Related papers: Holmes-VAU: Towards Long-term Video Anomaly Unders…
While vision-language models (VLMs) excel at tasks involving single images or short videos, they still struggle with Long Video Question Answering (LVQA) due to its demand for complex multi-step temporal reasoning. Vanilla approaches, which…
Vision-language models (VLMs) have demonstrated impressive multimodal comprehension capabilities and are being deployed in an increasing number of online video understanding applications. While recent efforts extensively explore advancing…
Facial Action Unit (AU) detection in in-the-wild environments remains a formidable challenge due to severe spatial-temporal heterogeneity, unconstrained poses, and complex audio-visual dependencies. While recent multimodal approaches have…
Video object segmentation (VOS) aims to distinguish and track target objects in a video. Despite the excellent performance achieved by off-the-shell VOS models, existing VOS benchmarks mainly focus on short-term videos lasting about 5…
As industrial manufacturing scales, automating fine-grained product image analysis has become critical for quality control. However, existing approaches are hindered by limited dataset coverage and poor model generalization across diverse…
Partially relevant video retrieval aims to retrieve untrimmed videos using text queries that describe only partial content. However, the inherent asymmetry between brief queries and rich video content inevitably introduces uncertainty into…
Unmanned aerial vehicles (UAVs) are widely applied for purposes of inspection, search, and rescue operations by the virtue of low-cost, large-coverage, real-time, and high-resolution data acquisition capacities. Massive volumes of aerial…
Recent studies have shown that agent-based systems leveraging large language models (LLMs) for key information retrieval and integration have emerged as a promising approach for long video understanding. However, these systems face two…
In this paper, we propose $\text{HF}^2$-VAD, a Hybrid framework that integrates Flow reconstruction and Frame prediction seamlessly to handle Video Anomaly Detection. Firstly, we design the network of ML-MemAE-SC (Multi-Level Memory modules…
In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a…
Deep learning algorithms have pushed the boundaries of computer vision research and have depicted commendable performance in a variety of applications. However, training a robust deep neural network necessitates a large amount of labeled…
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…
Social video anomaly is an observation in video streams that does not conform to a common pattern of dataset's behaviour. Social video anomaly detection plays a critical role in applications from e-commerce to e-learning. Traditionally,…
Video understanding in multimodal language models remains limited by context length: models often miss key transition frames and struggle to maintain coherence across long time scales. To address this, we adapt Native Sparse Attention (NSA)…
Understanding long-form videos remains a significant challenge for vision--language models (VLMs) due to their extensive temporal length and high information density. Most current multimodal large language models (MLLMs) rely on uniform…
Video anomaly detection (VAD) is an essential task in the image processing community with prospects in video surveillance, which faces fundamental challenges in balancing detection accuracy with computational efficiency. As video content…
Human-centric Video Anomaly Detection (VAD) aims to identify human behaviors that deviate from normal. At its core, human-centric VAD faces substantial challenges, such as the complexity of diverse human behaviors, the rarity of anomalies,…
Video anomaly detection (VAD) aims to detect anomalies that deviate from what is expected. In open-world scenarios, the expected events may change as requirements change. For example, not wearing a mask may be considered abnormal during a…
Long video understanding presents challenges due to the inherent high computational complexity and redundant temporal information. An effective representation for long videos must efficiently process such redundancy while preserving…
Video Large Language Models (Video LLMs) have recently exhibited remarkable capabilities in general video understanding. However, they mainly focus on holistic comprehension and struggle with capturing fine-grained spatial and temporal…