相关论文: Boundary-Recovering Network for Temporal Action De…

Image Classification and Video Action Recognition are perhaps the two most foundational tasks in computer vision. Consequently, explaining the inner workings of trained deep neural networks is of prime importance. While numerous efforts…

The goal of video-based person re-identification is to match two input videos, so that the distance of the two videos is small if two videos contain the same person. A common approach for person re-identification is to first extract image…

Currently, one-stage frameworks have been widely applied for temporal action detection, but they still suffer from the challenge that the action instances span a wide range of time. The reason is that these one-stage detectors, e.g., Single…

Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with closed-set setting on large training data, recent zero-shot…

Machine unlearning has reached a critical bottleneck. As traditional weight-space interventions focus primarily on erasing targeted concepts, they often fail to prevent the unintended suppression of other significant representations. This…

Deep neural networks have achieved remarkable success for video-based action recognition. However, most of existing approaches cannot be deployed in practice due to the high computational cost. To address this challenge, we propose a new…

Traffic signs play a critical role in road safety and traffic management for autonomous driving systems. Accurate traffic sign classification is essential but challenging due to real-world complexities like adversarial examples and…

Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled service systems. Existing methods require training one specific model for each dataset, which exhibits limited generalization…

Temporal action detection aims to locate the boundaries of action in the video. The current method based on boundary matching enumerates and calculates all possible boundary matchings to generate proposals. However, these methods neglect…

In recent years, a number of approaches based on 2D or 3D convolutional neural networks (CNN) have emerged for video action recognition, achieving state-of-the-art results on several large-scale benchmark datasets. In this paper, we carry…

We address the problem of activity detection in continuous, untrimmed video streams. This is a difficult task that requires extracting meaningful spatio-temporal features to capture activities, accurately localizing the start and end times…

Shot boundary detection (SBD) is an important pre-processing step for video manipulation. Here, each segment of frames is classified as either sharp, gradual or no transition. Current SBD techniques analyze hand-crafted features and attempt…

Visual surveillance aims to perform robust foreground object detection regardless of the time and place. Object detection shows good results using only spatial information, but foreground object detection in visual surveillance requires…

The encoding of the target in object tracking moves from the coarse bounding-box to fine-grained segmentation map recently. Revisiting de facto real-time approaches that are capable of predicting mask during tracking, we observed that they…

Temporally localizing actions in a video is a fundamental challenge in video understanding. Most existing approaches have often drawn inspiration from image object detection and extended the advances, e.g., SSD and Faster R-CNN, to produce…

Video anomaly detection (VAD) is crucial in scenarios such as surveillance and autonomous driving, where timely detection of unexpected activities is essential. Although existing methods have primarily focused on detecting anomalous objects…

In low-altitude surveillance and early warning systems, detecting weak moving targets remains a significant challenge due to low signal energy, small spatial extent, and complex background clutter. Existing methods struggle with extracting…

Handling missing data in time series classification remains a significant challenge in various domains. Traditional methods often rely on imputation, which may introduce bias or fail to capture the underlying temporal dynamics. In this…

Autonomous driving requires an accurate and fast 3D perception system that includes 3D object detection, tracking, and segmentation. Although recent low-cost camera-based approaches have shown promising results, they are susceptible to poor…

Normalization like Batch Normalization (BN) is a milestone technique to normalize the distributions of intermediate layers in deep learning, enabling faster training and better generalization accuracy. However, in fidelity image…