相关论文: Video Labeling for Automatic Video Surveillance in…

Machine learning has been utilized to perform tasks in many different domains such as classification, object detection, image segmentation and natural language analysis. Data labeling has always been one of the most important tasks in…

While huge volumes of unlabeled data are generated and made available in many domains, the demand for automated understanding of visual data is higher than ever before. Most existing machine learning models typically rely on massive amounts…

Large vision-language models (VLMs) achieve strong performance in Visual Question Answering but still rely heavily on supervised fine-tuning (SFT) with massive labeled datasets, which is costly due to human annotations. Crucially,…

This paper proposes VLA-AN, an efficient and onboard Vision-Language-Action (VLA) framework dedicated to autonomous drone navigation in complex environments. VLA-AN addresses four major limitations of existing large aerial navigation…

Existing work on object detection often relies on a single form of annotation: the model is trained using either accurate yet costly bounding boxes or cheaper but less expressive image-level tags. However, real-world annotations are often…

The remarkable growth of unmanned aerial vehicles (UAVs) has also sparked concerns about safety measures during their missions. To advance towards safer autonomous aerial robots, this work presents a vision-based solution to ensuring safe…

This paper presents the watch-from-sky framework, where multiple unmanned aerial vehicles (UAVs) play four roles, i.e., sensing, data forwarding, computing, and patrolling, for predictive police surveillance. Our framework is promising for…

The rapid advancement of vision-language models (VLMs) has established a new paradigm in video anomaly detection (VAD): leveraging VLMs to simultaneously detect anomalies and provide comprehendible explanations for the decisions. Existing…

Unmanned Aerial Vehicles (UAVs) or drones are being introduced in a wide range of commercial applications. This has also made them prime targets of attackers who compromise their fundamental security properties, including confidentiality,…

Crowd monitoring in sports stadiums is important to enhance public safety and improve the audience experience. Existing approaches mainly rely on cameras and microphones, which can cause significant disturbances and often raise privacy…

In unsupervised domain adaptation (UDA), classifiers for the target domain (TD) are trained with clean labeled data from the source domain (SD) and unlabeled data from TD. However, in the wild, it is difficult to acquire a large amount of…

We present LAVA, a simple yet effective method for multi-domain visual transfer learning with limited data. LAVA builds on a few recent innovations to enable adapting to partially labelled datasets with class and domain shifts. First, LAVA…

Video anomaly detection (VAD) has been paid increasing attention due to its potential applications, its current dominant tasks focus on online detecting anomalies% at the frame level, which can be roughly interpreted as the binary or…

Static image action recognition, which aims to recognize action based on a single image, usually relies on expensive human labeling effort such as adequate labeled action images and large-scale labeled image dataset. In contrast, abundant…

Vision-Language-Action models (VLAs) represent a significant frontier in embodied intelligence, aiming to bridge digital knowledge with physical-world interaction. Despite their remarkable performance, foundational VLAs are hindered by the…

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…

Unsupervised domain adaptation (UDA) has been a potent technique to handle the lack of annotations in the target domain, particularly in semantic segmentation task. This study introduces a different UDA scenarios where the target domain…

Occlusion is a longstanding difficulty that challenges the UAV-based object detection. Many works address this problem by adapting the detection model. However, few of them exploit that the UAV could fundamentally improve detection…

Autonomous tracking of flying aerial objects has important civilian and defense applications, ranging from search and rescue to counter-unmanned aerial systems (counter-UAS). Ground based tracking requires setting up infrastructure, could…

Audio-Visual Video Parsing (AVVP) entails the challenging task of localizing both uni-modal events (i.e., those occurring exclusively in either the visual or acoustic modality of a video) and multi-modal events (i.e., those occurring in…