object models from data is paramount for the task of semi-supervised video object segmentation. Most existing approaches mainly rely on models that estimate the segmentation mask based on a reference…

Deep learning has been demonstrated to achieve excellent results for image classification and object detection. However, the impact of deep learning on video analysis (e.g. action detection and recognition) has been limited due to…

In video person re-identification (Re-ID), the network must consistently extract features of the target person from successive frames. Existing methods tend to focus only on how to use temporal information, which often leads to networks…

The tracking-by-detection paradigm today has become the dominant method for multi-object tracking and works by detecting objects in each frame and then performing data association across frames. However, its sequential frame-wise matching…

Traditional video captioning requests a holistic description of the video, yet the detailed descriptions of the specific objects may not be available. Without associating the moving trajectories, these image-based data-driven methods cannot…

Visual-based perception is the key module for autonomous driving. Among those visual perception tasks, video object detection is a primary yet challenging one because of feature degradation caused by fast motion or multiple poses. Current…