相关论文: MEVA: A Large-Scale Multiview, Multimodal Video Da…

Despite significant breakthroughs in video analysis driven by the rapid development of large multimodal models (LMMs), there remains a lack of a versatile evaluation benchmark to comprehensively assess these models' performance in video…

Nowadays, short-form videos (SVs) are essential to web information acquisition and sharing in our daily life. The prevailing use of SVs to spread emotions leads to the necessity of conducting video emotion analysis (VEA) towards SVs.…

We present HourVideo, a benchmark dataset for hour-long video-language understanding. Our dataset consists of a novel task suite comprising summarization, perception (recall, tracking), visual reasoning (spatial, temporal, predictive,…

There are substantial instructional videos on the Internet, which enables us to acquire knowledge for completing various tasks. However, most existing datasets for instructional video analysis have the limitations in diversity and…

Idle animations are essential for virtual characters, as they convey realistic behaviour during inactive states. While automatic animation generation has been widely studied, limited attention has been given to idle motion due to the…

We introduce Human-like Video Models (HVM-1), large-scale video models pretrained with nearly 5000 hours of curated human-like video data (mostly egocentric, temporally extended, continuous video recordings), using the spatiotemporal masked…

In this era, the success of large language models and text-to-image models can be attributed to the driving force of large-scale datasets. However, in the realm of 3D vision, while remarkable progress has been made with models trained on…

We present a new public dataset with a focus on simulating robotic vision tasks in everyday indoor environments using real imagery. The dataset includes 20,000+ RGB-D images and 50,000+ 2D bounding boxes of object instances densely captured…

Spatio-temporal action detection is an important and challenging problem in video understanding. However, the application of the existing large-scale spatio-temporal action datasets in specific fields is limited, and there is currently no…

Automatic detection of natural disasters and incidents has become more important as a tool for fast response. There have been many studies to detect incidents using still images and text. However, the number of approaches that exploit…

Despite the significant impact of visual events on human cognition, understanding events in videos remains a challenging task for AI due to their complex structures, semantic hierarchies, and dynamic evolution. To address this, we propose…

Video understanding with multimodal large language models (MLLMs) remains challenging due to the long token sequences of videos, which contain extensive temporal dependencies and redundant frames. Existing approaches typically treat MLLMs…

Event cameras, with their high temporal and dynamic range and minimal memory usage, have found applications in various fields. However, their potential in static traffic monitoring remains largely unexplored. To facilitate this exploration,…

In this era, the success of large language models and text-to-image models can be attributed to the driving force of large-scale datasets. However, in the realm of 3D vision, while significant progress has been achieved in object-centric…

Current developments in temporal event or action localization usually target actions captured by a single camera. However, extensive events or actions in the wild may be captured as a sequence of shots by multiple cameras at different…

Unmanned Aerial Vehicles (UAVs) offer wide-ranging applications but also pose significant safety and privacy violation risks in areas like airport and infrastructure inspection, spurring the rapid development of Anti-UAV technologies in…

Understanding events in texts is a core objective of natural language understanding, which requires detecting event occurrences, extracting event arguments, and analyzing inter-event relationships. However, due to the annotation challenges…

Recognizing the motion of Micro Aerial Vehicles (MAVs) is crucial for enabling cooperative perception and control in autonomous aerial swarms. Yet, vision-based recognition models relying only on RGB data often fail to capture the complex…

Activity detection in security videos is a difficult problem due to multiple factors such as large field of view, presence of multiple activities, varying scales and viewpoints, and its untrimmed nature. The existing research in activity…

Autonomous driving, particularly navigating complex and unanticipated scenarios, demands sophisticated reasoning and planning capabilities. While Multi-modal Large Language Models (MLLMs) offer a promising avenue for this, their use has…