Related papers: Leveraging Multimodal LLM Descriptions of Activity…
Recent Multimodal Large Language Models (MLLMs) have demonstrated significant progress in perceiving and reasoning over multimodal inquiries, ushering in a new research era for foundation models. However, vision-language misalignment in…
Video Anomaly Detection (VAD) has traditionally been framed as binary classification or outlier detection, providing neither interpretable reasoning nor precise spatial localization of anomalous events. While Vision-Language Models (VLMs)…
We tackle the complex problem of detecting and recognising anomalies in surveillance videos at the frame level, utilising only video-level supervision. We introduce the novel method AnomalyCLIP, the first to combine Large Language and…
Language-based object detection (LOD) aims to align visual objects with language expressions. A large amount of paired data is utilized to improve LOD model generalizations. During the training process, recent studies leverage…
Anomaly detection in videos has been attracting an increasing amount of attention. Despite the competitive performance of recent methods on benchmark datasets, they typically lack desirable features such as modularity, cross-domain…
Vision-Language Models (VLMs) offer the ability to generate high-level, interpretable descriptions of complex activities from images and videos, making them valuable for situational awareness (SA) applications. In such settings, the focus…
Anomaly detection is vital in various industrial scenarios, including the identification of unusual patterns in production lines and the detection of manufacturing defects for quality control. Existing techniques tend to be specialized in…
Anomaly analysis in surveillance videos is a crucial topic in computer vision. In recent years, multimodal large language models (MLLMs) have outperformed task-specific models in various domains. Although MLLMs are particularly versatile,…
Recently, the remarkable success of large language models (LLMs) has achieved a profound impact on the field of artificial intelligence. Numerous advanced works based on LLMs have been proposed and applied in various scenarios. Among them,…
Vision-language models (VLMs) have recently emerged as a promising paradigm for video anomaly detection (VAD) due to their strong visual reasoning ability and natural language-based explainability. In this paper, we aim to address a key…
Robotic manipulation, a key frontier in robotics and embodied AI, requires precise motor control and multimodal understanding, yet traditional rule-based methods fail to scale or generalize in unstructured, novel environments. In recent…
Semantic segmentation networks have achieved significant success under the assumption of independent and identically distributed data. However, these networks often struggle to detect anomalies from unknown semantic classes due to the…
The practical deployment of Visual Anomaly Detection (VAD) systems is hindered by their sensitivity to real-world imaging variations, particularly the complex interplay between viewpoint and illumination which drastically alters defect…
Multi-task learning based video anomaly detection methods combine multiple proxy tasks in different branches to detect video anomalies in different situations. Most existing methods either do not combine complementary tasks to effectively…
Multimodal large language models (MLLMs) demonstrate remarkable capabilities in handling complex multimodal tasks and are increasingly adopted in video understanding applications. However, their rapid advancement raises serious data privacy…
Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs) to integrate visual and textual information. This paper presents a comprehensive analysis of…
Group activity detection (GAD) aims to simultaneously identify group members and categorize their collective activities within video sequences. Existing deep learning-based methods develop specialized architectures (e.g., transformer…
The increasing availability of traffic videos functioning on a 24/7/365 time scale has the great potential of increasing the spatio-temporal coverage of traffic accidents, which will help improve traffic safety. However, analyzing footage…
When applying pre-trained large language models (LLMs) to address anomaly detection tasks, the multivariate time series (MTS) modality of anomaly detection does not align with the text modality of LLMs. Existing methods simply transform the…
What makes good representations for video understanding, such as anticipating future activities, or answering video-conditioned questions? While earlier approaches focus on end-to-end learning directly from video pixels, we propose to…