Related papers: DeepSVU: Towards In-depth Security-oriented Video …
This report provides a comprehensive overview of the 4th Pixel-level Video Understanding in the Wild (PVUW) Challenge, held in conjunction with CVPR 2025. It summarizes the challenge outcomes, participating methodologies, and future…
With the advancement of multi-modal Large Language Models (LLMs), Video LLMs have been further developed to perform on holistic and specialized video understanding. However, existing works are limited to specialized video understanding…
The evaluation of Long Video Understanding (LVU) performance poses an important but challenging research problem. Despite previous efforts, the existing video understanding benchmarks are severely constrained by several issues, especially…
With increasing physical threats in recent years targeted at critical infrastructures, it is crucial to establish a reliable threat monitoring system integrating video surveillance and digital sensors based on cutting-edge technologies. A…
Comprehending long videos remains a significant challenge for Large Multi-modal Models (LMMs). Current LMMs struggle to process even minutes to hours videos due to their lack of explicit memory and retrieval mechanisms. To address this…
Reinforcement Learning with Verifiable Rewards (RLVR) has substantially advanced the video understanding capabilities of Multimodal Large Language Models (MLLMs). However, the rapid progress of MLLMs is outpacing the complexity of existing…
We propose the Multi-modal Untrimmed Video Retrieval task, along with a new benchmark (MUVR) to advance video retrieval for long-video platforms. MUVR aims to retrieve untrimmed videos containing relevant segments using multi-modal queries.…
Human-centric Point Cloud Video Understanding (PVU) is an emerging field focused on extracting and interpreting human-related features from sequences of human point clouds, further advancing downstream human-centric tasks and applications.…
Recent studies have demonstrated the effectiveness of Large Language Models (LLMs) as reasoning modules that can deconstruct complex tasks into more manageable sub-tasks, particularly when applied to visual reasoning tasks for images. In…
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…
The recent advent of Large Language Models (LLMs) has ushered sophisticated reasoning capabilities into the realm of video through Video Large Language Models (VideoLLMs). However, VideoLLMs currently rely on a single vision encoder for all…
While the safety risks of image-based large language models (Image LLMs) have been extensively studied, their video-based counterparts (Video LLMs) remain critically under-examined. To systematically study this problem, we introduce…
Video Moment Retrieval (MR) and Highlight Detection (HD) have attracted significant attention due to the growing demand for video analysis. Recent approaches treat MR and HD as similar video grounding problems and address them together with…
Current state-of-the-art object detection and segmentation methods work well under the closed-world assumption. This closed-world setting assumes that the list of object categories is available during training and deployment. However, many…
This report summarizes the objectives, datasets, and top-performing methodologies of the 2026 Pixel-level Video Understanding in the Wild (PVUW) Challenge, hosted at CVPR 2026, which evaluates state-of-the-art models under highly…
Despite the recent advances in unified image segmentation (IS), developing a unified video segmentation (VS) model remains a challenge. This is mainly because generic category-specified VS tasks need to detect all objects and track them…
Pixel-level Video Understanding in the Wild Challenge (PVUW) focus on complex video understanding. In this CVPR 2024 workshop, we add two new tracks, Complex Video Object Segmentation Track based on MOSE dataset and Motion Expression guided…
Recently, driven by advancements in Multimodal Large Language Models (MLLMs), Vision Language Action Models (VLAMs) are being proposed to achieve better performance in open-vocabulary scenarios for robotic manipulation tasks. Since…
Large Language Models (LLMs) have allowed recent LLM-based approaches to achieve excellent performance on long-video understanding benchmarks. We investigate how extensive world knowledge and strong reasoning skills of underlying LLMs…
Video Anomaly Understanding (VAU) is a novel task focused on describing unusual occurrences in videos. Despite growing interest, the evaluation of VAU remains an open challenge. Existing benchmarks rely on n-gram-based metrics (e.g., BLEU,…